DEVICE, SYSTEM AND METHOD FOR SEGMENTATION OF IMAGES

DETAILED ACTION The specification is objected to as failing to provide proper antecedent basis for the claimed subject matter. See 37 CFR 1.75(d)(1) and MPEP § 608.01(o). Correction of the following is required: Claim 15’s “Non-transitory computer readable medium” does not have an antecedent basis in the remainder of applicant’s disclosure. Claim(s) 1,2,3,4,5,6,7,8,11,12,13 and 14 and 15,16,17,18,19,20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Syeda-Mahmood et al. (US 10467767 B2) in view of BUTLER et al. (US 2023/0143748 A1): Claim(s) 9,10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Syeda-Mahmood et al. (US 10467767 B2) in view of BUTLER et al. (US 2023/0143748 A1) as applied in claims 1,2,3,4,5,6,7,8,11,12,13 and 14 and 15,16,17,18,19,20 further in view of SHAO et al. (CN 113160253 A) with SEARCH machine translation: Response to Amendment The amendment was received 8/12/2026. Claims 1-20 pending: PNG media_image1.png 780 154 media_image1.png Greyscale Specification The specification is objected to as failing to provide proper antecedent basis for the claimed subject matter. See 37 CFR 1.75(d)(1) and MPEP § 608.01(o). Correction of the following is required: Claim 15’s “A non-transitory computer readable medium” does not have an antecedent basis in the remainder of applicant’s disclosure. Suggestion to overcome the objection to the specification is to cut and paste the original (6/26/2024) preliminary amendment claim set of claims 1-15 (original, June 26, 2024, preliminary amendment Claim 15 claims “Non-transitory computer readable medium”) filed 6/26/2024 to the remainder of the specification. Response to Arguments Specification Objections Applicant's arguments filed 8/12/2026 have been fully considered but they are not persuasive: Applicant’s state in page 10, 5th para: “Applicant respectfully disagrees. Clear support and antecedent basis for this term is provided in the specification, including paragraph [0099]. Thus, Applicant respectfully requests withdrawal of the specification objections.” PNG media_image2.png 947 934 media_image2.png Greyscale The examiner respectfully disagrees since [0099] states that “a suitable non-transitory medium” can be under the broadest reasonable interpretation “an optical1 storage medium” which includes “signals” “held to be non-statutory”2 thus “the claims as a whole were not to a statutory category and thus failed the first criterion for eligibility”. PNG media_image2.png 947 934 media_image2.png Greyscale In contrast, claim 15 states: “A non3-transitory 4” or A not-transitory computer readable radio (non-statutory) signal5 frequency. Claim Interpretation under 35 U.S.C. §112(f) Applicant’s arguments, see remarks, page 10, filed 8/12/2026, with respect to 35 USC 112(f) have been fully considered and are persuasive. The 35 USC 112(f) interpretation of “input” “output” “processing unit” has been withdrawn. Claim Rejection under 35 U.S.C. §101 Applicant’s arguments, see pages 11-14, filed 8/12/2026, with respect to 35 USC 101 have been fully considered6 and are persuasive. The 35 USC 101 rejection of claims 1-4 and 8-15 has been withdrawn. Claim Rejections under 35 U.S.C. §103 Applicant's arguments filed 8/12/2026 have been fully considered but they are not persuasive: In response to applicant's arguments Applicants state in page 15, 4th para: However, in contrast to claim 1, Syeda-Mahmood does not disclose applying a trained algorithm or computing system that has been trained on a plurality of segmentations of a plurality of objects in a plurality of image slices onto obtained image data to propagate a label of the first label slice to a second slice or onto the first segmentation and the second segmentation to propagate the first and second label slices to the intermediate slice. Rather, Syeda-Mahmood discloses applying a deformable image registration and label fusion for propagation. See SyedaMahmood, col. 3, lines 10-16. against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986). Applicants state in page 15, penult para: “The Office Action appears to acknowledge that Syeda-Mahmood does not disclose these elements of claim 1. See Office Action, page 22. Instead, the Office Action relies on Butler for disclosing these elements. Id.” PNG media_image3.png 1190 850 media_image3.png Greyscale Applicants state in page 16, 2nd para: Butler also separately describes propagation of data to adjacent slices. See Butler, paragraphs [0037] and [0216]. However, in contrast to the "trained algorithm or computing system" of claim 1, Butler does not disclose that the trained random-forest model can be applied onto image data to propagate a label of a first label slice to the second slice or onto first and second segmentations to propagate first and second labeled slices to an intermediate slice. In response, the examiner is not relying in Butler to teach said: onto image data to propagate a label of a first label slice to the second slice or onto first and second segmentations to propagate first and second labeled slices to an intermediate slice. The examiner is relying on Butler to teach the claimed training aspects of claim 1, such as “trained”. Such as shown in above said reproduced page 22: “trained” of the Office action of 5/14/2026. In response to applicant's arguments: page 16, 3rd para: Thus, Butler merely discloses a trained random-forest model that can be applied to generate pixel probability maps (not to perform the propagation functions of the trained algorithm or computing system of claim 1 ). against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986). Applicants state in page 16, 4th para: Therefore, if Syeda-Mahmood was modified with Butler, the combination would teach the use of Syeda-Mahmood' s deformable image registration and label fusion to propagate labels and Butler's trained random-forest model to generate pixel probability maps. Rather than teaching the application of the trained algorithm or computing system of claim 1 for propagation functions. In response: Since Syeda suggests selecting manual or automated annotation labelling for fig. 5:5017 via c.3,ll.45 to c.4,l.5: [0025] Referring to FIG. 5, an exemplary method for 3D segment reconstruction according to embodiments of the present disclosure is illustrated. An image study comprises a plurality of 2D slices that together describe a 3D volume. At 501, annotations are read for a subset of the 2D slices. The annotations include anatomical labeling of at least one anatomical feature. These annotations may be manual, or may be