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
Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d). The certified copy has been filed in parent Application No. 18/038,562 (the instant application), filed on 05/24/2023.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 13 October 2025 was received and the information disclosure statement has been considered by the examiner.
Response to Arguments
Claims 1 and 3-6 have been amended. Claims 12 and 14-15 are canceled. Claims 1-11, 13 and 16 are pending in this action.
Applicant’s arguments, see pg. 7 section “Claim Objections”, filed 15 December 2025, with respect to the objections of claims 1 and 4-6 have been fully considered and are persuasive. The objection of claims 1 and 4-6 has been withdrawn.
Applicant’s arguments, see pg. 7-8 section “Claim Interpretation”, filed 15 December 2025, with respect to the claim interpretation of claim 4 under 35 U.S.C. 112(f) have been fully considered and are persuasive. The applicant has amended away from invoking 35 U.S.C. 112(f) for claim 4 and therefore claim 4 is no longer being interpreted as invoking 35 U.S.C. 112(f).
Applicant’s arguments, see pg. 8-9 section “Claim Rejections Under 35 U.S.C. 112(b)”, filed 15 December 2025, with respect to the rejection of claim 4 under 35 U.S.C. 112(b) have been fully considered and are persuasive. Specifically, the applicant argues that the rejection is moot as claim 4 is no longer being interpreted as invoking 35 U.S.C. 112(f). The examiner agrees. The rejection of claim 4 under 35 U.S.C. 112(b) has been withdrawn.
Applicant’s arguments, see pg. 9 section “Claim Rejections Under 35 U.S.C. 112(a)”, filed 15 December 2025, with respect to the rejection of claim 4 under 35 U.S.C. 112(a) have been fully considered and are persuasive. Specifically, the applicant argues that the rejection is moot as claim 4 is no longer being interpreted as invoking 35 U.S.C. 112(f). The examiner agrees. The rejection of claim 4 under 35 U.S.C. 112(a) has been withdrawn.
Applicant's arguments, see pg. 9-18 section “Claim Rejections Under 35 U.S.C. 103”, filed 15 December 2025, regarding the rejection of claims 1-11, 13 and 16 under 35 U.S.C. 103 have been fully considered but they are not persuasive. The specific reason are detailed below. The applicant organized their arguments using numbered subheadings. For clarity of the records the examiner will do likewise.
Argument 1
The applicant argues that Tachibana does not disclose an input module that receives an image "with pre-defined first and second parts" and that therefore Tachibana et al. ("Deep Learning Electronic Cleansing for Single- and Dual-Energy CT Colonography", as cited on the IDS submitted on 05/24/2023; hereafter, Tachibana) does not teach the corresponding limitation in the claim. The examiner disagrees. The claim language states "an input module configure for receiving the medical image . . . that comprises a first image part not comprising image content to be suppressed and a second image part comprising image content to be suppressed;" By the broadest reasonable interpretation of the claim, the image includes in it parts to be suppressed and parts not to be suppressed. The broadest reasonable interpretation does not include "pre-defining" those parts or, as is implied by "pre-defining", labeling those parts in the input image. Further, there is no indication in the specification that the parts of the image are "pre-defined". Rather, the claim is merely noting the content of the image. Tachibana discloses an image which was received as input and comprised parts to be suppressed and parts not to be suppressed (Tachibana, pg. 2039 col. 1 para. 2, the image is classified into one or a plurality of classes. Fig. 4, the classes are shown. At least the tagged fecal materials are understood as to be suppressed and at least the softer tissue is understood as not to be suppressed). Therefore, the applicant's argument is not persuasive.
Argument 2
The applicant argues that Tachibana does not disclose detecting an image contour of the object of interest and dividing the contour into a first image contour and a second image contour. The examiner disagrees. By the broadest reasonable interpretation, a contour is understood as a boundary marking the edge of a region. The regions in Tachibana as taught by the examiner therefore teach a contour as the regions have a boundary or edge marked in the image. Further, the claim states "dividing the detected image contour into a first image contour and a second image contour". Referring to Tachibana, the contour established by the soft tissue may be understood as the original contour which is then divided into air and tagged fecal matter regions each possessing their own contour which may be understood as a first and a second contour. Therefore, the first contour is divided (see Tachibana, Fig. 4b). Therefore, the applicant's argument is not persuasive.
Argument 3
The applicant argues that Tachibana does not disclose training processing circuitry which trains using image data of the first image contour to learn its appearance. The applicant further argues that the data-driven model is trained "using image data of the first image contour only". The examiner disagrees. The claim states "training a data-driven model using image data of the first image contour". By the broadest reasonable interpretation, this does not exclude the scenario in which more data is used in the training than "the first image contour only." In other words, the claim language does not state the language which the applicant argued, namely, "using image data of the first image contour only." Therefore, as long as a model is trained by data including the first image contour and the model learns an appearance of the image contour then that model and its training would read on the claim. Tachibana discloses training a data-driven model using image data of the first image contour to learn an appearance of the image contour of the object of interest (pg. 2040 col. 2 para. last through pg. 2041 col. 1 para. 1, training is performed using images that are labeled with the classes of materials. As they are labeled, they are understood to comprise the first image contour and the model may learn the appearance of the contour). Therefore, the applicant’s argument is not persuasive.
