DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Information Disclosure Statement
The listing of references in the specification, e.g., at pages 3, 4, 33 and 34 is not a proper information disclosure statement. 37 CFR 1.98(b) requires a list of all patents, publications, or other information submitted for consideration by the Office, and MPEP § 609.04(a) states, “the list may not be incorporated into the specification but must be submitted in a separate paper.” Therefore, unless the references have been cited by the examiner on form PTO-892, have been indicated by Applicant on the IDS received 7 April 2024, or have been indicated on a search report, opinion, or other submitted PCT document, they have not been considered.
Drawings
37 C.F.R. 1.97(u)(1)-(2) read as follows:
(1) The different views must be numbered in consecutive Arabic numerals, starting with 1, independent of the numbering of the sheets and, if possible, in the order in which they appear on the drawing sheet(s). Partial views intended to form one complete view, on one or several sheets, must be identified by the same number followed by a capital letter. View numbers must be preceded by the abbreviation "FIG." Where only a single view is used in an application to illustrate the claimed invention, it must not be numbered and the abbreviation "FIG." must not appear.
(2) Numbers and letters identifying the views must be simple and clear and must not be used in association with brackets, circles, or inverted commas. The view numbers must be larger than the numbers used for reference characters.
The drawings are objected to because each view is labeled using the term “Figure”, e.g., “Figure 1”, and must be preceded by the abbreviation “FIG.”
The drawings are objected to because partial views 12a - 12d of Figure 12 are not capitalized, i.e., 12A, 12B, 12C and 12D.
The drawings should be amended in the manner of “FIG. 1, FIG. 2, FIG. 3” and so on for figures without partial views, and in the manner of “FIG. 12A, FIG. 12B, FIG. 12C and FIG. 12D” for those with partial views. The corresponding changes should also be made in the specification.
Figure 3 and Figures 12a - 12d should be designated by a legend such as --Prior Art-- because only that which is old is illustrated. See MPEP § 608.02(g). The background section, which sets forth what is relevant and known from the prior art, spans line 12 on page 1 through line 3 on page 8.
Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Specification
The disclosure is objected to because the heading “Brief Summary of the Invention” should be inserted between “present invention.” and “According to the invention” on page 8 of the specification. See 37 CFR 1.77(b).
The disclosure is objected to because the specification, primarily in line 11 on page 1 through line 10 on page 13 of the specification, ambiguously describes what is known in the prior art and what is being disclosed by the instant application, making it difficult to accurately parse any admissions of prior art from disclosure of the claimed embodiments. For example, Figures 12a-c are described on page 6 as being part of the prior art, but are not provided with a “Prior Art” label in the drawings.
The disclosure is also objected to because the numbering of the partial views of Figure 12 in the specification is inconsistent with the drawings, e.g., “12-c” on page 6 of the specification compared to “12c” in the drawings.
The abstract of the disclosure is objected to because it is not a concise statement of the technical disclosure. The first two sentences can be simplified, for example, as “A method and system for contouring an image for display comprises providing at least ...” The text should be readily understood without needing to refer to the detailed description. For example, without reading the specification, “the medical image” is confusing because earlier the abstract mentions “an image for display” and not “a medical image”. A corrected abstract of the disclosure is required and must be presented on a separate sheet, apart from any other text. See MPEP § 608.01(b).
Claim Interpretation
According to the Federal Circuit’s decision in SuperGuide v. DirecTV, claim language of the type “at least one of … and …” and “at least one of the local image intensities and spatial information of the image” creates a presumption that applicant intended the plain and ordinary meaning of the claim language to be a conjunctive list, unless the specification supports an interpretation of the claim language that rebuts the presumption.1
Claims 32, 33, 35, 36, 42, 46, 49 and 51 recite limitations that raise the presumption of a conjunctive list per SuperGuide. Despite slight variations in wording, these claims recite limitations in the form of “at least one of the parameters W and L”. The specification, for example at lines 24-31 on page 3 and lines 14-20 on page 31, describes the parameters W and L as being separately definable, which supports an interpretation of the limitations having the form above as being disjunctive lists. Therefore, Applicant successfully rebuts the presumption that “at least one of the parameters W and L” is a conjunctive list of parameters. Accordingly, “at least one of the parameters W and L” and the like is interpreted as only requiring one of W and L at a minimum.
Claim 42 recites “at least one of the local image intensities and spatial information of the image”. Comparing lines 14-15 on page 10 of the specification with lines 24-25 on page 31 suggests that including both types of information is optional, which supports an interpretation as a disjunctive list. Therefore, Applicant successfully rebuts the presumption that “at least one of the local image intensities and spatial information of the image” is a conjunctive list of information used by the machine learning algorithm, and is therefore interpreted as only requiring one type of information at a minimum.
Claim Objections
Claim 32 is objected to because of the following informalities:
“contour is generated; according to the determined local image intensity” should be changed to “contour is generated[[;]], according to the determined local image intensity” for clarity.
“and adjusting at least one” should be changed to “[[and]] adjusting at least one” since the “and” is redundant with “and displaying the medical image”.
Claim 33 is objected to because of the following informalities:
“and adjusting at least one” should be changed to “[[and]] adjusting at least one” since the “and” is redundant with “and displaying the medical image...”.
Claims 34-50 are objected to because of the following informalities:
beginning each claim with “A method as in claim ...” could create ambiguity as to whether the full scope of each parent claim is included. To avoid that ambiguity, “A method” should be changed to “[[A]] The method”.
Claim 39 is objected to because of the following informalities:
“A method as in any of claim 32” should be changed to “[[A]] The method as in
Claim 42 is objected to because of the following informalities:
“suitably” should be changed to “suitability” because “the suitably” is confusing and appears to be a typo.
Claim 43 is objected to because of the following informalities:
the comma included in the phrase “part of the contour, or a part of the contour for review” should be removed because a comma preceding the conjunction “or” does not typically appear in lists of only two elements instead of the usual three or more elements, i.e., “A, B, or C”. Removing the comma would make the claim easier to understand.
Claim 45 is objected to because of the following informalities:
“A method as claim 32” should be written as “[[A]] The method of [[as]] claim 32” for clarity. All dependent claims should follow this format.
Claim 49 is objected to because of the following informalities:
“are one of the following:” should be changed to “[[are]] is one or more of the following:” to be consistent with “at least one” and the specification at lines 19-22 of page 11 and lines 12-15 of page 21.
Claim 51 is objected to because of the following informalities:
there should be an instance of “and” between “to be contoured;” and “a processor” to improve clarity.
“contour is generated; according to the determined local image intensity” should be changed to “contour is generated[[;]], according to the determined local image intensity” for clarity.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
Claims 32-51 are rejected under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention.