the result of various automatic annotation processes. For a 2D slice lacking annotations, at 502, anatomical labels are propagated to it from at least one neighbor. In some embodiments, neighboring slices from either side of the slice are used. Where labels are prorogated form multiple slices, joint label fusion is applied at 503 to fuse the two propagated annotations into a consensus annotation. The process may be repeated, iterating over all slices lacking annotations. Anatomical labels are propagated between any two slices through calculating deformable image registration between the two slices. In some embodiments, deformable registration between adjacent 2D slices is calculated using ANTs registration. In other embodiments, deformable registration is calculated by optical flow. In some embodiments, deformable registration between non-adjacent 2D slices is produced by composing registrations produced for adjacent slices located between the two non-adjacent slices. Accordingly, fewer manually segmented slices are required for accurate 3D reconstruction than in alternative interpolation schemes. , one of skill in the art of segmentation could or would have done is refer to others making Syeda’s be as BULTER’s seeing in the change “a two stage CRF model was deployed as a final step to get better segmentation results in terms of accuracy and boundary smoothness. A number of validation experiments were performed, and the results visually show how a two stage CRF benefits the segmentation”, BUTLER [0195] via explicit, creative, routine, inferential Supreme Court steps: A,B,C: A) create A Label Fusion Program based on Syeda’s fig. 5: A1) at 501 create code calling/returning from A Segmented Image Program: PNG media_image4.png 941 907 media_image4.png Greyscale B) create the Segmented Image Program based in BUTLER’s fig. 2: PNG media_image5.png 956 1107 media_image5.png Greyscale C) run the Label Fusion Program calling the Segmented Image Program and see what happens (I foresee goodness/more motivation: Beneficial propagation/ transmission of labels via: “a two stage CRF model was deployed as a final step to get better segmentation results in terms of accuracy and boundary smoothness. A number of validation experiments were performed, and the results visually show how a two stage CRF benefits the segmentation”). 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. The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows: 1. Determining the scope and contents of the prior art. 2. Ascertaining the differences between the prior art and the claims at issue. 3. Resolving the level of ordinary skill in the pertinent art. 4. Considering objective evidence present in the application indicating obviousness or nonobviousness. Claim(s) 1,2,3,4,5,6,7,8,11,12,13 and 14 and 15,16,17,18,19,20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Syeda-Mahmood et al. (US 10467767 B2) in view of BUTLER et al. (US 2023/0143748 A1): PNG media_image6.png 786 468 media_image6.png Greyscale Re 1. (Currently Amended), Syeda teaches A device for segmentation of images, the device (likewise) comprising8: a processor (fig. 8:16: “Processing Unit”) configured to: : [[-]] a first image slice (fig. 4:401) of a plurality of image slices of a 3D image data set (or likewise “FIG. 2 depicts an exemplary set of 2D slices of a 3D volume.”, c.1,ll.30-35) , [[-]] a first segmentation9 (fig. 4:401) of the first image slice in which at least one object is segmented (or likewise “segmentation are depicted as labeled slices 111 . . . 115”, c. 2,ll.35-40), and [[-]] a second image slice (fig. 4:402) of the plurality of image slices of the 3D image data set (or said likewise “segmentation are depicted as labeled slices 111 . . . 115”, c. 2,ll.35-40); trained algorithm (or likewise “at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention”, c.6,ll.60-65) or}}} computing system (or likewise “computing system environments”, c.5,ll.60-65) {{{that10 has been trained}}} on11 a plurality of segmentations of a plurality of objects in a plurality of image slices (or likewise “slices that need to be manually segmented”, c.2,ll.15-20: fig. 1:slices 101-115) onto12 the obtained image data to propagate13 the segmentation14 of the at least one object in the first segmentation from the first image slice (fig. 4:401) to1516 the second image slice (fig. 4:402 or likewise propagating slice 401 to slice 402 also propagates labels intermediate to 401/402 via “propagating and fusing labels from manually labeled slices such as 111 . . . 115 to the remaining unlabeled 2D slices”, c. 2,ll.35-40, wherein the propagating “Anatomical labels are propagated between17 any two slices through calculating deformable image registration1819 between the two slices.”, c.3,ll.60-65); and [[to]] compute a third segmentation of a third image slice (fig. 4:403) arranged (in “a series” [0016] 1st S & [0017] 1st S) {{{, within the 3D image data set,}}} in20 between21 (i.e., linking or likewise “propagation22” [0006]) the first image slice (fig. 4:401) {{{and the second image slice (fig. 4:402)}}} trained algorithm or}}} computing system onto the first segmentation {{{and the second segmentation}}} segmentation {{{and second segmentation}}} image slice (fig. 4:401) {{{and second image slice (fig. 4:402)}}} to the third image slice (fig. 4:403 or likewise “First slice 401 and second slice 402 are manually labeled. Deformable registration is applied to propagate labels to intermediate slice 403”, c.3,ll.10-25: fig. 4: PNG media_image7.png 1037 829 media_image7.png Greyscale ); and 23 the third segmentation of the third image slice}}}24. Syeda does not teach under “a narrow subset of claim scope” (said MPEP 2143.03, 2nd para) the difference of claim 1 of: (a) trained (algorithm)25…26 (computing system) that has been trained… (the) trained (algorithm). BUTLER teach the difference of claim 1 of: (a) trained (or likewise “[0139] Using the training information generated, the random forest algorithm generates probability maps”) (algorithm)27…28 29… (the) trained (algorithm). Since Syeda teaches “These annotations30 may be manual, or may be the result of various automatic annotation processes.” (i.e., the reason to combine references under 35 USC 103), c.3,ll.50-55, one of skill in the art of segmentation can make Syeda’s be as BULTER’s seeing the change “a two stage CRF model was deployed as a final step to get better segmentation results in terms of accuracy and boundary smoothness. A number of validation experiments were performed, and the results visually show how a two stage CRF benefits the