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 .
Response to Arguments
The claim objection for claim 3 has been withdrawn in light of the amended claim. However, the claim objection for claim 13 will be maintained, as the Applicant has not amended claim 13 to overcome the objection.
The rejections under 35 U.S.C. 112(b) have been withdrawn. However, in light of the amended claim 1, a new rejection under 35 U.S.C. 112(b) has been introduced.
The rejection under 35 U.S.C. 101 has been withdrawn in light of the amended claims.
Applicant’s arguments with respect to the 35 U.S.C. 103 rejections of claim(s) 1-6, 8-14, 16-20 have been considered but are unpersuasive.
The Applicant on Page 10 of Remarks states “Chitiboi and Xu, taken alone or in hypothetical combination, fail to teach or suggest "wherein the trained scan plane network determines the one or more image scan planes or image scan plane parameters by fitting a plane to a predicted plane mask encompassing the anatomic landmark-of-interest in the subset of higher resolution images or the image construct generated from the higher resolution images", as recited in independent claims 1, 11, and 19. The Examiner admitted that Chitiboi and Xu "does not teach 'wherein the trained scan plane network determines the one or more image scan planes or image scan plane parameters by fitting an analytical plane to a plane mask encompassing the anatomic landmark-of-interest in the subset of higher resolution images or the image construct generated from the higher resolution images"'. Office Action, p. 17. Instead, the Examiner solely relied on Zhang for allegedly disclosing this recitation. Id. Zhang discloses generating a binary mask of brain parenchyma. Zhang, para. 115. Zhang is completely silent with regard to a predicted plane mask (i.e., a mask of a plane). In addition, Zhang is completely silent with regard to utilizing a network to predict image scan planes or image scan plane parameters by fitting a plane to predicted plane mask encompassing an anatomic landmark-of-interest. Thus, Zhang fails to obviate the deficiencies of Chitiboi and Xu”.
The Examiner in the Applicant initiated interview agreed with the Applicant that Zhang failed to teach the amended limitation (which was previously claim 7). However, upon further consideration, it is unclear what the Applicant is trying to claim when stating a plane is being fitted to a predicted plane mask encompassing the anatomic landmark-of-interest. On paragraph [0091], the specification states “In these examples, FIGS. 9A and 9B depict a fitted mid-sagittal plane mask as a landmark structure 226 to which an analytic plane 224 is fitted”. Figs. 9a-9b only show the landmark 226 and plane 224 as a straight line (which is presumed to be aligned/fitted) and does not seem to differentiate a plane mask from the landmark-of-interest. Thus, it is unclear what the Applicant is claiming when stating a plane can be determined by fitting a plane into a plane mask in the landmark-of-interest. A 35 U.S.C. 112(b) rejection will be written below pertaining to this.
On page 10 of the Remarks, Applicant further argues “In addition, Chitiboi and Xu, taken alone or in hypothetical combination, fail to teach or suggest "wherein the trained localizer network is trained to select a respective higher resolution image having maximal coverage of the anatomic landmark-of-interest", as recited in claims 4 and 12. The Examiner solely relied on paragraph 22 of Chitiboi for allegedly teaching this recitation. Office Action, p. 12. This portion of Chitiboi (as well as the rest of Chitiboi) is completely silent with regard to selecting a higher resolution image having maximal coverage of an anatomic landmark-of-interest. Chitiboi is completely silent with regard to maximal coverage. Xu fails to obviate these deficiencies”.
Maximal coverage is a loose term for describing the view of the landmark-of-interest, as someone can have a “maximal coverage” by simply having a full view of the organ, part, etc. in question. Since Chitiboi receives these input images from previously acquired target views (such as MRI images) that showcase the part in question, through BRI, it can be interpreted as having the “maximal coverage” of the landmark-of-interest.
