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 .
Notice to Applicants
This action is in response to the Request for Continued Examination filed on 02/12/2026.
Claims 1-20 are pending.
Request for Continued Examination
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 02/12/2026 has been entered.
Response to Arguments
The examiner has fully considered Applicant’s presented arguments.
On page 12 of the remarks, Applicant argues that the amendments to claims 19-20 overcome the 35 U.S.C. 112(b) rejections of claims 19-20. This is persuasive. The 112(b) rejections of claims 19-20 have been withdrawn.
On pages 14-19 of the remarks, Applicant argues that the amendments to independent claims 1, 11, and 12 overcome all previous 35 U.S.C. 103 rejections. This is persuasive, particularly regarding the new limitation of “the plurality of zones corresponding to different time to maximum properties using the first technique” added to each of the independent claims. All previous 103 rejections have been withdrawn. However, the claim amendments necessitate new 103 rejections presented below.
Claim Rejections – 35 USC § 103
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 1-4, 10-12, and 15-17 are rejected under 35 U.S.C. 103 as being unpatentable over Kim et al. (Korean Patent KR-20200055690-A) in view of Betting et al. (U.S. Publ. US-2016/0055644-A1) and Zaharchuk (U.S. Publ. US-2020/0381096-A1).
Regarding claim 1, Kim discloses a computer-implemented segmentation method (see paragraph 0001), the method comprising:
performing a first automated segmentation operation on one or more first images of a subject area to automatically determine a first segmentation map of the subject area (see paragraph 0041, where a lesion area is extracted from an input medical image),
wherein the one or more first images are generated using a first technique (see paragraph 0041, where the input medical image is a DWI image);
performing, (see paragraph 0042, where a lesion area is extracted through a different input medical image using machine learning and histogram-based area recognition),
wherein the one or more second images of the subject area are generated using a second technique different from the first technique (see paragraph 0042, where the input medical image is a PWI image),
and the first technique and the second technique capture different properties of the subject area; (paragraphs 0002-0003 specify that DWI and PWI images capture different properties of the imaged areas);
automatically determining a mismatch between segmented portions of the first segmentation map and the second segmentation map, (see paragraphs 0003, 0023, and 0086),
wherein the second segmentation map is determined using a region growing procedure to grow regions around seed locations within one or more regions of interest, based on one or more predetermined region growing criteria (see paragraph 0035, where an iterative algorithm is used for connected component labeling, where an object pixel of interest, or a seed, is newly labeled, and then each iteration grows the region using pixel values to the left of or above successive pixels added to the region; paragraph 0035 also specifies that these connected component labels are used as frequency distribution tables for the histograms).
Kim fails to disclose wherein performing the first automated segmentation operation comprises: automatically applying one or more thresholds to: values of pixels within the one or more first images; or values of elements within one or more maps determined based on the one or more first images, to determine a plurality of zones within the one or more first images or the one or more maps, the plurality of zones corresponding to different time to maximum properties using the first technique.
Kim also fails to disclose performing, at least partially based on the first segmentation map, a second automated segmentation operation on one or more second images of the subject area to automatically determine a second segmentation map of the subject area (emphasis added via underline).
Pertaining to the same field of endeavor, Betting discloses wherein performing the first automated segmentation operation comprises: automatically applying one or more thresholds to: values of pixels within the one or more first images; or values of elements within one or more maps determined based on the one or more first images (see paragraph 0009, where the DWI image can be segmented; see paragraph 0010, where an ADC map created from the DWI image can be segmented, which paragraphs 0045-0046 specify involves applying intensity thresholds to the ADC values),
to determine a plurality of zones within the one or more first images or the one or more maps (see paragraph 0009, where the image can be split into two segments/zones with pixels being assigned either black/white values; see paragraph 0010, where the image can be split into three segments/zones with pixels being assigned either black, white, or a gray value),
performing, at least partially based on the first segmentation map, a second automated segmentation operation on one or more second images of the subject area to automatically determine a second segmentation map of the subject area (see figure 1 and paragraphs 0007-0010, where a first diffusion image is segmented to create a contour mask, which is then applied to a second perfusion image to improve its segmentation).