segmentation”, BUTLER [0195] by combining Syeda’s fig. 5 with BULTER’s fig. 16: PNG media_image8.png 1542 1145 media_image8.png Greyscale Since Syeda suggests selecting manual or automated annotation labelling for fig. 5:50131 via c.3,ll.45 to c.4,l.5: [0025] Referring to FIG. 5, an exemplary method for 3D segment reconstruction according to embodiments of the present disclosure is illustrated. An image study comprises a plurality of 2D slices that together describe a 3D volume. At 501, annotations are read for a subset of the 2D slices. The annotations include anatomical labeling of at least one anatomical feature. These annotations may be manual, or may be the result of various automatic annotation processes. For a 2D slice lacking annotations, at 502, anatomical labels are propagated to it from at least one neighbor. In some embodiments, neighboring slices from either side of the slice are used. Where labels are prorogated form multiple slices, joint label fusion is applied at 503 to fuse the two propagated annotations into a consensus annotation. The process may be repeated, iterating over all slices lacking annotations. Anatomical labels are propagated between any two slices through calculating deformable image registration between the two slices. In some embodiments, deformable registration between adjacent 2D slices is calculated using ANTs registration. In other embodiments, deformable registration is calculated by optical flow. In some embodiments, deformable registration between non-adjacent 2D slices is produced by composing registrations produced for adjacent slices located between the two non-adjacent slices. Accordingly, fewer manually segmented slices are required for accurate 3D reconstruction than in alternative interpolation schemes. , one of skill in the art of segmentation could or would have done is refer to others making Syeda’s be as BULTER’s seeing in the change “a two stage CRF model was deployed as a final step to get better segmentation results in terms of accuracy and boundary smoothness. A number of validation experiments were performed, and the results visually show how a two stage CRF benefits the segmentation”, BUTLER [0195] via explicit, creative, routine, inferential Supreme Court steps: A,B,C: A) create A Label Fusion Program based on Syeda’s fig. 5: A1) at 501 create code calling/returning from A Segmented Image Program: PNG media_image4.png 941 907 media_image4.png Greyscale B) create the Segmented Image Program based in BUTLER’s fig. 2: PNG media_image5.png 956 1107 media_image5.png Greyscale C) run the Label Fusion Program calling the Segmented Image Program and see what happens (I foresee goodness/more motivation: Beneficial propagation/ transmission of labels via: “a two stage CRF model was deployed as a final step to get better segmentation results in terms of accuracy and boundary smoothness. A number of validation experiments were performed, and the results visually show how a two stage CRF benefits the segmentation”). Re 2.(Currently Amended), Syeda of the combination (illustrated above) of Syeda,BUTLER teaches The device wherein the processor is configured to use a learning system (or likewise “a decision tree learning model32” BUTLER [0017]) {{{, a neural network, a convolutional neural network, a segmentation network, or a U-net-like network}}}33 as the trained algorithm or computing system. Re 3.(Currently Amended), BUTLER of the combination of Syeda,BULTER teaches The device processor includes: [[-]] identifying, based on the first image slice and the first segmentation, characteristics of at least one the segmented object 34 of the CT data35” BUTLER [0023]), [[-]] identifying one or more of the identified characteristics in the second image slice (or likewise “multiple segmentations may be performed in different 2D ‘slices’”, BULTER [0215] last S) and [[-]] using36 the characteristics identified in the first image slice and the second image slice (or likewise of each slice “each pixel is represented as a node37 in a graph” [0151]) to38 propagate the segmentation of the at least one object in the first segmentation from the first image slice to the second image slice resulting in the second segmentation of the second image slice (or likewise “To propagate… a graph may be constructed that not only includes pixels from Si, but also the pixels located adjacent to the seed points in Si+1. Therefore, when the segmentation is complete for Si, it will also have generated a set of seed points in the slice Si+1 for both the foreground and the background. The same procedure is repeated sequentially at every slice.” [0227]). Re 4.(Currently Amended), BUTLER of the combination of Syeda,BUTLER teaches The device wherein the characteristics include 39. Re 5.(Currently Amended), Syeda of the combination of Syeda,BUTLER teaches The device processor is configured to: compute two third segmentations, wherein a first of the two third segmentations , and a second of the two third segmentations compute a final third segmentation by weighted40 interpolation (or likewise “registration-based interpolation and by adaptive slice selection are both statistically significant41 for all interpolation”, Syeda, c.5, ll.20-25) of the two third segmentations. Re 6.(Currently Amended), Syeda of the combination of Syeda,BUTLER teaches The device wherein the processor : compute weights for the weighted interpolation based on at least one of spatial distance of the respective image slice from third image slice or Re 7.(Currently Amended), Syeda of the combination of Syeda,BUTLER teaches The device processor image slice and the second image slice the third segmentation of [[a]] the third image slice, of the two or more third image slices closest to the third image slice are used (or likewise an “adjacent42…inter-slice distance…i.e., argmax.sub.j<i,jϵS and argmin.sub.j>i,jϵS, will be applied to… propagate labels to intermediate slice 403, allowing 3D segmentation reconstruction”, c. 2,l. 50 to c.3,l.15). Re 8.(Currently Amended), BUTLER of the combination of Syeda,BUTLER teaches The device processor : train the algorithm or computing system on a plurality of segmentations of a plurality of objects in a plurality of image slices, wherein the plurality of image slices comprise at least one of real images Re 11.(Currently Amended) BUTLER of the combination (illustrated above) of Syeda,BUTLER teaches The device processor : [[–]] use the computed second segmentation together with the second image slice, the first segmentation and the first image slice for43 training the algorithm or computing system (or likewise “The Applicant's segmentation method may be used”, Butler [0109]). Re 12.