Claim 32 recites, “a most recently generated position on the contour” and “the most recently generated position on the contour”, and claim 43 recites, “the most recently generated part of the contour” and “a part of the contour for review” (emphasis added). The term “part” in claim 43 is assumed to be a misspelling of “position”, otherwise it is confusing and would possibly necessitate a rejection under 35 U.S.C. 112(b). The term “most recently” is confusing. After consulting the specification, it appears more likely that the term “currently” is more appropriate than “most recently” and creates less confusion if substituted in the claim. For purposes of applying prior art, “part” means “position” and “most recently” means “current”.
Claims 32, 33 and 51 each recite “the determined local image intensity” respectively preceded by “determining local image intensities of the at least one medical image for each position of the contour”, “determining local image intensities of the at least one medical image for at least one portion of the selected contour to be reviewed” and “determining the local image intensities of the at least one medical image for each position of the contour”. The phrase “the determined local image intensity” lacks antecedent basis because it is unclear which intensity amongst the “intensities” corresponds to “the intensity”. For purposes of applying prior art, “image intensity” is interpreted as “image intensities” in each claim and specific to claim 51, “the local image intensities” is interpreted as “[[the]] local image intensities”.
Claims 32 and 51 recite, “each position of the contour”. There is no preceding recitation of a “position” in claim 32 and “the start position” in claim 51 is only one position. Therefore, the antecedent basis is ambiguous. For purposes of applying prior art, it is assumed “the contour” includes a plurality of positions and “each position” refers to each position of the plurality of positions.
Claim 32 recites, “for each position of the contour” preceded by “one or more structures to be contoured”. There is no specific number of contours specified or implied in the claim. Thus, the antecedent basis of “the contour” is ambiguous. For purposes of applying prior art, “the contour” is interpreted as “[[the]] a contour”. Dependent claims 37 and 38 are rejected for inheriting and not curing the deficiencies of claim 33.
Claim 33 recites, “the further section of the contour position”. The claim does not explicitly recite any other “sections”. Thus, the antecedent basis of “the further section” is ambiguous. Claim 33 also recites, “the current window”, which lacks a clear antecedent basis. For purposes of applying prior art, “the further section” is interpreted as “[[the]] a further section” and “the current window” is interpreted as “[[the]] a current window”. Dependent claims 37 and 38 are rejected for inheriting and not curing the deficiencies of claim 33.
Claim 34 recites, “until the one or more structures to be contoured have been contoured”. The state of “being contoured” is ambiguous and not explicitly defined or described. Thus, it is unclear what condition(s) must be present for the repetition of “the contouring steps” to cease. For purposes of applying prior art, claim 34 is interpreted as meaning the repetition stops when a condition related to “the one or more structures” is satisfied.
Claims 35 and 36 each recite, “the at least one portion”. Claim 32 does not explicitly recite any “portion”. Therefore, “the at least one portion” lacks a clear antecedent basis. For purposes of applying prior art, “portion” is interpreted to be “position”.
The preamble of claim 37 includes “the contour review step of:”. However, on its face, claim 37 recites a detecting step and a reviewing step. The placement of the semicolon makes it unclear whether “the step” includes just the “detecting” or the “reviewing” as well. For purposes of applying prior art, “the step” is assumed to encompass both the “detecting” and the “reviewing” as part of the “contour review steps” of claim 33.
Claim 38 recites, “the step of editing or correcting one or more contour portions after the detected contour portions have been reviewed.” It is unclear if “the step of editing or correcting” refers to a single step that considers two alternatives or two separate alternatives. Furthermore, the distinction between “editing” and “correcting” is unclear. Still further, claim 33 does not explicitly reciting “detecting” contour portions, which makes the meaning of “after” ambiguous. For purposes of applying prior art, based on the specification at line 12 on page 2, the phrase “editing or correcting” is interpreted as being equivalent to “modifying” and the phrase “the step of” is interpreted as not being included in the claim.
The preamble of claim 39 includes “the step of:”. However, on its face, claim 39 recites a determining step, a providing step, and a suggesting step. Accordingly, “the step” lacks a clear antecedent basis. If it is assumed that the body of the claim is referring to determining whether the parameters are suitable or not suitable for the current task, in the event they are not suitable, the providing and suggesting steps are performed. However, under the same interpretation, if the determination is that the parameters are suitable, the providing and suggesting steps are not performed or at least are not required by the prior art to be performed in order to rejected the claim under 35 U.S.C. 102 or 35 U.S.C. 103. For purposes of applying prior art, “the step” is interpreted to refer to a determination of suitability as explained above. Dependent claims 40 and 41 are rejected for inheriting and not curing the deficiencies of claim 39. The examiner suggests removing “the step of” from the preamble, though examiner notes: the claim interpretation provided above would still apply, i.e., the “providing” and “suggesting” steps (sub-steps) not required in the event the parameters are “suitable”.
The preamble of claim 43 includes “the step of:”. However, on its face, claim 43 recites a determining step and an assessing step. Accordingly, “the step” lacks a clear antecedent basis. For purposes of applying prior art, “the step” is interpreted to refer to both the “determining” and “assessing” steps (sub-steps). Dependent claim 44 is rejected for inheriting and not curing the deficiencies of claim 43. The examiner suggests removing “the step of” from the preamble
Claim 44 provides a list of claim elements separated by semicolons without a conjunction separating the last two claim elements, e.g., “or” or “and”. In the event “and” was the original intent, claim 44 would be subject to analysis under Superguide Corp. v. Direct TV Enterprises, Inc., 358 F.3d 870, 69 USPQ2d 1865 (Fed. Cir. 2004). In the event “or” was the original intent, claim 44 would not be subject to analysis under Superguide. Thus, the scope of claim 44 is ambiguous. For purposes of applying prior art, based on the specification at lines 14-20 on page 31, claim 44 is interpreted as including the term “or” between “a configurable percentile of intensities;” and “statistical measures”.
Claim 45 recites, “the current W, L parameters”, which lacks antecedent basis because there is no explicit recitation of “current” parameters. For purposes of applying prior art, “the current W, L parameters” is interpreted as “[[the]] current W, L parameters”.
Claim 46 provides a list of claim elements separated by semicolons without a conjunction separating the last two claim elements, e.g., “or” or “and”. In the event “and” was the original intent, claim 46 would be subject to analysis under Superguide. In the event “or” was the original intent, claim 46 would not be subject to analysis under Superguide. Furthermore, it is unclear whether “an interactive mechanism such as a mouse click, a keyboard hotkey or voice control” is meant to be “one” of the “one or more of” in the preamble, or three separate things, e.g., a mouse click, a keyboard hotkey or a voice control. Still further, the phrase “such as” renders the claim indefinite because it is unclear whether the limitations following the phrase are part of the claimed invention. See MPEP § 2173.05(d). Thus, the scope of claim 46 is ambiguous. For purposes of applying prior art, based on the specification at line 24 on page 32 through line 8 on page 33, claim 46 is interpreted as not including the phrase “such as” and including the term “or” between “a mouse hover over a region of the image or the contour;” and “an interactive mechanism”.