On page 11 of the Remarks, Applicant argues “Further, Chitiboi and Xu, taken alone or in hypothetical combination, fail to teach or suggest "wherein the subset of higher resolution images or the image construct generated from the higher resolution images, prior to processing by the trained scan plane network, are processed by a trained coverage network to identify an imaging field-of-view associated with the anatomic landmark-of-interest or a related anatomic structure", as recited in claims 5 and 13. The Examiner solely relied on paragraph 36 of Chitiboi for allegedly teaching this recitation. Office Action, p. 12. Paragraph 36 of Chitiboi discloses utilizing a machine learning network to evaluate the final acquired target views acquired utilizing the technique in Chitiboi, not analyzing the input images utilized to generate an image depicting a projection of a plane that is then utilized for acquiring a target view. This portion of Chitiboi (as well as the rest of Chitiboi) is completely silent with regard to utilizing a network, prior to processing by the trained scan plane network (i.e., to determine one or more image scan planes or image scan plane parameters that contain regions of the anatomic landmark-of-interest), to identify an imaging field-of-view associated with the anatomic landmark-of-interest or a related anatomic structure within a subset of higher resolution images or the image construct generated from the higher resolution images. Xu fails to obviate these deficiencies”.
Chitiboi’s machine learning model is trained to generate target views based on previously acquired target views. Although claim 5 states “prior to processing”, the images are claimed as being processed by a network to identify a field-of-view, akin to Chitiboi’s method of repeatedly training a model based on previous views and iterations.
Claim Objections
Claim 13 states “wherein the subset of higher resolution images or the trained image construct generated from the higher resolution images, prior to processing by the scan plane network”. “Trained image construct” should read as “the image construct” and “scan plane network” should read as “the trained scan plane network”. 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 1-6, 8-14, 16-20 is/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 1 (and correspondingly claim 11 and 19) recites “wherein the trained scan plane network determines the one or more image scan planes or image scan plane parameters by fitting a plane to a predicted plane mask encompassing the anatomic landmark-of-interest in the subset of higher resolution images or the image construct generated from the higher resolution images”. As described in the Response to Arguments above, it is unclear what the Applicant is claiming when describing a plane is determined by fitting a plane to a plane mask encompassing a landmark-of-interest. On paragraph [0091], the specification states “In these examples, FIGS. 9A and 9B depict a fitted mid-sagittal plane mask as a landmark structure 226 to which an analytic plane 224 is fitted”. However, Figs. 9a-9b only show the landmark 226 and plane 224 as a straight line (which is presumed to be aligned/fitted) and does not seem to differentiate a plane mask from the landmark-of-interest. Thus, it is unclear what the Applicant is claiming. For examination purposes, the examiner will interpret this limitation as fitting a plane into a landmark-of-interest.
Claims 2-6 and 8-10 are rejected for their dependencies on claim 1. Claims 12-14, 16-18 are rejected for their dependencies on claim 11. Claim 20 is rejected for its dependence on claim 19.
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.
Claim(s) 1-5, 8-9, 11-13, 16-17, 19 are rejected under 35 U.S.C. 103 as being unpatentable over Chitiboi (US 20220156918 A1) in view of Xu (US 10910099 B2).
Regarding claim 1, Chitiboi discloses a method for imaging an anatomic region (Chibitoi, paragraph [0017], "The present invention generally relates to methods and systems for automatic, dynamic, and adaptive slice planning for cardiac MRI (magnetic resonance imaging) acquisition"), comprising:
acquiring a plurality of higher resolution images using an imaging system (Chitiboi, paragraph [0020], "At step 102, an input image of an anatomical object of interest of a patient is received").
Chitiboi does not teach explicitly teach “wherein each higher resolution image of the plurality of higher resolution images has a resolution higher than a scout image or localizer image”.
However, Xu teaches wherein each higher resolution image of the plurality of higher resolution images has a resolution higher than a scout image or localizer image (Xu, Col. 12, Line 64-65, " In act 503, The medical image data may be resized or rescaled to a different size or resolution").
It would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to rescale Chitiboi’s images to a higher resolution, as taught by Xu.
The suggestion/motivation for doing so would have been to provide clearer images for improved detection of region of interests.