(Currently Amended), BUTLER of the combination (illustrated above) of Syeda,BUTLER teaches The device processor is configured to output display information for output on a display, the display information including one or more of [[-]] which44 image slices have been segmented already (or likewise “j) presenting the segmented image to an interface.”, BUTLER [0044]) 45. Re 13.(Currently Amended), BUTLER of the combination (illustrated above) of Syeda,BUTLER teaches A system for segmentation of images, the system comprising: [[-]] [[a]] the device (or “a user input device” BUTLER [0041]) of [[-]] a display (or “a display” [0041]) a user interface (or “a graphical user interface” BUTLER [0044]: item “c)”) at least one of select image slices onto which a segmentation shall be propagated Claim 14 is rejected like claim 1: Re 14.( Original), Syeda of the combination (illustrated above) of Syeda,BUTLER teaches A method for segmentation of images, the method comprising: - obtaining image data including: [[-]] a first image slice of a plurality of image slices of a 3D image data set, [[-]] a first segmentation of the first image slice in which at least one object is segmented, and [[-]] a second image slice of the plurality of image slices of the 3D image data set; [[-]] computing a second segmentation of the second image slice based on the obtained image data by applying a trained algorithm or computing system that has been trained on a plurality of segmentations of a plurality of objects in a plurality of image slices onto the obtained image data to propagate the segmentation of the at least one object in the first segmentation from the first image slice to the second image slice; [[-]] computing a third segmentation of a third image slice arranged, within the 3D image data set, in between the first image slice and the second image slice trained algorithm or computing system onto the first segmentation and the second segmentation segmentation and the second segmentation image slice and the second image slice to the third image slice; and [[-]] outputting the second segmentation of the second image slice and the third segmentation of the third image slice. Claim 15 is rejected like claims 1 and 14: Re 15. (Currently Amended), Syeda of the combination of Syeda,BUTLER teaches A non-transitory 46 (or “a computer readable storage medium”) comprising instructions which, when executed by a processor, cause the processor to: obtain image data including: a first image slice of a plurality of image slices of a 3D image data set, a first segmentation of the first image slice in which at least one object is segmented, and a second image slice of the plurality of image slices of the 3D image data set; compute a second segmentation of the second image slice based on the obtained image data by applying a trained algorithm or computing system that has been trained on a plurality of segmentations of a plurality of objects in a plurality of image slices onto the obtained image data to propagate the segmentation of the at least one object in the first segmentation from the first image slice to the second image slice; compute a third segmentation of a third image slice arranged, within the 3D image data set, in between the first image slice and the second image slice by applying the trained algorithm or computing system onto the first segmentation and the second segmentation to propagate the segmentation of the at least one object in the first segmentation and the second segmentation from the first image slice and the second image slice to the third image slice; and outputting the second segmentation of the second image slice and the third segmentation of the third image slice. Claim 16 is rejected like claim 3: Re 16. (New), Syeda of the combination of Syeda-BUTLER teaches The non-transitory computer readable medium as claimed in claim 15, wherein applying the trained algorithm or computing system onto the first image slice includes: identifying, based on the first image slice and the first segmentation, characteristics of at least one of the segmented object or the segmentation applied to the first image slice, identifying one or more of the identified characteristics in the second image slice, and using the characteristics identified in the first image slice and the second image slice to propagate the segmentation of the at least one object in the first segmentation from the first image slice to the second image slice resulting in the second segmentation of the second image slice. Claim 17 is rejected like claim 4: Re 17. (New), Syeda of the combination of Syeda-BUTLER teaches The non-transitory computer readable medium as claimed in claim 16, wherein the characteristics include one or more of brightness, texture, edges, boundaries, patterns, characteristic structures or points, homogeneity, area, shape, size, or any other implicitly learned feature. Claim 18 is rejected like claim 5: Re 18. (New), Syeda of the combination of Syeda-BUTLER teaches The non-transitory computer readable medium as claimed in claim 15, wherein the instruction, when executed by the processor, further cause the processor to: compute two third segmentations, wherein a first of the two third segmentations is computed by propagating the segmentation of the at least one object in the first segmentation from the first image slice to the third image slice, and a second of the two third segmentations is computed by propagating the segmentation of the at least one object in the second segmentation from the second image slice to the third image slice, and compute a final third segmentation by weighted interpolation of the two third segmentations. Claim 19 rejected like claim 6: Re 19. (New), Syeda of the combination of Syeda-BUTLER teaches The non-transitory computer readable medium as claimed in claim 18, wherein the instruction, when executed by the processor, further cause the processor to: compute weights for the weighted interpolation based on at least one of spatial distance of the respective image slice from third image slice or similarity of the respective image slice with the third image slice. Claim 20 rejected like claim 7: Re 20. (New), Syeda of the combination of Syeda-BUTLER teaches The non-transitory computer readable medium as claimed in claim 15, wherein the instructions, when executed by the processor, further cause the processor to: compute two or more third segmentations of two or more third image slices arranged, within the 3D image data set, in between the first