Claim 47 provides a list of claim elements separated by semicolons without a conjunction separating the last two claim elements, e.g., “or” or “and”. In the event “and” was the original intent, claim 47 would be subject to analysis under Superguide. In the event “or” was the original intent, claim 47 would not be subject to analysis under Superguide. Thus, the scope of claim 47 is ambiguous. For purposes of applying prior art, based on the specification at lines 1-23 on page 32, claim 47 is interpreted as including the term “or” between “style or thickness of the contour being generated or edited;” and “a change in the colour of the region around the contour being generated”.
Claim 48 recites, “after editing or generation of a contour has been completed the steps are repeated so that a plurality of contours are created or reviewed on a medical image”. Claim 32 recites several steps. It is unclear which steps are specifically being referenced. Thus, the antecedent basis of “the steps” is ambiguous. Additionally, it is unclear how steps of claim 32 can be repeated so that a plurality of contours are “created” or “reviewed” because claim 32 does not explicitly recite any “creating” or “reviewing”. The term “creating” is assumed to be equivalent to “contouring”. Furthermore, the phrase “after editing” is ambiguous because claims 32 and 48 do not explicitly recite any “editing”. For purposes of applying prior art, claim 48 is interpreted to mean that the “contour steps” are repeated and a second contour is generated as a result.
Claim 49 recites, “the start of the contouring or reviewing process”, “a previous use of the system” and “parameters of the stored image”. Claim 32 does not explicitly recite any “start” or “reviewing” process, “system” or “stored image”. Thus, the phrases “the start of the contouring or reviewing process”, “the system” and “parameters of the stored image” lack antecedent basis. For purposes of applying prior art, claim 49 is interpreted as not reciting “at the start of the contouring or reviewing process”, “set from a previous use of the system;” and “user configured or defined from parameters of the stored image”. Furthermore, “at least one of ... are one of the following” is confusing because the term “is” should follow “at least one”. The phrase “at least one” means “one or more” and the term “are” contradicts that. Still further, claim 49 provides a list of claim elements separated by semicolons without a conjunction separating the last two claim elements, e.g., “or” or “and”. In the event “and” was the original intent, claim 49 would be subject to analysis under Superguide. In the event “or” was the original intent, claim 49 would not be subject to analysis under Superguide. Thus, the scope of claim 49 is ambiguous. For purposes of applying prior art, based on the specification at lines 8-28 on page 21, claim 49 is interpreted as including the term “or” between “set from a previous use of the system;” and “user configured”.
Claim 50 recites, “A method as in claim 1”. Claim 1 is canceled. Thus is it unclear which parent claim is intended to be further limited by claim 50. For purposes of applying prior art, claim 50 is treated as depending from claim 32. Therefore, dependent claim 50 is rejected for inheriting and not curing the deficiencies of claim 32 noted above.
Claim 51 recites, “the correct value for the start position of the contour”. The preceding limitations do not explicitly recite a correct value, position, or contour. Therefore, “the correct value”, “the start position” and “the contour” lack antecedent basis. Additionally, “the display device” lacks a clear antecedent basis because a “display” and not a “display device” is recited in the claim. For purposes of applying prior art, “the correct value for the start position of the contour” is interpreted as “[[the]] a correct value for [[the]] a start position of [[the]] a contour”, and “the display device” is interpreted as “the display
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 32-51 are rejected under 35 U.S.C. 101 because the claimed inventions are directed to a judicial exception without significantly more.
[Claim 32] A method for contouring a medical image that is displayed on (k) a display device, comprising the steps of:
(a) providing at least one medical image with one or more structures to be contoured;
(b) providing a window width parameter, W, and a window level parameter, L for the at least one medical image;
(c) displaying the medical image according to the W,L parameters;
(d) performing the following contouring steps:
(e) determining local image intensities of the at least one medical image for each position of the contour, as the contour is generated for a structure on the image;
(f) determining if the window width parameter, W, and the window level parameter, L, are suitable for contouring for each position of the contour on the medical image as the contour is generated; according to the determined local image intensity;
(g) if at least one of the parameters is not suitable for contouring, providing an alert that at least one of the parameters W and L is not suitable for a most recently generated position on the contour; and
(h) adjusting at least one of the window width parameter, W, and the window level parameter, L to be suitable for contouring of the structure for the most recently generated position on the contour; and displaying the medical image according to the adjusted W,L settings.
[Claim 33] A method for reviewing a previously contoured medical image that is displayed on (k) a display device, comprising the steps of:
(a) providing at least one medical image and at least one contour on the medical image to be reviewed;
(b) providing a window width parameter, W, and a window level parameter, L for the at least one medical image;
(c) displaying the medical image according to the W, L parameters and displaying the at least one contour;
(j) selecting at least one contour on the previously contoured image for review;
(d) performing the following contour review steps:
(e) determining local image intensities of the at least one medical image for at least one portion of the selected contour to be reviewed;
(f) determining that at least one of the current window width parameter W and window level parameter L are not suitable for reviewing the at least one portion of the at least one contour, according to the determined local image intensity;
(g) providing an alert that at least one of the parameters W and L are not suitable for reviewing the at least one portion of the contour; and
(h) adjusting at least one of the window width parameter, W, and the window level parameter, L, to be suitable for reviewing the at least one portion of the contour; reviewing the further section of the contour portion using the adjusted parameters; and (i) displaying the medical image according to the adjusted W,L settings.
[Claim 51] A system for analysing a medical image comprising:
(k) a display for (c) displaying at least one medical image to be contoured;
(l) a processor for (b) setting a window width parameter, W, and a window level parameter, L, for the display device to the correct value for the start position of the contour for a structure on the at least one medical image to be contoured;
(l) the processor (e) determining the local image intensities of the at least one medical image for each position of the contour, as the contour is generated;
(l) the processor (f) determining if the window width parameter, W, and the window level parameter, L, are correct for each position of the contour on the medical image as the contour is generated; according to the determined local image intensity;
(g) if at least one of the parameters is not correct, alerting the user that at least one of the parameters W and L is not correct for a current position on the contour; and
(h) adjusting at least one of the window width parameter, W, and the window level parameter, L to be correct for the current position on the contour.
Claim Interpretation
Under the broadest reasonable interpretation, the terms of the claims are presumed to have their plain meaning consistent with the specification as it would be interpreted by one of ordinary skill in the art. See MPEP 2111. Corresponding groups of claim limitations between each independent claim are assigned a common letter as indicated above for simplifying the analysis of all pending claims. Differences of actual recited claim terms for each of these limitations are noted below where necessary.
Limitations (a) - (j) recite or relate to the terms “contour”, “contoured” and “contouring”. These terms are recognized as having the plain meaning of detecting outlines or boundaries of objects within an image.
Claims 32 and 33 do not put any limits on the device or entity that causes limitations (a) - (i) to occur in the first place. Claims 32 and 33 are method claims including a series of steps. The preamble of each claim specifies that the medical image “is displayed on a display device”. There is no further reference to said display device in the claims and accordingly, no patentable weight is given. Even if patentable weight were given for the sake of argument, there is still no explicit connection between the display device and the recited steps. Limitations (c) and (i) could use the display of limitation (k), but the BRI does not require it.