Further, one skilled in the art could have combined the elements as described above by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Chitiboi in view of Xu discloses providing the plurality of higher resolution images to a trained localizer network to select a subset of higher resolution images for detection and visualization of an anatomic landmark-of-interest based on the image contents of the subset of higher resolution images (Chitiboi, paragraph [0040], "At block 504, AI manager 506 detects images of the available images 502 (e.g., using a classifier) that contain the heart."),
processing the subset of higher resolution images or an image construct generated from the higher resolution images using a trained scan plane network to determine one or more image scan planes or image scan plane parameters that contain regions of the anatomic landmark-of-interest (Chitiboi, paragraph [0028], " In one embodiment, where the one or more additional input images are also input into the machine learning based network, the machine learning based network predicts the location for acquiring the target view of the anatomical object of interest by computing, for each respective image (i.e., the input image and additional input images), a single 2D line representing the intersection of the imaging plane of the respective image and the imaging plane of the target view through regression. By determining 2 or more 2D line intersections of the same 3D imaging plane of the target view in multiple images, the full 3D plane orientation for the target view is computed"),
wherein the trained scan plane network determines the one or more image scan planes or image scan plane parameters by fitting a plane to a predicted plane mask encompassing the anatomic landmark-of-interest in the subset of higher resolution images or the image construct generated from the higher resolution images (Chitiboi, paragraph [0027], "A 2D line segment 206, positioned in the middle of the pair of boundary lines 202 and 204, represents the intersection of the imaging plane of the input image and the imaging plane of the target view and has a distance transform value of zero. Line 206 represents the exact 2D projection of the plane for acquiring the target view of the heart."),
and acquiring one or more diagnostic images using the one or more image scan planes or image scan plane parameters (Chitiboi, paragraph [0030], "At step 108, the target view of the anatomical object of interest is acquired based on the output image. For example, the MRI scanner may automatically navigate to the projection of the 3D image plane identified in the output image and acquire the target view of the anatomical object of interest.").
Therefore, it would have been obvious to combine Chitiboi in view of Xu to obtain the invention as specified in claim 1.
Regarding claim 2, Chitiboi in view of Xu discloses the method of claim 1, wherein the higher resolution image is acquired as part of a pre-acquisition step prior to acquisition of one or more diagnostic images (Chitiboi, paragraph [0020], Fig. 1 below, "At step 102, an input image of an anatomical object of interest of a patient is received", obtaining the higher resolution image is a step prior to obtaining the diagnostic image).
PNG
media_image1.png
496
476
media_image1.png
Greyscale
Regarding claim 3, Chitiboi in view of Xu discloses the method of claim 1, wherein one or both of the trained localizer network or the trained scan plane network are trained using pairs of higher resolution images and corresponding diagnostic images acquired based on the higher resolution images, wherein the diagnostic images include data specifying how to determine an image scan plane-of-interest with respect to the associated higher resolution image (Chibitoi, paragraph [0025], "The machine learning based network is trained during a prior offline or training stage using a training data set to predict a location for acquiring a particular target view of the anatomical object of interest. The training data set comprises training images of the anatomical object of interest annotated with the location for acquiring the particular target view of the anatomical object of interest").
Regarding claim 4, Chitiboi in view of Xu discloses the method of claim 1, wherein the trained localizer network is trained to select a respective higher resolution image having maximal coverage of the anatomic landmark-of-interest (Chitiboi, paragraph [0022], "In one embodiment, one or more additional input images may also be received. For example, the one or more additional input images may include previously acquired target views of the anatomical object of interest", previously acquired views of the object is a maximal coverage of the landmark of interest).
Regarding claim 5, Chitiboi in view of Xu discloses the method of claim 1, wherein the subset of higher resolution images or the image construct generated from the higher resolution images, prior to processing by the trained scan plane network, are processed by a trained coverage network to identify an imaging field-of-view associated with the anatomic landmark-of-interest or a related anatomic structure (Chitiboi, paragraph [0036], "In one embodiment, a machine learning based network may be trained to evaluate acquired target views for a cardiac MRI examination for quality control. The acquired target views may be target views acquired in accordance with method 100 of FIG. 1. The machine learning based network may evaluate acquired target views to identify low quality image scans, incomplete ventricle coverage, wrong views, or other acquired target views that are not suitable for the cardiac MRI examination. The identified target views may be reacquired or a user may be prompted to recheck the image position.").