image slice and the second image slice, wherein for computing the third segmentation of the third image slice, one or two segmentations of one or more image slices of the two or more third image slices closest to the third image slice are used. Claim(s) 9,10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Syeda-Mahmood et al. (US 10467767 B2) in view of BUTLER et al. (US 2023/0143748 A1) as applied in claims 1,2,3,4,5,6,7,8,11,12,13 and 14 and 15,16,17,18,19,20 further in view of SHAO et al. (CN 113160253 A) with SEARCH machine translation: PNG media_image9.png 784 563 media_image9.png Greyscale Re 9. (Currently Amended), Syeda of the combination of Syeda,BUTLER teaches The device wherein the processor rd S to [0125] 1st S) 47 by: [[-]] selecting a training image data set in which a segmented object is present (or likewise “the initially segmented object boundaries”, BUTLER [0118] 4th S); [[-]] randomly selecting, from the plurality of training image slices of the training image data set, a first training image slice, in48 which the segmented object is present; [[-]] randomly selecting, from the plurality of training image slices of the training image data set, a second training image slice, in49 which the segmented object is present; and [[-]] applying the algorithm the randomly selected first and second training image slices. Syeda of the combination of Syeda,BUTLER does not teach the difference of claim 9 of: selecting a training image data set in which … randomly selecting, from the plurality of training image slices of the training image data set, a first training image slice, in50 which… randomly selecting, from the plurality of training image slices of the training image data set, a second training image slice, in51 which … the randomly selected first and second training image slices. SHAO teach the difference of claim 9 of: selecting a training image data set (or likewise “randomly selecting one group as the training image in a three-dimensional image set”, pg. 8, 1st txt bk) in which (or likewise “a three-dimensional image set…comprises a coronal surface, sagittal surface, cross section three different slicing direction, each slicing direction has a plurality of slices”, pg. 8, 1st txt bk)… randomly selecting, from the plurality of training image slices of the training image data set, a first training image slice (or likewise said “randomly selecting one group as the training image in a three-dimensional image set”), in52 which (or likewise said “a three-dimensional image set…comprises a coronal surface, sagittal surface, cross section three different slicing direction, each slicing direction has a plurality of slices”)… randomly selecting, from the plurality of training image slices of the training image data set, a second training image slice (or likewise said “randomly selecting one group as the training image in a three-dimensional image set”), in53 which (or likewise said “a three-dimensional image set…comprises a coronal surface, sagittal surface, cross section three different slicing direction, each slicing direction has a plurality of slices”) … the randomly selected first and second training image slices (or likewise said “randomly selecting one group as…a plurality of slices”). Since Syeda of the combination of Syeda,BUTLER teaches annotations/marking labels and segmentation one of skill in the art of annotations/marking labels and segmentations can make Syeda’s of the combination of Syeda,BUTLER be as SHAO’s seeing in the change “effectively improving the automation of the medical image segmentation, intelligent level”, SHAO, page 12 , 3rd txt blk. Re 10.(Currently Amended), Syeda of the combination of Syeda,BUTLER teaches The device processor : [[-]] randomly select the54 training data set or the type of object to be used for training (or likewise “labelling pixels within the foreground and the background objects …during the training stage” BUTLER [0115] 1st S to [0125] 1st S) from all objects (or likewise “from every pixel55” [0147]) present in training image data sets. Syeda of the combination of Syeda,BUTLER does not teach the difference of claim 10 of: randomly select the56 training data set. SHAO teach the difference of claim 10 of: randomly select the57 training data set58 (or likewise “randomly selecting one group59 as the training image in a three-dimensional image set”, pg. 8, 1st txt blk). Similar to the rejection of claim 9, Since Syeda of the combination of Syeda,BUTLER teaches annotations/marking labels and segmentation one of skill in the art of annotations/marking labels and segmentations can make Syeda’s of the combination of Syeda,BUTLER be as SHAO’s seeing in the change “effectively improving the automation of the medical image segmentation, intelligent level”, SHAO, page 12, 3rd txt blk. Conclusion The prior art “nearest to the subject matter defined in the claims” (MPEP 707.05) made of record and not relied upon is considered pertinent to applicant's disclosure. The following table lists several references that are relevant to the subject matter claimed and disclosed in this Application. The references are not relied on by the Examiner, but are provided to assist the Applicant in responding to this Office action. Citation Relevance MUSTAFA NOOR--E-ALAM (LUNG NODULE DETECTION AND SEGMENTATION USING A PATCH-BASED MULTI ATLAS METHOD) MUSTAFA teaches “label propagation” via page 11, fig. 2-3: PNG media_image10.png 682 847 media_image10.png Greyscale “2.2.5 Label propagation: After the selection of atlases, the labels of the target image are decided. Early MAS (Multi-Atlas segmentation) algorithms [47] used the nearest neighborhood algorithm for choosing the target image pixel label.” as the closest to applicant’s disclosure of “label propagation”: PNG media_image11.png 434 932 media_image11.png Greyscale Gooding et al. (GB 2592693 A) Gooding teaches machine learning finding the same structure from one slice to the other as “propagation” via page 3, last para: PNG media_image12.png 605 998 media_image12.png Greyscale Consequently, interactive methods for 3D images can be addressed through intuitive user interaction in 2D, while using the additional spatial context available through the remaining image slices in the 3D image and by using an efficient automatic contour prediction engine that integrated spatial context information over a population of examples. Specifically, a user may interact with a single image slice by contouring a structure in that image slice. Starting from this interaction, a ML model may learn to segment structures on nearby image slices. The ML model can infer the contours based on the spatial information such as similar location on an image slice, similar intensity values, or morphology. Two-dimensional interaction keeps the interaction mechanism simple and intuitive, while the benefits of 3D segmentation are retained through the provision of spatial context to the ML model. The inference of corresponding structures from one image slice to another image slice is also referred to as spatial propagation. as the closest to the claimed “propagate the segmentation of the at least one object in the first segmentation from the first image slice to the second image slice” of claim 1. THIS ACTION IS MADE FINAL. 