Claim 51 is a system claim including a display and a processor. The display of limitation (k) performs limitation (c). However a display that displays an image is simply a generic display performing its generic function. The processor of limitation (l) is recited as determining (performing) limitations (e) - (h). However, the processor is differently described with respect to limitation (b), i.e., “a processor for setting a window width parameter ...” The language “for setting” implies that the processor is not actually determining the parameters and is merely being used for such determination by something or someone else. Relevantly, the specification provides several descriptions where a person (e.g., a clinician) is changing the settings. See e.g., “the clinician may need to change the (W,L) settings several times while contouring” on page 5, and regarding prior devices, “there is also the possibility for the user to freely and interactively (via a computer mouse for example) adjust the contrast of the displayed image. In other words, the user is setting a custom (W,L) parameters for the displayed image” on page 7. The BRI of limitation (l) encompasses a person merely using the processor as a tool and the specification describes similar concepts.
Although claim 51 differs from the method claims by explicitly reciting the processor as performing the “determining” of limitations (e) - (h), the BRI encompasses a person interacting with the processor, e.g., as user input to a GUI, and any division of the responsibility of actually determining or setting forth the functional aspects of those limitations between the implicit user and the explicitly recited processor. In other words, the user may determine not only the parameters W and L, but the local intensities, contour positions, parameter adjustments and so forth, and the processor simply performs those specific functions as instructed, or the user may have little to no involvement and nearly everything is automated.
The claimed providing, selecting, determining, performing, displaying and adjusting steps/functions encompass mental choices or evaluations, e.g., “suitable” or “correct” window parameters for an image object boundary.
Step 1: do the claims fall within any statutory category?
Claims 32 and 33 each recite a series of steps and is therefore a process. Claim 51 recites a system comprising a display and a processor, and is therefore a machine. See MPEP 2106.03. (Step 1: YES).
Step 2A, Prong One: do the claims recite a judicial exception?
Based on the claim interpretation above, limitations (a) - (j) fall within the mental process grouping of abstract ideas because they cover concepts performed in the human mind, including observation, evaluation, judgment, and opinion. See MPEP 2106.04(a)(2), subsection III.
The subject matter of limitations (a) - (j) describes the general nature of contouring or segmenting digital medical images, where a person such as a doctor, clinician, radiologist or the like uses software to interact with scans/images of a patient and adjust contrast and/or saturation to accentuate or diminish different pixels corresponding to different measurement values. Limitations (a) - (j) are reasonably interpreted as including manual (by-hand), unautomated acts and/or decisions made by a person who interacts with a generic computer having a display and displaying the medical image. Even though claim 51 explicitly recites the processor as performing the “determining” and at least being partly involved in “setting a window”, claims 51 as well as claims 32 and 33 are reasonably interpreted as describing the actions of a person using a computer as the end result of their internal mental decision making, judgments, and opinions, e.g., interaction of a person with a graphical user interface (GUI) or otherwise providing a input to a recited or implied processor.
The recitation of structural elements in limitations (k) and (l) does not negate the mental nature of these limitations because the claims merely use the structural components as tools to carry out the end result of the user’s mental process. See MPEP 2106.04(a)(2), subsection III.C.
Under the broadest reasonable interpretation, the claims 32, 33 and 51 describe the observations, evaluations, judgments, and opinions of a person interactively adjusting the contrast of a displayed medical image while assessing the edge features (contours) of a particular target object or feature, which falls within the mental process grouping of abstract ideas. See MPEP 2106.04(a)(2), subsection III. (Step 2A, Prong One: YES).
Step 2A, Prong Two: Do the claims as a whole integrate the recited judicial exception into a practical application of the exception?
Limitations (k) and (l) include additional elements: (i) a display device and (ii) a processor.
The additional element of (i) a display device is described as a generic computer component (e.g., a smartphone display (screen), laptop display, standalone monitor and the like) performing its generic function of displaying image data, is recited at a high level of generality, and does not amount to any of the relevant considerations for evaluating whether additional limitations integrate a judicial exception into a practical application provided in MPEP 2106.04(d), subsection I.
The additional element of (ii) a processor is described as performing limitations (b) and (e) - (h). As explained above, limitations (e) - (h) under the broadest reasonable interpretation, describe a person’s mental process of deciding how to next adjust the contrast of the medical image to reveal or suppress certain values. The additional element (ii) amounts to merely requiring instructions to implement the abstract idea on a computer or merely using a computer as a tool to perform the abstract idea. See MPEP 2106.05(f).
The additional elements (i)-(ii) implicitly invoke a general-purpose computer being merely used as a tool to perform an existing process: windowing or contrast enhancement or contrast stretching or grey-level mapping, particularly in CT and MRI scanning. See MPEP 2106.05(f)(2). Windowing is essentially displaying only a partial range of all the intensity values of an image while discarding the rest, typically by assigning values outside the selected range to be black or white. Windowing with multiple partial ranges simply repeats the same process for a different subset of the total collection of intensity values to enhance an image.
Limitation (b), which is performed by limitation (l) that includes the additional element of (ii) a processor, amounts to mere data gathering (of input values of settings) in conjunction with the abstract idea recited at a high-level of generality, i.e., using a computer to clip or window an image being displayed.
The additional elements (i)-(ii) merely confine the use of the abstract idea to a particular technological environment, i.e., medical image windowing, and thus fail to add an inventive concept to the claims. See MPEP 2106.05(h).
The display and processor of the additional elements (i)-(ii) are recited so generically that they can be viewed as nothing more than an attempt to generally link the use of the judicial exception to the technological environment of a computer and leaving the actual determination of “suitable” or “correct” window parameters to the user’s mental abilities as they interact with the computer.
It should be noted that because the courts have made it clear that mere physicality or tangibility of an additional element or elements is not a relevant consideration in the eligibility analysis, the physical nature of the controller does not affect this analysis. See MPEP 2106.05(I).
Dependent claims 34-41 and 43-50 describe further actions implicitly taken or determined by the user in continuing to adjust the window (e.g., claims 34, 37, 39, 43, 45, 46, 48, 49, 50), further actions explicitly taken by the user in continuing to adjust the window (e.g., claim 35), routine features of general purpose computers (e.g., claims 34, 38, 39, 43, 44, 46, 47, 50. For example, using a computer as a calculator to calculate statistical parameters like an average.), or merely automating a feature of claim 32 (e.g., claims 36, 40, 41. The implication is that the reference feature from claim 32 is not automatic.).
Dependent claim 42 describes the vaguely described parameter of “suitability” as being “done with a machine learning algorithm; where the machine learning algorithm uses information from at least one of the local image intensities and spatial information of the image.” The operations of “the determination” in claim 42 are described at a high level of generality and/or describe routine aspects in the field of machine learning, e.g., training a machine learning model to recognize a pattern to optimize for a particular feature, which merely generally links the abstract idea to a particular field of use: machine learning. See MPEP 2106.05(h).