Regarding claim 8, Chitiboi in view of Xu discloses the method of claim 1, wherein the anatomic landmark-of-interest is not segmented prior to determining the one or more image scan planes or image scan plane parameters (Chitiboi, paragraph [0020], "At step 102, an input image of an anatomical object of interest of a patient is received. In one embodiment, the anatomical object of interest of the patient is a heart of the patient. However, the anatomical object of interest may be any anatomical object of interest of the patient, such as, e.g., an organ, a bone, or any other anatomical structure of the patient.", these images are clean and not segmented).
Regarding claim 9, Chitiboi in view of Xu discloses the method of claim 1, wherein the image construct generated from higher resolution images is a three-dimensional localizer volume parameterized to serve as input to the trained scan plane network (Chitiboi, paragraph [0021], "The input image may comprise 2D (two dimensional) images or 3D (three dimensional) volumes, and may comprise a single image or a plurality of images (e.g., a sequence of images acquired over time)").
Regarding claim 11, Chitiboi discloses a method for imaging an anatomic region (Chibitoi, paragraph [0017], "The present invention generally relates to methods and systems for automatic, dynamic, and adaptive slice planning for cardiac MRI (magnetic resonance imaging) acquisition"), comprising:
acquiring a plurality of higher resolution images using an imaging system (Chitiboi, paragraph [0020], "At step 102, an input image of an anatomical object of interest of a patient is received").
Chitiboi does not teach explicitly teach “wherein each higher resolution image of the plurality of higher resolution images has a resolution higher than a scout image or localizer image”.
However, Xu teaches wherein each higher resolution image of the plurality of higher resolution images has a resolution higher than a scout image or localizer image (Xu, Col. 12, Line 64-65, " In act 503, The medical image data may be resized or rescaled to a different size or resolution").
It would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to rescale Chitiboi’s images to a higher resolution, as taught by Xu.
The suggestion/motivation for doing so would have been to provide clearer images for improved detection of region of interests.
Further, one skilled in the art could have combined the elements as described above by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Chitiboi in view of Xu discloses providing the plurality of higher resolution images to a trained localizer network to select a subset of higher resolution images for detection and visualization of an anatomic landmark-of-interest based on the image contents of the subset of higher resolution images (Chitiboi, paragraph [0040], "At block 504, AI manager 506 detects images of the available images 502 (e.g., using a classifier) that contain the heart."),
processing the subset of higher resolution images or an image construct generated from the higher resolution images using a trained scan plane network to determine one or more image scan planes or image scan plane parameters that contain regions of the anatomic landmark-of-interest (Chitiboi, paragraph [0028], " In one embodiment, where the one or more additional input images are also input into the machine learning based network, the machine learning based network predicts the location for acquiring the target view of the anatomical object of interest by computing, for each respective image (i.e., the input image and additional input images), a single 2D line representing the intersection of the imaging plane of the respective image and the imaging plane of the target view through regression. By determining 2 or more 2D line intersections of the same 3D imaging plane of the target view in multiple images, the full 3D plane orientation for the target view is computed"),
wherein the trained scan plane network determines the one or more image scan planes or image scan plane parameters by fitting a plane to a predicted plane mask encompassing the anatomic landmark-of-interest in the subset of higher resolution images or the image construct generated from the higher resolution images (Chitiboi, paragraph [0027], "A 2D line segment 206, positioned in the middle of the pair of boundary lines 202 and 204, represents the intersection of the imaging plane of the input image and the imaging plane of the target view and has a distance transform value of zero. Line 206 represents the exact 2D projection of the plane for acquiring the target view of the heart."),
and generating one or more modified higher resolution images by reformatting one or more higher resolution images of the plurality of higher resolution images utilizing the one or more image scan planes or image scan plane parameters (Chitiboi, paragraph [0030], "At step 108, the target view of the anatomical object of interest is acquired based on the output image. For example, the MRI scanner may automatically navigate to the projection of the 3D image plane identified in the output image and acquire the target view of the anatomical object of interest.", the output image is a modified version of the input image with acquired views of interest).
Therefore, it would have been obvious to combine Chitiboi in view of Xu to obtain the invention as specified in claim 11.
Claims 12-13, 16-17 correspond to claims 4-5, 8-9 respectively. Thus, they are rejected for the same reasons of obviousness as claims 4-5, 8-9 respectively.