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 DENNIS ROSARIO whose telephone number is (571)272-7397. The examiner can normally be reached Monday-Friday, 9AM-5PM EST. Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Henok Shiferaw can be reached at 571-272-4637. 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. /DENNIS ROSARIO/Examiner, Art Unit 2676 /Henok Shiferaw/Supervisory Patent Examiner, Art Unit 2676 1 optical: Relating to optics, wherein optics is defined: (functioning as singular) the branch of science concerned with vision and the generation, nature, propagation, and behaviour of electromagnetic light, wherein propagation is defined: the act of propagating, wherein propagate is defined: physics to move through, cause to move through, or transmit, esp in the form of a wave, wherein transmit is defined: to send out (signals) by means of radio waves or along a transmission line (Dictionary.com) 2 MPEP 2106 Patent Subject Matter Eligibility [R-10.2019] II. ESTABLISH BROADEST REASONABLE INTERPRETATION OF CLAIM AS A WHOLE, 2nd para: Claim interpretation affects the evaluation of both criteria for eligibility. For example, in Mentor Graphics v. EVE-USA, Inc., 851 F.3d 1275, 112 USPQ2d 1120 (Fed. Cir. 2017), claim interpretation was crucial to the court’s determination that claims to a "machine-readable medium" were not to a statutory category. In Mentor Graphics, the court interpreted the claims in light of the specification, which expressly defined the medium as encompassing "any data storage device" including random-access memory and carrier waves. Although random-access memory and magnetic tape are statutory media, carrier waves are not because they are signals similar to the transitory, propagating signals held to be non-statutory in Nuijten. 851 F.3d at 1294, 112 USPQ2d at 1133 (citing In re Nuijten, 500 F.3d 1346, 84 USPQ2d 1495 (Fed. Cir. 2007)). Accordingly, because the BRI of the claims covered both subject matter that falls within a statutory category (the random-access memory), as well as subject matter that does not (the carrier waves), the claims as a whole were not to a statutory category and thus failed the first criterion for eligibility. 3 Non-: a prefix meaning “not,” freely used as an English formative, usually with a simple negative force as implying mere negation or absence of something (rather than the opposite or reverse of it, as often expressed byun- ) (Dictionary.com) 4 medium: one of the means or channels of general communication, information, or entertainment in society, as newspapers, radio, or television, wherein channel is defined: Telecommunications. a frequency band of sufficient width for one- or two-way communication from or to a transmitter used for television, radio, CB radio, telephone, or telegraph communication, wherein band is defined: Also called frequency band, wave band. Radio and Television. a specific range of frequencies, especially a set of radio frequencies, as HF, VHF, and UHF, wherein radio frequencies is defined: A frequency of electromagnetic radiation in the range at which radio signals are transmitted, ranging from approximately 3 kilohertz to 300 gigahertz. Many astronomical bodies, such as pulsars, quasars, and possibly black holes, emit radio frequency radiation. (Dictionary.com) 5 MPEP 2106 Patent Subject Matter Eligibility [R-10.2019] II. ESTABLISH BROADEST REASONABLE INTERPRETATION OF CLAIM AS A WHOLE, 2nd para: Claim interpretation affects the evaluation of both criteria for eligibility. For example, in Mentor Graphics v. EVE-USA, Inc., 851 F.3d 1275, 112 USPQ2d 1120 (Fed. Cir. 2017), claim interpretation was crucial to the court’s determination that claims to a "machine-readable medium" were not to a statutory category. In Mentor Graphics, the court interpreted the claims in light of the specification, which expressly defined the medium as encompassing "any data storage device" including random-access memory and carrier waves. Although random-access memory and magnetic tape are statutory media, carrier waves are not because they are signals similar to the transitory, propagating signals held to be non-statutory in Nuijten. 851 F.3d at 1294, 112 USPQ2d at 1133 (citing In re Nuijten, 500 F.3d 1346, 84 USPQ2d 1495 (Fed. Cir. 2007)). Accordingly, because the BRI of the claims covered both subject matter that falls within a statutory category (the random-access memory), as well as subject matter that does not (the carrier waves), the claims as a whole were not to a statutory category and thus failed the first criterion for eligibility. 6 See attached Search Notes entry of 10/7/2026 regarding an RQAS discussion of claim 1. 7 (i.e., the reason/initial motivation/cause to combine references under 35 USC 103) 8 BROAD CLAIM LANGUAGE: -ing (of “comprising” or any “-ing” word in this claim set): a suffix of nouns formed from verbs, expressing the action of the verb or its result, product, material, etc. (the art of building; a new building; cotton wadding )., wherein etc. is defined: and others; and so forth; and so on (used to indicate that more of the same sort or class might have been mentioned, but for brevity have been omitted), wherein so is defined: likewise or correspondingly; also; too. (Dictionary.com) 9 segmentation: the act or an instance of dividing into segments (Dictionary.com) 10 that: (used to indicate a person, thing [“trained algorithm”], idea, state, event, time, remark, etc., as pointed out or present, mentioned before, supposed to be understood, or by way of emphasis). (Dictionary.com) 11 on: in connection, association, or cooperation with; as a part or element of. (Dictionary.com) 12 onto: to a place or position on; upon; on, wherein on is defined in the above “on”-footnote. (Dictionary.com) 13 propagate: to create (an effect) at a distance, as by electromagnetic waves, compression waves, etc., traveling through space or a physical medium; transmit. (Dictionary.com) 