Kim and Betting are considered analogous art, as they are both directed to segmentation of PWI and DWI images. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have integrated the teachings of Betting into Kim because applying the mask removes unwanted objects from the perfusion image, which improves its segmentation accuracy (see Betting paragraphs 0009 and 0025-0026).
Kim in view of Betting fails to further disclose to determine a plurality of zones within the one or more first images or the one or more maps, the plurality of zones corresponding to different time to maximum properties using the first technique (emphasis added via underline). More specifically, Betting's plurality of zones do not correspond to the specific species of time-to-maximum properties, but rather to ADC map properties.
Pertaining to the same field of endeavor, Zaharchuk discloses to determine a plurality of zones within the one or more first images or the one or more maps, the plurality of zones corresponding to different time to maximum properties using the first technique (see paragraphs 0076, 0081, and 0083-0084, where the medical images can be segmented based on ADC and/or time-to-maximum properties).
Kim and Zaharchuk are considered analogous art, as they are both directed to segmentation of PWI and DWI images. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have integrated the teachings of Zaharchuk into Kim and Betting because timing parameters such as time to maximum can be used to measure biological parameters such as cerebrovascular reserve/CVR (see Zaharchuk paragraph 0122).
Regarding claim 2, Kim in view of Zaharchuk fails to disclose the limitations of claim 2.
Pertaining to the same field of endeavor, Betting discloses wherein performing the first automated segmentation operation comprises: providing the plurality of zones of the one or more first images or the one or more maps as separate inputs to a procedure for determining the first segmentation map (see paragraphs 0009 and 0011, where mathematical morphology techniques are then applied to further improve the contour mask).
Kim and Betting are considered analogous art, as they are both directed to segmentation of PWI and DWI images. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have integrated the teachings of Betting into Kim and Zaharchuk because applying the mask removes unwanted objects from the perfusion image, which improves its segmentation accuracy (see Betting paragraphs 0009 and 0025-0026).
Regarding claim 3, Kim in view of Zaharchuk fails to disclose the limitations of claim 3.
Pertaining to the same field of endeavor, Betting discloses wherein the determination of the second segmentation map of the subject area comprises: identifying the one or more regions of interest within the one or more second images at least partially based on the first segmentation map (see paragraphs 0009-0010, where the mask/first segmentation map is applied to the second PWI image to remove unwanted areas, leaving only regions of interest to further analyze); and selectively utilizing information specifying the identified one or more regions of interest in the second automated segmentation operation to automatically determine the second segmentation map of the subject area (paragraph 0014 defines the PWI image with the mask applied as an "improved perfusion image"; paragraph 0015 specifies that the improved perfusion image can be used to precisely locate the position and center of necrosis in the second images).
Kim and Betting are considered analogous art, as they are both directed to segmentation of PWI and DWI images. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have integrated the teachings of Betting into Kim and Zaharchuk because applying the mask to the PWI image leaves only voxels representing parenchyma while also retaining necrosis information (see Betting paragraph 0014).
Regarding claim 4, Kim in view of Betting and Zaharchuk discloses wherein the seed locations are selected at least partially based on at least one of information within or derived from at least one of the one or more first images or the one or more second images at the seed locations (see Kim paragraph 0035, where a seed location is only selected if the current pixel is not a background pixel, and only if the pixels to the left and above have not been labeled yet).
Regarding claim 10, Kim in view of Betting and Zaharchuk discloses determining a first map of a first property within the subject area based on the one or more first images (see Kim paragraph 0041, where, if a plurality of DWI images are used, ADC variables are extracted from the DWI images), wherein the first automated segmentation operation is performed based on the first map (see Kim paragraph 0041, where the ADC variables can be used to reduce image noise before segmenting the region).
Regarding claim 11, Kim discloses a non-transitory computer readable medium storing instructions (see 0081).
The remainder of claim 11 recites limitations identical to those of claim 1. Therefore, Kim in view of Betting and Zaharchuk discloses claim 11 as applied to claim 1 above.
Regarding claim 12, Kim discloses an image segmentation system, the system comprising a processor and a memory storing computer readable instructions (see paragraph 0081). Kim also discloses and output the determined mismatch to a user of the system (see paragraphs 0080 and 0084-0085).