Argument 4
The applicant used a numbered system for their arguments in this section. For clarity of the record, the examiner is responding to each argument in like manner.
The applicant argues against the combination of references.
What the examiner asserts from the prior art.
The examiner agrees that the described mapping was included in the mapping of claim 1 in the prior action.
Tachibana already solves its artifact problem with a purpose-built post-cleansing pipeline – no unmet need exists to import Xie et al. (WO2020172188 A1, as cited on the IDS submitted on 05/24/2023; hereafter, Xie).
The applicant argues specifically that Tachibana already performs its own smoothing and reconstructing to overcome replacement artifacts and has no unmet need that would have to be met by Xie.
In response the examiner notes that there is no requirement in the MPEP that an obviousness teaching meet an unmet need, see MPEP 2143.I.B the only reference to "unmet need" is in example 10 and it is not noted as a requirement for an obviousness teaching. Further, the applicant argues that Tachibana already performs its own smoothing operation. Assuming for argument that Tachibana does, then teaching the smoothing operation in a combination with Xie is a simple substitution of one known element (the smoothing operation of Tachibana) for another (the smoothing operation of Xie) to obtain predictable results (a smoothed output). While this is a rationale listed in MPEP 2143.I as an example rationale, it is not required that the examiner lean on such an example rationale. Therefore, the motivation to combine provided by the examiner is not overcome by this argument.
Xie addresses a different clinical problem, using different data, artifacts, and learning objective, and is technically incompatible with Tachibana's invention.
The applicant argues specifically that the two references would be incompatible and require redesign.
The examiner disagrees. MPEP 2145.III. states “It is well-established that a determination of obviousness based on teachings from multiple references does not require an actual, physical substitution of elements.” In re Mouttet, 686 F.3d 1322, 1332, 103 USPQ2d 1219, 1226 (Fed. Cir. 2012) (citing In re Etter, 756 F.2d 852, 859, 225 USPQ 1, 6 (Fed. Cir. 1985) (en banc)), see also MPEP 2145.X.D. In other words, for an obviousness teaching, the referenced prior art do not need to be actually physically combinable. Rather, the references need to belong to analogous art which may be shown by the references belonging to the same field of endeavor, see MPEP 2141.01(a).I. The examiner showed in the previous action that Tachibana and Xie are from the same field of endeavor of removing material from a CT image (Tachibana, pg. 2035 col. 1 para. 3; Xie, [0002]). Therefore, the applicant's argument is not persuasive.
The rejection lacks an articulated reason to combine with a reasonable expectation of success. (KSR; MPEP 2143)
The applicant specifically argues that the proffered rationale is conclusory and that there is no evidence that applying the coronary calcium in-painting CNN of Xie would yield predictable success when applied to air-soft tissue boundaries of Tachibana.
The examiner disagrees. The applicant focuses their argument on the subject of the respective images of Xie and Tachibana. However, the claim and field of endeavor are not about dual-energy colonography or coronary calcium in-painting of Tachibana and Xie respectively. The claim and field of endeavor are image analysis. Considering Tachibana from an image analysis perspective, Tachibana discloses an image with light and dark regions and performing a process to remove the light region by replacing it with dark pixels and blending the replacement (Tachibana, pg. 2040 col. 1 para. last through col. 2 para. 1 and Fig. 6). Xie discloses an image with light and dark regions and performing a process to remove the light region by replacing it with dark pixels and blending the replacement (Xie, [0044] and Fig. 1A, 1B, and 3). Therefore, the argument of the applicant that there is no evidence that combining Xie with Tachibana would lead to predictable success is not persuasive. Despite the subject of the images of Tachibana being different than the subject of the images of Xie, the process they are performing is substantially similar and a person of ordinary skill in the art would be enabled to combine the smoothing operation of Xie (i.e. generating a restored image) with Tachibana with a predictable expectation of success.
Hindsight and teaching away
The applicant argues that the combination of Tachibana in view of Xie rests on impermissible hindsight.