14 segmentation: division into segments. (Dictionary.com) 15 Regarding “to” and applicant’s disclosure [0097], last S: “Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims.” 16 to: (used for expressing direction or motion or direction toward something [the second image slice]) in the direction of; toward. (Dictionary.com) 17 between: at a point or in a region intermediate to two other points in space, times, degrees, etc [slices 401/402] (Dictionary.com) 18 registration: the act of registering, wherein registering is defined: Printing. to be in register, wherein register is defined: Printing. a precise adjustment or correspondence, as of lines, columns, etc., especially on the two sides of a leaf, wherein correspondence is defined: Mathematics. function, wherein function is defined: Mathematics. Also called correspondence, map, mapping, transformation. a relation between two sets in which one element of the second set is assigned to each element of the first set, as the expression y = x 2 ; operator, wherein assign is defined: to give or allocate; allot, wherein give is defined: to convey or transmit. (Dictionary.com) 19 Given that the claimed “propagate” and “registration” (even Syeda’s “transform” [0022] 3rd S) is an identity, I am asserting that they both (even Syeda’s “transform” [0022] 3rd S) mean the same thing and thus are equivalent, wherein identity is defined: Logic. an assertion that two terms (“propagate” & “register”: even Syeda’s “transform” [0022] 3rd S) refer to the same thing (“transmit”), wherein refer to is defined: to relate to; apply to; mean or denote. (Dictionary.com) 20 in: (used to indicate inclusion within something abstract or immaterial). (Dictionary.com) 21 between: linking; connecting. (Dictonary.com) 22 propagation: the act of propagating, wherein propagating is defined: to create (an effect) at a distance, as by electromagnetic waves, compression waves, etc., traveling through space or a physical medium; transmit. , wherein transmit is defined: to send or forward, as to a recipient or destination; dispatch; convey, wherein to is defined: (used for expressing reference, reaction, or relation), wherein relation is defined: an existing connection; a significant association between or among things. (Dictionary.com) . 23 and: (used to connect alternatives). (Dictionary.com) 24 The text in {{{triple brackets}}} “does not limit the scope of a claim” via MPEP 2143.03 All Claim Limitations Must Be Considered [R-01.2024] "All words in a claim must be considered in judging the patentability of that claim against the prior art." In re Wilson, 424 F.2d 1382, 1385, 165 USPQ 494, 496 (CCPA 1970). Examiners must consider all claim limitations when determining patentability of an invention over the prior art. In re Gulack, 703 F.2d 1381, 1385, 217 USPQ 401, 403-04 (Fed. Cir. 1983). The subject matter of a properly construed claim is defined by the terms that limit the scope of the claim when given their broadest reasonable interpretation. In Axonics, Inc. v. Medtronic, Inc., 73 F.4th 950, 958-59, 2023 USPQ2d 795 (Fed. Cir. 2023), the court found the claims were improperly narrowed based on a preferred embodiment to sacral anatomy or sacral neuromodulation, whereas the patent claims made no reference to sacral anatomy or sacral neuromodulation. Thus, the relevant prior art was improperly limited to a narrow subset of claim scope. See also MPEP § 2111 et seq. It is the subject matter of the properly construed claim that must be examined. The determination of whether particular language is a limitation in a claim depends on the specific facts of the case. See, e.g., Griffin v. Bertina, 285 F.3d 1029, 1034, 62 USPQ2d 1431 (Fed. Cir. 2002). As a general matter, the grammar and ordinary meaning of terms (“and” “or”) as understood by one having ordinary skill in the art used in a claim will dictate whether, and to what extent, the language limits the claim scope. Language (“and” “or”) that suggests or makes a feature or step optional but does not require that feature or step does not limit the scope of a claim under the broadest reasonable claim interpretation. In addition, when a claim requires selection of an element from a list of alternatives, the prior art teaches the element if one of the alternatives is taught by the prior art. See, e.g., Fresenius USA, Inc. v. Baxter Int’l, Inc., 582 F.3d 1288, 1298, 92 USPQ2d 1163, 1171 (Fed. Cir. 2009). The following types of claim language may raise a question as to its limiting effect (this list is not exhaustive): • preamble (MPEP § 2111.02); • clauses such as "adapted to," adapted for," "wherein," and "whereby" (MPEP § 2111.04, subsection I); • contingent limitations (MPEP § 2111.04, subsection II); • printed matter (MPEP § 2111.05); and • functional language associated with a claim term (MPEP § 2181). 25 (italics) represent claim limitations already taught 26 ellipses (…) represent claim limitations already taught 27 (italics) represent claim limitations already taught 28 ellipses (…) represent claim limitations already taught 29 The strike-out text “does not limit the scope of a claim under the broadest reasonable claim interpretation” via MPEP 2143.03 All Claim Limitations Must Be Considered [R-01.2024], 3rd para, 2nd & 3rd Ss: Language that suggests or makes a feature or step optional but does not require that feature or step does not limit the scope of a claim under the broadest reasonable claim interpretation. In addition, when a claim requires selection of an element from a list of alternatives, the prior art teaches the element if one of the alternatives is taught by the prior art. 30 annotations/labeling is interpreted as a tracing, drawing, delineating, marking, coloring, contouring etc. an image 31 (i.e., the reason/initial motivation/cause to combine references under 35 USC 103) 32 model: a simplified representation of a system or phenomenon, as in the sciences or economics, with any hypotheses required to describe the system or explain the phenomenon, often mathematically. (Dictionary.com) 33 The curly-bracket text “does not limit the scope of a claim under the broadest reasonable claim interpretation” via MPEP 2143.03 All Claim Limitations Must Be Considered [R-01.2024], 3rd para, 2nd & 3rd Ss: Language that suggests or makes a feature or step optional but does not require that feature or step does not limit the scope of a claim under the broadest reasonable claim interpretation. In addition, when a claim requires selection of an element from a list of alternatives, the prior art teaches the element if one of the alternatives is taught by the prior art. 34 segmentation is identification: “[0023] Segmenting the CT data may include… identifying one or more boundaries”, BUTLER. 