Whether evaluated individually or in combination, the additional elements do not integrate the recited judicial exception into a practical application and the independent claims, therefore, are directed to the judicial exception. (Step 2A, Prong Two: NO).
Step 2B: do the claims as a whole amount to significantly more than the judicial exception?
As explained with respect to Step 2A Prong Two, the additional elements amount to performing the abstract idea using a computer as a tool to perform an existing process (implementing a windowing operation on an image), which cannot provide an inventive concept. See MPEP 2106.05(f). Based on the high-level of specify of the technical aspects of the independent and dependent claims as compared to subject matter in the specification, including the drawings, the additional elements do not constitute an improvement to the functioning of a computer or to another technology because they represent what is well-understood, routine, conventional activity2. See MPEP 2106.04(d)(1).
As explained above, limitation (b), which is performed by limitation (l) that includes the additional element of (ii) a processor, amounts to mere data gathering, which is a form of insignificant extra-solution activity. Under the 2019 PEG, a conclusion that an additional element is insignificant extra-solution activity in Step 2A should be re-evaluated in Step 2B. 2019 PEG Section III(B), 84 Fed. Reg. at 56. At Step 2B, the evaluation of the insignificant extra-solution activity consideration takes into account whether or not the extra-solution activity is well-known. See MPEP 2106.05(g). Here, the providing of window width (window range) and window level (window center) parameters is well-known.3 Limitation (b) therefore remains insignificant extra-solution activity.
The dependent claims do not include any subject matter that amounts to an improvement of the functioning of a computer, or an improvement to any other technology or technical field, as they merely describe and apply known concepts in the fields of image windowing and machine learning. See MPEP 2106.04(d)(1).
Even considering each claim as a whole, the claims do not amount to significantly more than the recited judicial exception and fail to encompass an inventive concept. Claims 32-51, therefore, are not eligible. (Step 2B: NO).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed inventions absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 32-41 and 43-51 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Pat. Appl. Pub. No. 20110205238 to Wallace (hereinafter “Wallace”) in view of U.S. Pat. Appl. Pub. No. 20050197567 to Qian et al. (hereinafter “Qian”).
Regarding claim 32, Wallace teaches a method for contouring a medical image that is displayed on a display device, comprising the steps of:
providing at least one medical image (Wallace, par. 57, “provide a requested image”) with one or more structures to be contoured (Wallace, pars. 51-52, “a window is generally selected so as to preserve the data of interest while discarding the data that is not of interest. Accordingly, window leveling can be used to convert a specific region of the original dynamic range to a lower dynamic range such that the specific region has high fidelity preserved, but other regions are much lower fidelity. In addition, medical images often have features that show up in specific ranges of intensities. For example, bone may show up as a very high intensity (e.g. white); while, soft tissue may show up as lower intensity (e.g. dark gray or black). The window could be selected such that the window corresponds to the range of intensities of interest in the image to which the window is applied ... It can therefore be useful at times to expand the relative values of pixel intensities that correspond to potential features of interest by using an appropriate level function.”);
providing a window width parameter, W (Wallace, par. 63, “WD ... the desired window width.”), and a window level parameter, L (Wallace, par. 63, “CD ... the desired window ... center”) for the at least one medical image (Wallace, par. 63, “At step (402) a desired window level is selected... the desired window level is chosen by selecting the parameters WD and CD, where WD and CD are the desired window width and center respectively.”; par. 63, “In various embodiments, the desired window level is the window level selected by user 111 for viewing on display 123 at workstation 119.”; par. 64, “In various embodiments, an initial image is specified using raw device data by the modality and stored in the image database on memory device 117.”);
displaying the medical image according to the W,L parameters (Wallace, par. 69, “At step (406) the server window level is applied. In various embodiments, the server window level is applied at the server.”; par. 70, “At step (408) the server window level is transmitted from server 109 to client 110 ... In some embodiments, this is achieved by image creation module 116 creating an image file and storing the window level in a color or alpha channel of the image file. The image file is then transmitted from server 109 to client 110.”; pars. 65-66, “In general, the width and center of the server window level can be different from the width and center of the desired window level. In various embodiments, the server window level is selected such that it includes the desired window level.” par. 80, “At step (414) the desired window level is displayed on display 123. User 111 can then examine the desired window level and request other desired window levels.”);
performing the following contouring steps (Using window leveling to separate different features, such as bone being white (a maximum intensity) and soft tissue being black (a minimum intensity) is an image segmentation (contouring) method. See Wallace at par. 52.):
determining local image intensities of the at least one medical image (Wallace, par. 118, “FIG. 7C illustrates a desired window level 712c and a set of disparate server window levels 714c, 716c, and 718c that is generated according to various embodiments of server 109. Window level 714c has a center that is substantially the same as desired window level 712c. The other window levels 716c and 718c are in different regions of the dynamic range of the original image. Such an arrangement could be used to transmit image data for features that correspond to different ranges of intensities”) for each window position of the pixels to be scaled to the desired window level, as a contour is generated for a structure on the image (Expanding or condensing the dynamic range of an input image distinguishes different types of objects and tissues. Contours delineate segmented image objects. An image that highlights bone CT numbers, for example, is an image that includes contours delineating bone from surrounding tissue. See Wallace at pars. 49-52);
determining if the window width parameter, W, and the window level parameter, L, are suitable (Wallace, par. 85, “image viewing system 100 requests additional pixel information (i.e. a new server window level) from the server, when the new desired window level exceeds some threshold in relation to the server window level. In some embodiments, this involves determining whether the desired window level is within a threshold of the boundary or edge of the server window level. In other words when user 111 requests a pixel transformation that approaches the boundary or “edges” of the pixel data available at the client, client 110 will request additional pixel data from the server. In various embodiments, the terms boundary and edge refer to the last pixel intensity values in the range of pixel intensity values included in the window.”) for contouring (segmenting) for each window, according to the determined local image intensity (See Wallace at par. 55);
if at least one of the parameters is not suitable for contouring (segmenting), providing an alert that at least one of the parameters W and L is not suitable for a most recently generated window position (Wallace, par. 86, “once the threshold is exceeded, additional pixel information is requested from the server.”) on the window that includes pixels of desired object contours; and
adjusting at least one of the window width parameter, W, and the window level parameter, L to be suitable for contouring (segmentation) of the structure for the most recently generated window position (Wallace, par. 96, “At step (518) it is determined whether the new desired window level is outside a boundary of the original window level. If not, then step (520) is executed. If yes, then additional pixel information is requested so that the desired window level can be determined. Specifically, a new server window level is requested for the new desired window level by executing step (504) and the steps that follow (504) as described above.”) on the desired contours of a specific intensity range; and displaying the medical image according to the adjusted W,L settings (Wallace, par. 102, “The desired window level can be displayed by executing steps (510) to (514).”), but does not teach that which is explicitly taught by Qian.