The remainder of claim 12 recites limitations identical to those of claim 1. Therefore, Kim in view of Betting and Zaharchuk discloses claim 12 as applied to claim 1 above.
Regarding claim 15, Kim in view of Betting and Zaharchuk discloses claim 15 as applied to claim 2 above.
Regarding claim 16, Kim in view of Betting and Zaharchuk discloses claim 16 as applied to claim 3 above.
Regarding claim 17, Kim in view of Betting and Zaharchuk discloses claim 17 as applied to claim 4 above.
Claims 5 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Kim et al. (Korean Patent KR-20200055690-A) in view of Betting et al. (U.S. Publ. US-2016/0055644-A1) and Zaharchuk (U.S. Publ. US-2020/0381096-A1), and further in view of Kriston et al. (U.S. Publ. US-2013/0188846-A1).
Regarding claim 5, Kim in view of Zaharchuk fails to disclose the limitations of claim 5.
Pertaining to the same field of endeavor, Betting discloses wherein generating an estimated second segmentation map comprises: selecting a plurality of seed locations (see paragraph 0046, where multiple necrosis regions can be segmented using region-growing processes, which use multiple seed locations); and expanding regions around the seed locations to identify segmented portions (see paragraph 0046, where the region-growing processes involve expanding regions representing necrosis around the seed locations).
Kim and Betting are considered analogous art, as they are both directed to segmentation of PWI and DWI images. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have integrated the teachings of Betting into Kim and Zaharchuk because doing so allows for automatic detection of necrosis regions in ADC images (see Betting paragraph 0046).
Kim in view of Betting and Zaharchuk fails to further disclose expanding regions around the seed locations to identify segmented portions using a reinforcement learning model (emphasis added via underline).
Pertaining to the same field of endeavor, Kriston discloses expanding regions around the seed locations to identify segmented portions using a reinforcement learning model (see paragraphs 0035-0036, where the region-growing results are validated by a model trained to identify acceptable results).
Kim and Kriston are considered analogous art, as they are both directed to segmentation in MRI images via region-growing. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have integrated the teachings of Kriston into Kim, Betting, and Zaharchuk because doing so improves reliability of segmentation results (see Kriston paragraph 0036).
Regarding claim 18, Kim in view of Betting, Zaharchuk, and Kriston discloses claim 18 as applied to claim 5 above.
Claims 6-7 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Kim et al. (Korean Patent KR-20200055690-A) in view of Betting et al. (U.S. Publ. US-2016/0055644-A1) and Zaharchuk (U.S. Publ. US-2020/0381096-A1), and further in view of Nagenthiraja et al. (U.S. Publ. US-2013/0266197-A1).
Regarding claim 6, Kim in view of Betting and Zaharchuk fails to disclose the limitations of claim 6.
Pertaining to the same field of endeavor, Nagenthiraja discloses wherein a first image of the one or more first images is a perfusion weighted image (see paragraph 0012), and wherein the first automated segmentation operation is performed to segment a portion of the subject area comprising a lesion, captured within the perfusion weighted image (see paragraph 0014).
Kim and Nagenthiraja are considered analogous art, as they are both directed to segmentation of PWI and DWI images. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have integrated the teachings of Nagenthiraja into Kim, Betting, and Zaharchuk because doing so improves speed and accuracy of lesion segmentation (see Nagenthiraja paragraph 0020).
Regarding claim 7, Kim in view of Betting and Zaharchuk fails to disclose the limitations of claim 7.
Pertaining to the same field of endeavor, Nagenthiraja discloses wherein a second image of the one or more second images is a diffusion weighted image (see paragraph 0013), wherein the second automated segmentation operation is performed to segment a portion of the subject area comprising an infarction captured within the diffusion weighted image (see paragraph 0015, where an area corresponding to a diffusion lesion is identified; paragraphs 0002 and 0033 specify that the diffusion lesion represents an infarcted region).
Kim and Nagenthiraja are considered analogous art, as they are both directed to segmentation of PWI and DWI images. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have integrated the teachings of Nagenthiraja into Kim, Betting, and Zaharchuk because doing so improves speed and accuracy of lesion segmentation (see Nagenthiraja paragraph 0020).
Regarding claim 19, Kim in view of Betting, Zaharchuk, and Nagenthiraja discloses claim 19 as applied to claim 6 above.