35 data (i.e., a fact) is the character of being true (Dictionary.com) 36 -ing (of “using”): a suffix of nouns formed from verbs, expressing the action of the verb or its result, product, material, etc. (the art of building; a new building; cotton wadding ). (Dictionary.com) 37 node: a data point or cluster within a tree or other information structure, as defined by its relationship to another data point or cluster, wherein defined is defined: determined, fixed, or clearly marked out as to extent, outline, or form, wherein mark is defined: to notice or observe, wherein notice is defined: to perceive; become aware of, wherein perceive is defined: to recognize, discern, envision, or understand, wherein recognize is defined: to identify as something or someone previously seen, known, etc.. (Dictionary.com) 38 to: (used for expressing a resulting state or condition). (Dictionary.com) 39 The strike-out text “does not limit the scope of a claim under the broadest reasonable claim interpretation” via MPEP 2143.03 All Claim Limitations Must Be Considered [R-01.2024], 3rd para, 2nd & 3rd Ss: Language that suggests or makes a feature or step optional but does not require that feature or step does not limit the scope of a claim under the broadest reasonable claim interpretation. In addition, when a claim requires selection of an element from a list of alternatives, the prior art teaches the element if one of the alternatives is taught by the prior art. 40 weighted: having additional weight, wherein weight is defined: importance, moment, consequence, or effective influence. (Dictionary.com) 41 significant: important and deserving of attention; of consequence. Their advice played a significant role in saving my marriage. Synonyms: weighty, momentous, consequential (Dictionary.com) 42 adjacent: lying near, close, or contiguous; adjoining; neighboring, wherein contiguous is defined: touching; in contact, wherein contact is defined: immediate proximity or association, wherein immediate is defined: having no object or space intervening; nearest or next. (Dictionary.com) 43 for: intended to belong to, or be used in connection with. (Dictionary.com) 44 which: being previously mentioned. (Dictionary.com) 45 The strike-out text “does not limit the scope of a claim under the broadest reasonable claim interpretation” via MPEP 2143.03 All Claim Limitations Must Be Considered [R-01.2024], 3rd para, 2nd & 3rd Ss: Language that suggests or makes a feature or step optional but does not require that feature or step does not limit the scope of a claim under the broadest reasonable claim interpretation. In addition, when a claim requires selection of an element from a list of alternatives, the prior art teaches the element if one of the alternatives is taught by the prior art. 46 Applicant’s disclose: pg. 3,ll. 5-15: In yet further aspects of the present invention, there are provided a corresponding method, a computer program which comprises program code means for causing a computer to perform the steps of the method disclosed herein when said computer program is carried out on a computer as well as a non-transitory computer-readable recording medium that stores therein a computer program product, which, when executed by a processor, causes the method disclosed herein to be performed. pg. 12, ll. 15: --A computer program may be stored/distributed on a suitable non-transitory medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems.--. 47 The strike-out text “does not limit the scope of a claim under the broadest reasonable claim interpretation” via MPEP 2143.03 All Claim Limitations Must Be Considered [R-01.2024], 3rd para, 2nd & 3rd Ss: Language that suggests or makes a feature or step optional but does not require that feature or step does not limit the scope of a claim under the broadest reasonable claim interpretation. In addition, when a claim requires selection of an element from a list of alternatives, the prior art teaches the element if one of the alternatives is taught by the prior art. 48 CLAIM SCOPE: the claim scope of “in” (of “in which”) encompasses “training image slices of the training image data set” OR “the training image data set” OR “a first training image slice”. 49 CLAIM SCOPE: the claim scope of “in” (of “in which”) encompasses “training image slices of the training image data set” OR “the training image data set” OR “a first training image slice” 50 CLAIM SCOPE: the claim scope of “in” (of “in which”) encompasses “training image slices of the training image data set” OR “the training image data set” OR “a first training image slice”. 51 CLAIM SCOPE: the claim scope of “in” (of “in which”) encompasses “training image slices of the training image data set” OR “the training image data set” OR “a first training image slice”. 52 CLAIM SCOPE: the claim scope of “in” (of “in which”) encompasses ““training image slices of the training image data set” OR “the training image data set” OR “a first training image slice”. 53 CLAIM SCOPE: the claim scope of “in” (of “in which”) encompasses “training image slices of the training image data set” OR “the training image data set” OR “a first training image slice”. 54 “the”: (used distributively, to note any one separately) for, to, or in each; a or an. (Dictionary.com) 55 pixel: The most basic unit of an image displayed on a computer or television screen or on a printer. Pixels are generally arranged in rows and columns; a given combination among the pixels of various brightness and color values forms an image, wherein unit is defined: a single thing or person, wherein thing is defined: a material object without life or consciousness; an inanimate object. (Dictionary.com) 56 “the”: (used distributively, to note any one separately) for, to, or in each; a or an. (Dictionary.com) 57 “the”: (used distributively, to note any one separately) for, to, or in each; a or an. (Dictionary.com) 58 set: Mathematics. a collection of objects or elements classed together, wherein collection is defined: something that is collected; a group of objects or an amount of material accumulated in one location, especially for some purpose or as a result of some process (Dictionary.com) 59 group: any collection or assemblage of persons or things; cluster; aggregation, wherein assemblage is defined: a group of persons or things gathered or collected; an assembly; collection; aggregate, wherein aggregate is defined: Mathematics. set. (Dictionary.com)