Qian teaches determining local image intensities of at least one medical image for each position of the contour (Qian, par. 51, “boundary of the nodule”), as the contour is generated for a structure on the image (Qian, par. 82, “when a user draws a nodule boundary to manually segment a nodule or draw a reference box around a nodule to let the computer segment a nodule in real time (e.g., on the subimage displayed in 708), it may be automatically checked to see whether the drawn boundary or the reference box actually contains a corresponding nodule position recorded in the diagnostic information table.”);
determining if (The user may determine if the current parameters for one or more nodules are suitable. See Qian at par. 64, “When window level settings are changed (e.g., by a user)”) the window width parameter, W, and the window level parameter, L, are suitable for contouring for each position of the contour (i.e., boundary (contour) of object of interest) on the medical image as the contour is generated (The user and/or the system may determine the suitability of windowing parameters for segmenting a nodule boundary (contouring). See Qian at pars. 60-61.), according to the determined local image intensity (Qian, pars. 100-106, “information about the homogeneity, brightness contrast, and boundary strength may be used when analyzing the intensity profiles (at 1126). ... a decision as to whether a nodule candidate is a false positive may be determined, at 1134, by analyzing the computed features in connection with utilizing knowledge-based reasoning ... In addition, a category of a nodule candidate may be utilized in the knowledge-based reasoning. For example, if a nodule shows strong inhomogeneous intensity distribution, it may suggest that the nodule is overlaid on a rib. Therefore, the effect of the rib edge in evaluating the edge strength along the OOI boundary may be taken into account. In addition to examining candidates in the intensity domain, intensity gradients and edges may also be analyzed along the web lines, for example, both in longitude and latitude directions. The features of the nodule candidate may include, but are not limited to, the magnitude and orientation of edges, their statistical distributions along web lines, such as the mean values and standard deviations, local and global spatial relationships of the strongest edges along the longitude lines. These features may be divided into groups according to their correlation strength and may be used as input to a set of cascaded classifiers to identify true nodules. If a candidate is considered to be a nodule during the above reasoning process, the underlying candidate may be saved in a nodule list at 1135 and presented to the user for further examination. Otherwise, it is rejected as a false positive at 1136.”);
if at least one of the parameters is not suitable for contouring (Qian, par. 106, “Otherwise, it is rejected as a false positive at 1136.”), providing an alert that at least one of the parameters W and L is not suitable for a most recently generated position on the contour (Qian, pars. 82-83, “when a user draws a nodule boundary to manually segment a nodule or draw a reference box around a nodule to let the computer segment a nodule in real time (e.g., on the subimage displayed in 708), it may be automatically checked to see whether the drawn boundary or the reference box actually contains a corresponding nodule position recorded in the diagnostic information table. In some embodiments, when there is no recorded nodule within the boundary or reference box, a warning message may be provided ... If the currently drawn reference rectangle substantially deviates from the previous one, some further action may be taken to caution a user. For example, a dialog box may pop up, warning of the discrepancy and asking a user to make a choice. Through this mechanism, a user is informed of any inconsistency. Such warning may help improve the quality of the segmentation and ultimately the diagnosis ... The dialog box 802 may prompt a user to make a choice between the two reference boxes. Such a choice may be made based on a user' domain-specific knowledge and/or patient-specific information.”); and
adjusting at least one of the window width parameter, W, and the window level parameter, L to be suitable for contouring of the structure for the most recently generated position on the contour (Qian at par. 102, “the lower and upper intensity thresholds may be relaxed in different scales so that different extraction results using different sets of threshold values may be derived. The amount of relaxation of the lower and upper thresholds at each step may be prefixed or may be dynamically adjusted.”. The suitability determination includes computing “edge strength along the boundary of an OOI, the difference of edge strength between the inner boundary and outer boundaries of an OOI, etc.” See id. at par. 104).
Wallace discloses a system including a server and a workstation having a display that provides an interface for manual and automatic dynamic range adjustment using different window length and center parameters to contour/segment target objects in a medical image. Thus, Wallace shows that it was known in the art before the effective filing date of the claimed invention to use window leveling and known intensity ranges of specific anatomical image object structures to dynamically scale input image intensity values to a more optimal range that delineates different structures, which is analogous to the claimed invention in that it is pertinent to the problem being solved by the claimed invention, accurately delineating structures in a medical image in the presence of human error and limited dynamic range displays. Qian discloses a system including a remote workstation having a display and a GUI that provides real-time contour analysis as a user manually edits object boundaries, delineates between object regions by increasing intensity homogeneity and eliminating false positive through profile analysis of enhanced regions. Thus, Qian shows that it was known in the art before the effective filing date of the claimed invention to perform automatic analysis of window parameters in real-time as a user edits portions of a contour and to use intensity profiles spanning horizontal and longitudinal distances across the image to differentiate between different image objects, which is analogous to the claimed invention in that it is pertinent to the problem being solved by the claimed invention, accurately delineating structures in a medical image in the presence of human error and limited dynamic range displays.
A person of ordinary skill in the art would have been motivated to combine the real-time contour analysis and intensity profiles disclosed by Qian with the window leveling software, workstation and image server disclosed by Wallace, to thereby contour or re-contour an image in real-time while identifying specific portions of a contour for optimization of the window parameters based on the intensity profile lines extending across object boundaries. Based on the foregoing, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have made such modification according to known methods to yield the predictable results to have the benefit of determining specific sets of intensity values that promote or detract from the accuracy of the final segmentation result.
Claim 33 substantially corresponds to claim 32 by reciting a method for reviewing a previously contoured medical image that is displayed on a display device, comprising steps that substantially correspond to the steps of claim 32. Claim 33 primarily differs from claim 32 by providing “at least one contour on the medical image to be reviewed” instead of providing the medical image “with one or more structures to be contoured”. Claim 33 additionally recites displaying “the at least one contour” and the medical image instead of just the medical image, “selecting at least one contour on the previously contoured image for review”, and “reviewing the further section of the contour portion using the adjusted parameters”. For the sake of brevity, the differences are addressed below.
Wallace in view of Qian further teaches at least one contour (Qian, par. 82, “a nodule boundary”) on the medical image to be reviewed (Wallace, par. 96, “At step (518) it is determined whether the new desired window level is outside a boundary of the original window level. If not, then step (520) is executed. If yes, then additional pixel information is requested so that the desired window level can be determined”);
displaying the at least one contour (Qian, par. 80, “displaying the extracted nodule boundary ... on the ROI display 509”);
selecting at least one contour (Qian, par. 82, “a nodule boundary”) on the previously (The prior window level. See Wallace at par. 96) contoured image for review (Qian, par. 82, “a nodule boundary”); and
reviewing the further section of the contour portion (Reviewing the displayed contour. See Qian at par. 80) using the adjusted parameters (Adjusted W and or L. See Wallace at par. 96, “so that the desired window level can be determined”).