The examiner disagrees. MPEP 2145.X.A. states “[a]ny judgment on obviousness is in a sense necessarily a reconstruction based on hindsight reasoning, but so long as it takes into account only knowledge which was within the level of ordinary skill in the art at the time the claimed invention was made and does not include knowledge gleaned only from applicant’s disclosure, such a reconstruction is proper.” In re McLaughlin, 443 F.2d 1392, 1395, 170 USPQ 209, 212 (CCPA 1971). Further, the applicant argues that combining Xie with Tachibana is impermissible because of the differences in the subjects of the images of Xie and Tachibana. For example, the applicant argues that importing Xie's single-energy, coronary-specific in-painting network would undermine the dual-energy inputs of Tachibana. The examiner disagrees. As stated above, the subject of the images, and further method used in acquiring the images, is not the matter of import for the claims. The image analysis being performed by the claim is the matter of import. Both Tachibana and Xie perform relevant image analysis and a person of ordinary skill in the art would recognize them as being combinable and further recognize the benefit of using the model of Xie to generate a restored image, namely "Any structure that was obscured or blocked by the calcium deposits [material to be suppressed] in the initial CT image 202 is shown clear of calcium deposits in the final CT image 218 [the restored image]" (Xie, [0053]).
Conclusion
Therefore, the applicant’s arguments are not persuasive and the rejection is maintained.
When considered as a whole, the applicant’s arguments with regards to the prior art are unpersuasive and the rejections of claims 1-11, 13, and 16 under 35 U.S.C. 103 have been maintained.
The claim terms are being granted the broadest reasonable interpretation. If the applicant finds that the manner in which the examiner is interpreting the claim under the broadest reasonable interpretation is not reflective of the applicant’s intended scope of the claim, the examiner recommends amending the claim to narrow the interpretation to what the applicant intends.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitations are: “input module” and “output module” in claim 1. The term “module” is understood as a substitute for “means”.
Because these claim limitations are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, they are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
These limitations are understood as computer-implemented means-plus-function limitations. Per MPEP 2181.II.B. “For a computer-implemented 35 U.S.C. 112(f) claim limitation, the specification must disclose an algorithm for performing the claimed specific computer function, or else the claim is indefinite under 35 U.S.C. 112(b).” However, MPEP 2182.II.B. also states that ““a microprocessor can serve as structure for a computer-implemented function only where the claimed function is ‘coextensive’ with a microprocessor itself.” EON Corp. IP Holdings LLC v. AT&T Mobility LLC, 785 F.3d 616, 622, 114 USPQ2d 1711, 1714 (Fed. Cir. 2015), citing In re Katz Interactive Call Processing Patent Litigation, 639 F.3d 1303, 1316, 97 USPQ2d 1737, 1747 (Fed. Cir. 2011). . . “Examples of such coextensive functions are ‘receiving’ data, ‘storing’ data, and ‘processing’ data—the only three functions on which the Katz court vacated the district court’s decision and remanded for the district court to determine whether disclosure of a microprocessor was sufficient.” 785 F.3d at 622, 114 USPQ2d at 1714. Thus, “[a] microprocessor or general purpose computer lends sufficient structure only to basic functions of a microprocessor. All other computer-implemented functions require disclosure of an algorithm.” Id., 114 USPQ2d at 1714.” The examiner understands the functions of “receiving” input and “providing” output as “coextensive” functions of a processor or general purpose computer as these are functions that a processor or general purpose computer may perform without special programming.
Therefore, the limitations invoking 35 U.S.C. 112(f) and being interpreted as follows:
“input module” – at least a processor and a memory storing instructions for performing the function, see applicant’s specification pg. 7 line 21-25.
“output module” – at least a processor and a memory storing instructions for performing the function, see applicant’s specification pg. 7 line 21-25.
If applicant does not intend to have these limitations interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitations to avoid them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitations recite sufficient structure to perform the claimed function so as to avoid them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 112(b)
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.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 4 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Regarding claim 4, claim 4 recites “a processing circuitry configured for transforming”. There are several processing circuitries recited in claim 1. It is unclear if this “a processing circuitry” is the same as one of the previously recited processing circuitries or if it is another processing circuitry. If it is another processing circuitry, the examiner recommends amending the claim to read “a material classifier processing circuitry”. For the purpose of examination, the examiner will interpret the claim as being amended in that fashion.
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.
Claims 1-2, 6-8, 10-11, 13, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Tachibana et al. ("Deep Learning Electronic Cleansing for Single- and Dual-Energy CT Colonography", as cited on the IDS submitted on 05/24/2023; hereafter, Tachibana) in view of Xie et al. (WO2020172188 A1, as cited on the IDS submitted on 05/24/2023; hereafter, Xie).