Regarding claim 20, Kim in view of Betting, Zaharchuk, and Nagenthiraja discloses claim 20 as applied to claim 7 above.
Claims 8 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Kim et al. (Korean Patent KR-20200055690-A) in view of Betting et al. (U.S. Publ. US-2016/0055644-A1) and Zaharchuk (U.S. Publ. US-2020/0381096-A1), and further in view of Bertges et al. (U.S. Publ. US-2022/0215536-A1).
Regarding claim 8, Kim in view of Betting and Zaharchuk fails to disclose the limitations of claim 8.
Pertaining to the same field of endeavor, Bertges discloses predicting a rate of change of a segmented region within at least one of the first segmentation map or the second segmentation map over time based on the one or more first images, the one or more second images, the first segmentation map, and the second segmentation map (see paragraphs 0007 and 0131, where a region representing an abdominal aortic aneurysm/AAA is segmented from images; paragraphs 0029 and 0125 specify that the growth rate/rate of change of the AAA is predicted); and generating a timeline of predicted change of the segmented region (see paragraph 0029, where a prognosis can include the predicted growth rate).
Kim and Bertges are considered analogous art, as they are both directed to segmentation of MRI images. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have integrated the teachings of Bertges into Kim, Betting, and Zaharchuk because doing so improves prediction of clinical courses of action for treatment (see Bertges paragraph 0164).
Regarding claim 13, Kim in view of Betting, Zaharchuk, and Bertges discloses claim 13 as applied to claim 8 above.
Claim 14 is rejected under 35 U.S.C. 103 as being unpatentable over Kim et al. (Korean Patent KR-20200055690-A) in view of Betting et al. (U.S. Publ. US-2016/0055644-A1) and Zaharchuk (U.S. Publ. US-2020/0381096-A1), and further in view of Bertges et al. (U.S. Publ. US-2022/0215536-A1) and Shen et al. (“Statistical prediction of tissue fate in acute ischemic brain injury”, Journal of Cerebral Blood Flow & Metabolism paper, October 2005).
Regarding claim 14, Kim in view of Betting, Zaharchuk, and Bertges fails to disclose the limitations of claim 14.
Pertaining to the same field of endeavor, Shen discloses wherein the memory further stores instructions which, when executed by the processor, cause the processor to: predict a mismatch at a predetermined time after the time at which at least one of the first images or the second images were captured based on the one or more first images, the one or more second images, the first segmentation maps and the second segmentation map (see page 13, figure 2, where probability maps of risk of future infarctions are predicted, particularly using ADC and CBF image data together, which page 6, first paragraph specifies represents mismatch pixels); and output the predicted mismatch or a rate of change of the mismatch to a user of the system (see page 13, figure 2).
Kim and Shen are considered analogous art, as they are both directed to segmentation of PWI and DWI images. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have integrated the teachings of Shen into Kim, Betting, Zaharchuk, and Bertges because doing so improves accuracy of future tissue fate predictions (see Shen page 7, first paragraph).
Allowable Subject Matter
Claim 9 is objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Regarding claim 9, as discussed in the non-final action mailed on 06/25/2026, the limitations of claim 9 are still undisclosed by the prior art after an updated search.
The examiner notes again that claim 14 would also be allowable if rewritten in independent form, if it were also amended to read output the predicted mismatch and a rate of change of the mismatch to a user of the system (emphasis added via underline).
The examiner also notes that claim 11 would be allowable if the limitations of either claim 9 or (the above suggested version of) claim 14 were to be incorporated into claim 11.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NICHOLAS JOHN HELCO whose telephone number is (703)756-5539. The examiner can normally be reached on Monday-Friday from 9:00 AM to 5:00 PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Matthew Bella, can be reached at telephone number 571-272-7778. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from Patent Center. Status information for published applications may be obtained from Patent Center. Status information for unpublished applications is available through Patent Center for authorized users only. Should you have questions about access to Patent Center, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
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) Form at https://www.uspto.gov/patents/uspto-automated- interview-request-air-form.
/NICHOLAS JOHN HELCO/Examiner, Art Unit 2667
/MATTHEW C BELLA/Supervisory Patent Examiner, Art Unit 2667