The rationale for obviousness is the same as provided for claim 32.
Regarding claim 34, Wallace in view of Qian teaches a method as in claim 32, where the contouring steps are repeated until the one or more structures to be contoured have been contoured (Steps 520 and 620 repeat until the output is “YES”. See Wallace, par. 97, “At step (520) a determination is made as to whether, the desired window level exceeds some threshold in relation to the server window level. In some embodiments, this comprises determining whether the desired window level is within a threshold of the boundary of the server window level. This can occur if the desired window level center is shifted or if the width is expanded or both.”).
Regarding claim 35, Wallace in view of Qian teaches a method as in claim 32, wherein adjusting at least one of the window width parameter, W, and the window level parameter, L, to be suitable for contouring the at least one structure or reviewing the at least one portion of the contour is performed by the user (Wallace, par. 109, “At step (602) a desired window level is selected at client 110. This can be for example a window level that user 111 has selected for viewing on display 123 at workstation 119. This step is analogous to steps (402) and (502) of FIGS. 4 and 5 respectively.”).
Regarding claim 36, Wallace in view of Qian teaches a method as in claim 32, wherein adjusting at least one of the window width parameter, W, and the window level parameter, L, to be suitable for contouring the at least one structure or reviewing the at least one portion of the contour is an automatic adjustment (Qian, pars. 82-83, “when a user draws a nodule boundary to manually segment a nodule or draw a reference box around a nodule to let the computer segment a nodule in real time (e.g., on the subimage displayed in 708), it may be automatically checked to see whether the drawn boundary or the reference box actually contains a corresponding nodule position recorded in the diagnostic information table. In some embodiments, when there is no recorded nodule within the boundary or reference box, a warning message may be provided ... If the currently drawn reference rectangle substantially deviates from the previous one, some further action may be taken to caution a user. For example, a dialog box may pop up, warning of the discrepancy and asking a user to make a choice. Through this mechanism, a user is informed of any inconsistency. Such warning may help improve the quality of the segmentation and ultimately the diagnosis ... The dialog box 802 may prompt a user to make a choice between the two reference boxes. Such a choice may be made based on a user' domain-specific knowledge and/or patient-specific information.”).
The rationale for obviousness is the same as provided for claim 32.
Regarding claim 37, Wallace in view of Qian teaches a method as in claim 33, further comprising the contour review step of:
detecting one or more portions (Window levels having different desired window lengths for different region types are portions of the contour. See Wallace at par. 122, “the window level can be stored in and transferred in any appropriate format. In some embodiments, this is achieved by storing the window levels in the color channel of one or more image files and the image file(s) is/are transmitted from server 109 to client 110.”) of the selected contour that are suitable for reviewing using the current window width and window level parameters (Wallace, par. 118, “Window level 714 c has a center that is substantially the same as desired window level 712 c. The other window levels 716 c and 718 c are in different regions of the dynamic range of the original image. Such an arrangement could be used to transmit image data for features that correspond to different ranges of intensities.”); and reviewing the one or more contour portions that have been detected (Wallace, par. 123, “At step (610) a client window level is determined such that when combined with one of the server window levels it yields the desired window level. In various embodiments, client 110 selects the most appropriate of the available server window levels and then applies the desired window level. In some embodiments, the most appropriate server window level is the one that results in the least amount of loss when the desired window level is generated. In some embodiments this accomplished by selecting the server window level that includes the desired window level and is closest to the desired window level.”).
Regarding claim 38, Wallace in view of Qian teaches a method as in claim 33, further comprising the step of editing or correcting one or more contour portions after the detected contour portions have been reviewed (Detecting a third window level after review a first and second window level. See Wallace at par. 123).
Claim 39 substantially corresponds to subject matter in claim 32, primarily differing by reciting “suitable for a current task of contour generation or contour review” in place of “suitable for reviewing the at least one portion of the at least one contour” (See Qian at pars. 60, 61, 82, 83, and 102-106).
The rationale for obviousness is the same as provided for claim 32.
Regarding claim 40, Wallace in view of Qian teaches a method as claimed in claim 39, wherein the parameter suggestion for the one or more parameters is automatic (The warning message is automatically generated in response to an automatic evaluation by the computer. See Qian at pars. 82-83).
The rationale for obviousness is the same as provided for claim 32.
Regarding claim 41, Wallace in view of Qian teaches a method as claimed in claim 39, wherein the parameter suggestion for the one or more parameters is applied automatically (Qian at pars. 82-83, “tools may be provided to help a user locate a marked nodule position and identify the nodule boundary. For example, such a tool may include a window level adjustment 511 to enable display of a subimage for which segmentation is performed to have a better visual effect.”).
The rationale for obviousness is the same as provided for claim 32.
Regarding claim 43, Wallace in view of Qian teaches a method as claimed in claim 32, further comprising the step of:
when a contour is generated or selected for review, determining a patch (Wallace, par. 82, “bounding box”) around either the most recently generated part of the contour (See Wallace at par. 82), or a part of the contour for review (See Wallace at par. 82), and assessing the local image intensities in the patch to determine if at least one of the W, L parameters is suitable, or needs to be adjusted (Wallace, par. 82, “let the computer segment a nodule in real time (e.g., on the subimage displayed in 708)”).
Regarding claim 44, Wallace in view of Qian teaches a method as claimed in claim 43, wherein the local image intensities in the patch used to determine the parameter suitability are calculated from one or more of:
mean intensity value (Qian, par. 105, “mean values”); maximum intensity value (A wider window width W will display a larger number of CT numbers or intensity values. A wider window center L will display a larger range of pixel values. A minimum and maximum pixel value are thereby set. See Wallace at par. 115, FIGs. 1B, 2, and 7A to 7C.); minimum intensity value (See Wallace at par. 115, FIGs. 1B, 2, and 7A to 7C.); a configurable percentile of intensities value (See Qian at par. 102, “lower and upper intensity thresholds”); statistical measures between the distribution of image patch intensity values and a predefined parametric function of the W, L values (Qian, par. 105, “The features of the nodule candidate may include, but are not limited to, the magnitude and orientation of edges, their statistical distributions along web lines, such as the mean values and standard deviations, local and global spatial relationships of the strongest edges along the longitude lines.”).
The rationale for obviousness is the same as provided for claim 32.
Regarding claim 45, Wallace in view of Qian teaches a method as claim 32, wherein the local image intensities, are compared to predefined, or user configurable threshold functions for at least one of the current W, L parameters (Wallace, par. 52, “The window could be selected such that the window corresponds to the range of intensities of interest in the image to which the window is applied. In addition, or in alternative to this, the level function could be used to skew the relative intensities of pixels in a given range to accentuate features in that range.”).