Regarding claim 1, Tachibana discloses:
An apparatus for processing a medical image of an object of interest (one of ordinary skill in the art would understand that some type of apparatus would inherently be needed to carry out the processing described by Tachibana. For example, pg. 2037 col. 2 para. 1, a deep learning model is used which a person of ordinary skill in the art would understand to be operated on a processor which a person would understand as an apparatus),
PNG
media_image1.png
50
294
media_image1.png
Greyscale
the apparatus comprising: an input module (as shown above, a person of ordinary skill in the art would understand the apparatus of Tachibana to include a processor which may perform the function of receiving an input) configured for receiving the medical image of the object of interest (pg. 2038 col. 2 para. 2, the system samples images in multiple orientations showing that the medical image was received. A person of ordinary skill in the art would understand that an apparatus performing processing of medical images would be able to receive an image, i.e. an input module)
PNG
media_image2.png
162
302
media_image2.png
Greyscale
that comprises a first image part not comprising image content to be suppressed and a second image part comprising image content to be suppressed (pg. 2039 col. 1 para. 2, the image is classified into one or a plurality of classes. Fig. 4, the classes are shown. At least the tagged fecal materials are understood as to be suppressed and at least the softer tissue is understood as not to be suppressed);
PNG
media_image3.png
96
292
media_image3.png
Greyscale
PNG
media_image4.png
244
532
media_image4.png
Greyscale
a contour classifier processing circuitry (a person of ordinary skill in the art would understand that a processor comprising processing circuitry would inherently be needed to perform the process of Tachibana. For example, pg. 2039 col. 1 para. 1, a machine learning model is used for classification which a person of ordinary skill in the art would understand to be operated on processing circuitry) configured for detecting an image contour of the object of interest (pg. 2039 col. 1 para. 2, the image is classified into one or a plurality of classes. Fig. 4, the classes are delineated in the image. The classes have distinct boundaries which is understood as detecting an image contour) and dividing the detected image contour into a first image contour and a second image contour, wherein the first image contour is representative of an image contour of the first image part of the object of interest, and the second image contour is representative of an image contour of the second image part of the object of interest (Fig. 4, the image contours show the soft tissue and the tagged fecal matter. The contour established by the soft tissue may be understood as the original contour which is then divided into air and tagged fecal matter regions each possessing their own contour which may be understood as a first and a second contour);
a suppression processing circuitry (a person of ordinary skill in the art would understand that a processor comprising processing circuitry would inherently be need to perform the process of Tachibana as described on pg. 2039 col. 1 para. 3 for suppressing image material) configured for suppressing the image content to be suppressed or substituting the image content to be suppressed with a virtual material to generate a cleansed image (pg. 2039 col. 1 para. 3, the tagged voxels have values converted to the value of air which is understood and suppressing);
PNG
media_image5.png
150
292
media_image5.png
Greyscale
a training processing circuitry (a person of ordinary skill in the art would understand that a processor comprising processing circuitry would inherently be need to perform the process of Tachibana. For example, pg. 2041 col. 1 para. 1, a model is trained which a person of ordinary skill in the art would understand to be performed on processing circuitry) configured for training a data-driven model using image data of the first image contour to learn an appearance of the image contour of the object of interest (pg. 2040 col. 2 para. last through pg. 2041 col. 1 para. 1, training is performed using images that are labeled with the classes of materials. As they are labeled, they are understood to comprise the first image contour and the model may learn the appearance of the contour);
PNG
media_image6.png
52
298
media_image6.png
Greyscale
to generate a restored image of the object of interest (pg. 2039 col. 1 para. 3, a smoothing operation is performed on the boundary of the removed region, i.e. the mucosal surface, and is understood to generate a restored image);
PNG
media_image7.png
102
296
media_image7.png
Greyscale
and an output module (a person of ordinary skill in the art would understand the apparatus of Tachibana to include a processor which may perform the function of providing an output) configured for providing the generated restored image of the object of interest (pg. 2039 col. 1 para. 3, the final cleansed image is generated which is understood to then be output. Also see figs. 6, 7, and 8 showing output images).
PNG
media_image8.png
78
298
media_image8.png
Greyscale
Tachibana does not disclose expressly to apply a trained data-driven model to the cleansed image to generate a restored image.
Xie discloses:
an inference processing circuitry ([0077] the process may be implemented on general purpose computer systems, application specific integrated circuits (ASICs), or other systems which are understood to comprise processing circuitry) configured for applying the trained data- driven model to the cleansed image ([0053] and Fig. 1, at step 110 the calcium-free image patches, understood as the cleansed image, are applied to the modified CT image using a neural network, understood as a data driven model) to generate a restored image of the object of interest ([0053] a final CT image is produced which is understood as a restored image because it resembles the original image with previously obscured features being visible);
Tachibana and Xie are combinable because they are from the same field of endeavor of removing material from a CT image (Tachibana, pg. 2035 col. 1 para. 3; Xie, [0002]).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention to combine the generation of the restored image of Xie with the invention of Tachibana.
The motivation for doing so would have been "Any structure that was obscured or blocked by the calcium deposits [material to be suppressed] in the initial CT image 202 is shown clear of calcium deposits in the final CT image 218 [the restored image]" (Xie, [0053]).
Therefore, it would have been obvious to combine Xie with Tachibana to obtain the invention as specified in claim 1.
Regarding claim 2, Tachibana in view of Xie discloses the subject matter of claim 1.