Claim 19 corresponds to claim 1, additionally reciting an imaging system (Chitiboi, paragraph [0017], “The present invention generally relates to methods and systems for automatic, dynamic, and adaptive slice planning for cardiac MRI (magnetic resonance imaging) acquisition”),
a memory encoding processor-executable routines for determining one or more imaging scan planes (Chitiboi, paragraph [0071], “Systems, apparatuses, and methods described herein may be implemented using digital circuitry, or using one or more computers using well-known computer processors, memory units, storage devices, computer software, and other components”),
a processing component configured to access the memory and execute the processor-executable routines (Chitiboi, paragraph [0076], “Processor 804 may include one or more central processing units (CPUs), for example.”). Thus, claim 19 is rejected for the same reasons of obviousness as claim 1.
Claim(s) 6, 14 are rejected under 35 U.S.C. 103 as being unpatentable over Chitiboi (US 20220156918 A1) in view of Xu (US 10910099 B2) and in further view of Zhang (US 20230419499 A1).
Regarding claim 6, Chitiboi in view of Xu discloses the method of claim 5.
Chitiboi in view of Xu does not teach “wherein the trained coverage network generates a binary coverage mask as part of identifying the imaging field-of-view”.
However, Zhang teaches wherein the trained coverage network generates a binary coverage mask as part of identifying the imaging field-of-view (Zhang, paragraph [0115], "A binary mask image of the brain parenchyma may be generated based on the probability map of the brain parenchyma region and a preset threshold, and the brain parenchyma region may be determined based on the binary mask image of the brain parenchyma").
It would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to generate a binary mask of Chitiboi’s (in view of Xu) image, as taught by Zhang.
The suggestion/motivation for doing so would have been to reduce images into 2 potential pixel values, thus reducing computational resources for segmentation.
Further, one skilled in the art could have combined the elements as described above by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Therefore, it would have been obvious to combine Chitiboi in view of Xu and in further view of Zhang to obtain the invention as specified in claim 6.
Claim 14 corresponds to claim 6. Thus, they are rejected for the same reasons of obviousness as claim 14.
Claim(s) 10, 18, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Chitiboi (US 20220156918 A1) in view of Xu (US 10910099 B2) and in further view of Goto (US 20180177452 A1).
Regarding claim 10, Chitiboi in view of Xu discloses the method of claim 1, wherein the plurality of higher resolution images comprises axial scan images (Chitiboi, paragraph [0027] "FIGS. 2A-2D show exemplary output plane locations, generated in accordance with one or more embodiments. FIG. 2A shows an output plane location 200 of a 2Ch view of the heart of a patient generated from an axial scout input image").
Chitiboi in view of Xu does not explicitly teach “and the one or more image scan planes comprise oblique planes”.
However, Goto teaches and the one or more image scan planes comprise oblique planes (Goto, paragraph [0021], "FIGS. 10A-10C are diagrams showing different perspectives of an oblique plane OB intersecting the 3D image DT").
It would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to obtain an oblique scan plane for Chitiboi’s (in view of Xu) planes, as taught by Goto.
The suggestion/motivation for doing so would have been to visualize objects that do not align with straight planes.
Further, one skilled in the art could have combined the elements as described above by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Therefore, it would have been obvious to combine Chitiboi in view of Xu and in further view of Goto to obtain the invention as specified in claim 10.
Claim 18 corresponds to claim 10. Thus, it is rejected for the same reasons of obviousness as claim 10.
Claim 20 corresponds to claim 10, additionally reciting a system (Chitiboi, paragraph [0017], “The present invention generally relates to methods and systems for automatic, dynamic, and adaptive slice planning for cardiac MRI (magnetic resonance imaging) acquisition”). Thus, claim 20 is rejected for the same reasons of obviousness as claim 10.
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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to WAYNE ZHANG whose telephone number is (571) 272-0245. The examiner can normally be reached Monday-Friday 10:00-6:00 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, Ms. Sumati Lefkowitz can be reached on (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.
/WAYNE ZHANG/Examiner, Art Unit 2672
/SUMATI LEFKOWITZ/Supervisory Patent Examiner, Art Unit 2672
Prosecution Insights