Regarding claim 46, Wallace in view of Qian teaches a method as in claim 32, wherein the adjusting of at least one of the window width parameter, W, and the window level parameter L is performed by a user in response to one or more of: a pop-up window with suggestions for new W, L settings (Qian, par. 83, “a dialog box may pop up”); a context sensitive menu accessed via the display (Qian, par. 49, “triggered through a single mouse click on a button or from a menu”; par. 83, “a dialog box may pop up”); an interactive mechanism such as a mouse click (Qian, par. 49, “triggered through a single mouse click on a button or from a menu”; par. 83, “a dialog box may pop up”).
The rationale for obviousness is the same as provided for claim 32.
Regarding claim 47, Wallace in view of Qian teaches a method as in claim 32, wherein the alert provided to the user is a visual alert (dialog box 802. See Qian at FIG. 8 and pars. 82-83); wherein the alert is provided by a message in a user interface (message in dialog box 802. See Qian at FIG. 8 and pars. 82-83).
The rationale for obviousness is the same as provided for claim 32.
Regarding claim 48, Wallace in view of Qian teaches a method as in claim 32, wherein after editing or generation of a contour has been completed the steps are repeated so that a plurality of contours are created or reviewed on a medical image (Steps 520 and 620 repeat until the output is “YES”. See Wallace at par. 97).
Regarding claim 49, Wallace in view of Qian teaches a method as in claim 32, wherein at least one of the window width parameter, W, and the window level parameter, L, at the start of the contouring or reviewing process are one of the following: image modality dependent (Wallace, par. 64, “an initial image is specified using raw device data by the modality and stored in the image database on memory device 117. Such an image then may use a modality LUT to convert from raw device data to source image pixel data.”); workflow dependent (Wallace, par. 64, “the modality may also specify a particular image transformation or window leveling that targets specific values of interest”); set from a previous use of the system (Wallace, par. 114, “for some changes to desired window level, no additional information will be required from the server.”); user configured (Wallace, par. 81, “it is determined whether user 111 has modified the desired window level.”) or defined from parameters of the stored image (Wallace, par. 106, “In some embodiments, a single RGB color image is used to store each of the window levels in a different color channel. In other embodiments, three separate gray scale images are used to store one of the three window level images.”).
Regarding claim 50, Wallace in view of Qian teaches a method as in [claim 32] wherein a minimum value and a maximum value (A wider window width W will display a larger number of CT numbers or intensity values. A wider window center L will display a larger range of pixel values. A minimum and maximum pixel value are thereby set. See Wallace at par. 115, FIGs. 1B, 2, and 7A to 7C.) of at least one of the W, L parameters (Wallace, par. 63, “WD and CD are the desired window width and center respectively.”) is set for contouring (Wallace, par. 63, “the desired window level is the window level selected by user 111 for viewing on display 123 at workstation 119.”; par. 66, “In some embodiments, the server window level has the same or similar center and a width that is the next power of 2 larger than twice the width of the desired window level and smaller than a width that would take the window level beyond a boundary of the original image.”), editing (See id.), or contour reviewing (id.).
The rationale for obviousness is the same as provided for claim 32.
Claim 51 substantially corresponds to claim 32 by reciting a system for analysing a medical image comprising a display (Wallace, par. 80, “At step (414) the desired window level is displayed on display 123. User 111 can then examine the desired window level and request other desired window levels.”) for displaying the at least one medical image and a processor (Wallace, par. 58, “at least one processor”) for performing the steps of the method of claim 32. Claim 51 primarily differs from claim 32 by requiring setting the W and L parameters “for the display device” (Wallace, par. 80, “display 123.”) “to the correct value for the start position of the contour for a structure on the at least one medical image to be contoured” (A user-drawn boundary provides a series of pixel positions for the contour, including a start and end position. See Qian at par. 82, “when a user draws a nodule boundary to manually segment a nodule or draw a reference box around a nodule to let the computer segment a nodule in real time (e.g., on the subimage displayed in 708), it may be automatically checked to see whether the drawn boundary or the reference box actually contains a corresponding nodule position recorded in the diagnostic information table.”).
The rationale for obviousness is the same as provided for claim 32.
Claim 42 is rejected under 35 U.S.C. 103 as being unpatentable over Wallace in view of Qian and in further view of GB Pat. No. 256954 (published 19 August 2020) to Mark et al. (hereinafter “Mark”).
Regarding claim 42, Wallace in view of Qian teaches a method as in claim 32, but does not teach that which is explicitly taught by Mark.
Mark teaches wherein the determination of the suitably of at least one of the window width, W, and window level, L, parameter is done with a machine learning algorithm (Mark, pg. 26, “During application of the training method 1000, the internal parameters of the algorithm are optimised 1060 based on each performance of the correlation step 1050. The optimisation 1060 is such that the estimated local contours, i.e. the model-predicted local contours, match the set of gold-standard local contours 1010, as closely as possible”); wherein the machine learning algorithm uses information from at least one of the local image intensities and spatial information of the image (Mark, pg. 26, “image features, derived from intensities, gradients, and local context, are extracted 1040 from the training medical image scan and from the estimated universal auto-contouring contours 1020”).
Wallace and Qian are analogous to the claimed invention for the reasons provided above.
Mark discloses an automatic contouring method for generating a curated database of golden examples for determining a set of local contours in a medical image based on machine learning that uses local intensity and appearance features as inputs. Thus, Mark shows that it was known in the art before the effective filing date of the claimed invention to use machine learning to develop an accurate ground truth set of images and model to compare against automated or manually-produced segmentations, which is analogous to the claimed invention in that it is pertinent to the problem being solved by the claimed invention, accurately delineating structures in a medical image in the presence of human error and limited dynamic range displays.
A person of ordinary skill in the art would have been motivated to combine the machine-learning based local auto-contouring method disclosed by Mark with the real-time interaction segmentation GUI of Wallace in view of Qian, to thereby train a standardized database of accurately-segmented medical images in an iterative manner as the user interacts with the GUI by providing feedback to re-train a model and generate new output therefrom. Based on the foregoing, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have made such modification according to known methods to yield the predictable results to have the benefit of more accurate contouring and image enhancement.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
A Matter of Grayscale: Understanding Dicom Windows (2020) is pertinent for providing a succinct summary of the terminology, e.g., window level or center, window width or range and formulas, e.g., lower and upper bounds of the scaled intensity range known in the prior art of medical image windowing, which are functionally identical to the “window level parameters W,L” and range “between L - W/2 and L + W/2” described in lines 1-18 on page 4 of the specification.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to RYAN P POTTS whose telephone number is (571)272-6351. The examiner can normally be reached M-F, 9am-5pm EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Sumati Lefkowitz can be reached at 571-272-3638. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/RYAN P POTTS/Examiner, Art Unit 2672
/SUMATI LEFKOWITZ/Supervisory Patent Examiner, Art Unit 2672
1 See Superguide Corp. v. Direct TV Enterprises, Inc., 358 F.3d 870, 69 USPQ2d 1865 (Fed. Cir. 2004).
2 See A Matter of Grayscale: Understanding Dicom Windows (2020).
3 See 1.