Tachibana does not disclose expressly that the data-driven model comprises an auto-encoder configured for mapping local patches onto themselves wherein patches are one or a group of pixels.
Xie discloses:
The apparatus according to claim 1, wherein the data-driven model comprises an auto-encoder ([0057] the model includes a contracting path which is understood as an encoder) configured for mapping local image patches directly onto themselves (per the applicant's specification, the examiner understands this limitation to mean that the input type equals the output type, see pg. 3 line 10-11. Xie, [0058] as the image data works through the model it increases feature information by convolution but remains digital data representing the image which is understood as being the same type. Convolution is understood to perform operations on image patches such as mapping), wherein each local image patch represents one or a group of pixels or voxels in the medical image ([0058] convolution is performed which is understood to perform operations on image patches of one or a group of pixels).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention to combine the auto-encoding of Xie with the invention of Tachibana.
The motivation for doing so would have been "to extract details and features from the anatomical context of the modified CT image" (Xie, [0057]).
Therefore, it would have been obvious to combine Xie with Tachibana to obtain the invention as specified in claim 2.
Regarding claim 6, Tachibana in view of Xie discloses the subject matter of claim 1.
Tachibana discloses:
The apparatus according to claim 1,wherein the training processing circuitry is configured for training the data-driven model in a training phase (pg. 2040 col. 2 para. last through pg. 2041 col. 1 para. 1, training is performed using images that are labeled with the classes of materials. As they are labeled, they are understood to comprise the first image contour and the model may learn the appearance of the contour)
PNG
media_image6.png
52
298
media_image6.png
Greyscale
and freezing the trained data-driven model (pg. 2041 col. 1 para. 1, an appropriately trained model is obtained. A person of ordinary skill in the art would understand a "trained" model to be frozen, i.e. to no longer change the weights of the layers in the model);
PNG
media_image9.png
62
284
media_image9.png
Greyscale
Tachibana does not disclose expressly to apply the frozen data-driven model in an inference phase.
Xie discloses:
and wherein the inference processing circuitry is configured for applying the frozen trained data-driven model in an inference phase ([0053] and Fig. 1, at step 110 the calcium-free image patches are applied to the modified CT image using a neural network, which is understood as applying a frozen model in an inference phase).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention to combine the applying of the data model to the invention of Tachibana.
The motivation for doing so would have been "Any structure that was obscured or blocked by the calcium deposits [material to be suppressed] in the initial CT image 202 is shown clear of calcium deposits in the final CT image 218" (Xie, [0053]).
Therefore, it would have been obvious to combine Xie with Tachibana to obtain the invention as specified in claim 6.
Regarding claim 7, Tachibana in view of Xie discloses the subject matter of claim 7.
Tachibana discloses:
The apparatus according to claim 1, wherein the training processing circuitry is configured for training on the fly on a new instance of a medical image of the object of interest (pg. 2040 col. 2 para. last through pg. 2041 col. 1 para. 1, training is continued from a pretrained model which is understood to be training on the fly. The training is done on a medical image "for each type of input image").
PNG
media_image10.png
114
300
media_image10.png
Greyscale
PNG
media_image11.png
94
290
media_image11.png
Greyscale
Regarding claim 8, Tachibana in view of Xie discloses the subject matter of claim 1.
Tachibana discloses:
The apparatus according to claim 1, further comprising: a tagging processing circuitry configured for detecting the image content to be suppressed (pg. 2039 col. 1 para. 2, the image is classified into one or a plurality of classes. Fig. 4, the classes are delineated in the image. Determining the classes to be removed and labeling them is understood as tagging).
PNG
media_image3.png
96
292
media_image3.png
Greyscale
PNG
media_image4.png
244
532
media_image4.png
Greyscale
Regarding claim 10, Tachibana in view of Xie discloses the subject matter of claim 1.
Tachibana discloses:
The apparatus according to claim 1, wherein the image content to be suppressed comprises image content at locations which are tagged by a contrast agent (pg. 2039 col. 1 para. 3, the tagged fecal matter is to be suppressed. Pg. 2035 col. 1 para. 3, tagged fecal matter is understood to be tagged by a contrast agent).
PNG
media_image12.png
134
294
media_image12.png
Greyscale
PNG
media_image13.png
80
296
media_image13.png
Greyscale
Regarding claim 11, Tachibana in view of Xie discloses the subject matter of claim 10.
Tachibana discloses:
The apparatus according to claim 10, wherein the image content tagged by a contrast agent comprises at least one of: stool residuals in colonoscopy; and blood in angiography (pg. 2035 col. 1 para. 3, tagged fecal matter is understood to be tagged by a contrast agent).
PNG
media_image13.png
80
296
media_image13.png
Greyscale
Regarding claim 13, Tachibana discloses:
A computer-implemented method for processing a medical image of an object of interest (pg. 2037 col. 2 para. 1, a deep learning model is used which a person of ordinary skill in the art would understand to be operated on a processor. Further, a person of ordinary skill in the art would understand the disclosed process to be performed on a computer),
PNG
media_image1.png
50
294
media_image1.png
Greyscale
the computer-implemented method comprising: receiving the medical image of the object of interest (pg. 2038 col. 2 para. 2, the system samples images in multiple orientations showing that the medical image was received)
PNG
media_image2.png
162
302
media_image2.png
Greyscale
that comprises a first image part not comprising image content to be suppressed and a second image part comprising image content to be suppressed (pg. 2039 col. 1 para. 2, the image is classified into one or a plurality of classes. Fig. 4, the classes are shown. At least the tagged fecal materials are understood as to be suppressed and at least the softer tissue is understood as not to be suppressed);
PNG
media_image3.png
96
292
media_image3.png
Greyscale
PNG
media_image4.png
244
532
media_image4.png
Greyscale
detecting an image contour of the object of interest (pg. 2039 col. 1 para. 2, the image is classified into one or a plurality of classes. Fig. 4, the classes are delineated in the image. The classes have distinct boundaries which is understood as detecting an image contour) and dividing the detected image contour into a first image contour and a second image contour, wherein the first image contour is representative of an image contour of the first image part of the object of interest, and the second image contour is representative of an image contour of the second image part of the object of interest (Fig. 4, the image contours show the soft tissue and the tagged fecal matter. The contour established by the soft tissue may be understood as the original contour which is then divided into air and tagged fecal matter regions each possessing their own contour which may be understood as a first and a second contour);
suppressing the image content to be suppressed or substituting the image content to be suppressed with a virtual material to generate a cleansed image (pg. 2039 col. 1 para. 3, the tagged voxels have values converted to the value of air which is understood and suppressing);
PNG
media_image5.png
150
292
media_image5.png
Greyscale
training a data-driven model using image data of the first image contour to learn an appearance of the image contour of the object of interest (pg. 2040 col. 2 para. last through pg. 2041 col. 1 para. 1, training is performed using images that are labeled with the classes of materials. As they are labeled, they are understood to comprise the first image contour and the model may learn the appearance of the contour);
PNG
media_image6.png
52
298
media_image6.png
Greyscale
to generate a restored image of the object of interest (pg. 2039 col. 1 para. 3, a smoothing operation is performed on the boundary of the removed region, i.e. the mucosal surface, and is understood to generate a restored image);
PNG
media_image7.png
102
296
media_image7.png
Greyscale
and providing the generated restored image of the object of interest (pg. 2039 col. 1 para. 3, the final cleansed image is generated which is understood to then be output. Also see figs. 6, 7, and 8 showing output images).
PNG
media_image8.png
78
298
media_image8.png
Greyscale
Tachibana does not disclose expressly to apply a trained data-driven model to the cleansed image to generate a restored image.
Xie discloses:
applying the trained data- driven model to the cleansed image ([0053] and Fig. 1, at step 110 the calcium-free image patches, understood as the cleansed image, are applied to the modified CT image using a neural network, understood as a data driven model) to generate a restored image of the object of interest ([0053] a final CT image is produced which is understood as a restored image because it resembles the original image with previously obscured feature visible);
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention to combine the generation of the restored image of Xie with the invention of Tachibana.
The motivation for doing so would have been "Any structure that was obscured or blocked by the calcium deposits [material to be suppressed] in the initial CT image 202 is shown clear of calcium deposits in the final CT image 218 [the restored image]" (Xie, [0053]).
Therefore, it would have been obvious to combine Xie with Tachibana to obtain the invention as specified in claim 13.
Regarding claim 16, Tachibana discloses:
receiving the medical image of the object of interest (pg. 2038 col. 2 para. 2, the system samples images in multiple orientations showing that the medical image was received)
PNG
media_image2.png
162
302
media_image2.png
Greyscale
that comprises a first image part not comprising image content to be suppressed and a second image part comprising image content to be suppressed (pg. 2039 col. 1 para. 2, the image is classified into one or a plurality of classes. Fig. 4, the classes are shown. At least the tagged fecal materials are understood as to be suppressed and at least the softer tissue is understood as not to be suppressed);
PNG
media_image3.png
96
292
media_image3.png
Greyscale
PNG
media_image4.png
244
532
media_image4.png
Greyscale
detecting an image contour of the object of interest (pg. 2039 col. 1 para. 2, the image is classified into one or a plurality of classes. Fig. 4, the classes are delineated in the image. The classes have distinct boundaries which is understood as detecting an image contour) and dividing the detected image contour into a first image contour and a second image contour, wherein the first image contour is representative of an image contour of the first image part of the object of interest, and the second image contour is representative of an image contour of the second image part of the object of interest (Fig. 4, the image contours show the soft tissue and the tagged fecal matter. The contour established by the soft tissue may be understood as the original contour which is then divided into air and tagged fecal matter regions each possessing their own contour which may be understood as a first and a second contour);
suppressing the image content to be suppressed or substituting the image content to be suppressed with a virtual material to generate a cleansed image (pg. 2039 col. 1 para. 3, the tagged voxels have values converted to the value of air which is understood and suppressing);
PNG
media_image5.png
150
292
media_image5.png
Greyscale
training a data-driven model using image data of the first image contour to learn an appearance of the image contour of the object of interest (pg. 2040 col. 2 para. last through pg. 2041 col. 1 para. 1, training is performed using images that are labeled with the classes of materials. As they are labeled, they are understood to comprise the first image contour and the model may learn the appearance of the contour);
PNG
media_image6.png
52
298
media_image6.png
Greyscale
to generate a restored image of the object of interest (pg. 2039 col. 1 para. 3, a smoothing operation is performed on the boundary of the removed region, i.e. the mucosal surface, and is understood to generate a restored image);
PNG
media_image7.png
102
296
media_image7.png
Greyscale
and providing the generated restored image of the object of interest (pg. 2039 col. 1 para. 3, the final cleansed image is generated which is understood to then be output. Also see figs. 6, 7, and 8 showing output images).
PNG
media_image8.png
78
298
media_image8.png
Greyscale
Tachibana does not disclose expressly a non-transitory computer readable medium and to apply a trained data-driven model to the cleansed image to generate a restored image.
Xie discloses:
A non-transitory computer-readable medium for storing executable instructions, which cause a method to be performed to process a medical image of an object of interest ([0078] a memory with instructions stored thereon for operating the method),
applying the trained data- driven model to the cleansed image ([0053] and Fig. 1, at step 110 the calcium-free image patches, understood as the cleansed image, are applied to the modified CT image using a neural network, understood as a data driven model) to generate a restored image of the object of interest ([0053] a final CT image is produced which is understood as a restored image because it resembles the original image with previously obscured feature visible);
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention to combine the non-transitory memory storing instructions of Xie with the invention of Tachibana.
While it is likely inherent that the system of Tachibana operates via a processor that carries out instructions stored on a non-transitory memory, it fails to explicitly state this. One of ordinary skill in the art would recognize that storing a computer program in a memory for a processor to carry out functions has at least the benefits of preserving a program between power cycles of the processor and the ability to save the program and physically transport the memory to operate it on a different processor
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention to combine the generation of the restored image of Xie with the invention of Tachibana.
The motivation for doing so would have been "Any structure that was obscured or blocked by the calcium deposits [material to be suppressed] in the initial CT image 202 is shown clear of calcium deposits in the final CT image 218" (Xie, [0053]).
Therefore, it would have been obvious to combine Xie with Tachibana to obtain the invention as specified in claim 16.
Claims 3 and 4 are rejected under 35 U.S.C. 103 as being unpatentable over Tachibana et al. ("Deep Learning Electronic Cleansing for Single- and Dual-Energy CT Colonography", as cited on the IDS submitted on 05/24/2023; hereafter, Tachibana) in view of Xie et al. (WO2020172188 A1, as cited on the IDS submitted on 05/24/2023; hereafter, Xie) in further view of Lee et al. (US 20220284584 A1; hereafter, Lee).
Regarding claim 3, Tachibana in view of Xie discloses the subject matter of claim 1.
Tachibana in view of Xie does not disclose expressly that the data-driven model comprises a multivariate regressor configured for encoding into a latent subspace and reproducing the image from the subspace.
Lee discloses:
The apparatus according to claim 1, wherein the data-driven model comprises a multivariate regressor (the applicant's specification states that a multivariate regressor may be a random forest regressor, see pg. 12 line 28. [0188] a random forest classification model is used) configured for explicitly encoding local image patches into a latent subspace ([0188] the random forest classifier considers a sub-volume, i.e. a patch, and classifies the features. Classifying the features is understood to consider aspects of the patch which is understood as a latent subspace) and reproducing image data from the latent subspace ([0189] structural features are identified from the classification which is understood to teach that the image data is reproduced and output), wherein each local image patch represents one or a group of pixels or voxels in the medical image ([0188] the classifier considers a sub-volume which is understood as one or a group of pixels).
Lee is combinable with Tachibana in view of Xie because it is in the related field of endeavor of medical image analysis through machine learning (Lee, [0001]).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention to combine the multivariate regressor of Lee with the invention of Tachibana in view of Xie.
The motivation for doing so would have been that "a trained random forest classification algorithm can be used to identify structural features . . . in a NCT image" (Lee, [0191]).
Therefore, it would have been obvious to combine Lee with Tachibana in view of Xie to obtain the invention as specified in claim 3.
Regarding claim 4, Tachibana in view of Xie in further view of Lee discloses the subject matter of claim 3.
Tachibana discloses:
The apparatus according to claim 3, further comprising: a processing circuitry (pg. 2037 col. 2 para. 1, a deep learning model is used which a person of ordinary skill in the art would understand to be operated on a processor comprising processing circuitry. Further, a person of ordinary skill in the art would understand the disclosed process to be performed on processing circuitry)
PNG
media_image1.png
50
294
media_image1.png
Greyscale
configured for transforming the medical image of the object of interest into material images (pg. 2039 col. 1 para. 2, the image is classified into one or a plurality of classes. Fig. 4, the classes are delineated in the image. Classifying regions in the image as a material is understood as transforming the image into material images),
PNG
media_image3.png
96
292
media_image3.png
Greyscale
PNG
media_image4.png
244
532
media_image4.png
Greyscale
Tachibana in view of Xie does not disclose expressly that the training module is configured to train the multivariate regressor for reproducing images from the material images.
Lee discloses:
wherein the training processing circuitry is configured for training the multivariate regressor for reproducing image data from the material images ([0187] the random forest classifier, i.e. the multivariate regressor, takes as input a sub-volumes targeting a blood vessel. By targeting the material of a blood vessel, it is understood to take as input a material image. [0180]-[0181] training is performed accordingly).
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Tachibana et al. ("Deep Learning Electronic Cleansing for Single- and Dual-Energy CT Colonography", as cited on the IDS submitted on 05/24/2023; hereafter, Tachibana) in view of Xie et al. (WO2020172188 A1, as cited on the IDS submitted on 05/24/2023; hereafter, Xie) in further view of Lee et al. (US 20220284584 A1; hereafter, Lee) and Tegzes et al. (US 20180315188 A1; hereafter, Tegzes).
Regarding claim 5, Tachibana in view of Xie in further view of Lee discloses the subject matter of claim 3.
Tachibana in view of Xie in further view of Lee does not disclose expressly to tesselate the medical image into local regions, replace the image intensity with the mean image intensity of the regions, and train the multivariate regressor to reproduce image data from the mean intensity.
Tegzes discloses:
The apparatus according to claim 3, further comprising: a tessellation processing circuitry configured for tessellating the medical image of the object of interest into a plurality of local regions ([0105] the image is divided into "larger pixels" which are understood as local regions) and replacing an image intensity of the medical image by a mean intensity of the plurality of local regions ([0105] the "larger pixels" are super-pixels, which are commonly understood in the art to relate the average intensity of the region), wherein the training processing circuitry is configured for training the multivariate regressor for reproducing image data from the mean intensity of the plurality of local regions ([0105] a machine learning model may be trained to classify regions of the image from the super-pixels which is understood as reproducing image data from the super-pixels).
Tegzes is combinable with Tachibana in view of Xie in further view of Lee because it is in the related field of endeavor of medical image processing using machine learning systems (Tegzes, [0002]).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention to combine the tessellation of Tegzes with the invention of Tachibana in view of Xie in further view of Lee.
The motivation for doing so would have been to promote the differentiation between the foreground and the background (Tegzes, [0105]).
Therefore, it would have been obvious to combine Tegzes with Tachibana in view of Xie in further view of Lee to obtain the invention as specified in claim 5.
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Tachibana et al. ("Deep Learning Electronic Cleansing for Single- and Dual-Energy CT Colonography", as cited on the IDS submitted on 05/24/2023; hereafter, Tachibana) in view of Xie et al. (WO2020172188 A1, as cited on the IDS submitted on 05/24/2023; hereafter, Xie) in further view of Tegzes et al. (US 20180315188 A1; hereafter, Tegzes).
Regarding claim 9, Tachibana in view of Xie discloses the subject matter of claim 1.
Tachibana in view of Xie does not disclose expressly a compositing of the medical image and the restored image.
Tegzes discloses:
The apparatus according to claim 1, further comprising: a compositing processing circuitry configured for compositing the medical image and the restored image of the object of interest ([0137] various models are combined with original image intensity vales to form a composite model of the image information).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention to combine the compositing of Tegzes with the invention of Tachibana in view of Xie.
The motivation for doing so would have been "Thus, certain examples identify what to classify in an image (e.g., regions), as well as what features are used to classify the regions (e.g., size, location, ratio of air pixels, etc.), and efficient calculation of those features" (Tegzes, [0138]).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20090304248 A1, Zalis et al., discloses a system for removing tagged matter from CT images.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOSHUA B CROCKETT whose telephone number is (571)270-7989. The examiner can normally be reached Monday-Thursday 8am-5pm.
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, John M Villecco can be reached at (571) 272-7319. 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.
/JOSHUA B. CROCKETT/Examiner, Art Unit 2661
/JOHN VILLECCO/Supervisory Patent Examiner, Art Unit 2661