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 Remark(s)
Applicant's amendment filed April 16th, 2026 have been fully entered and considered. Regarding the arguments to the previous prior art rejections, new grounds of rejections are necessitated by the amendment, however, the examiner respectfully finds the arguments to be non-persuasive, see response to remarks section below. Accordingly, this action is made final.
Status of Claims
Claims 1, 3-7 are pending, claims 1 and 6-7 have been amended, claim 2 has been canceled. Claims 1, 3-7 remains rejected.
Response to Argument(s)
The amendment has narrowed down the scope of the claim, by moving the limitation from the previously presented claim 2 and narrowed down the limitation to be incorporated into the independent claims 1, 6 and 7 such as, for the limitation of:
“when an image is input, the mathematical model is configured to output, as the medical data, data of high-quality image having reduced noise with respect to the input image.
Wherein the limitation has added further the feature that is different to the previously recited claim 2, is that “data of high-quality image having reduced noise with respect to the input image”. that the high-quality image is by having reduced noise, which has narrowed down further the scope of the claim, require new grounds of rejections. However, regarding other limitations in the claim, the examiner finds the arguments to be non-persuasive, see replies below.
102 and 103 rejections:
In pages 5-8, of the remarks, the Applicants argue that the proposed Brosch does not teach or suggest the features of the independent claims 1, 6 and 7:
“perform a tilt-reduction process on the acquired tomographic image to reduce a tilt of the layer of the living tissue with respect to a main direction;
acquire medical data by inputting, into a mathematical model, a tilt-reduced image that is the tomographic image on which the tilt-reduction process was performed;
when an image is input, the mathematical model is configured to output, as the medical data, data of high-quality image having reduced noise with respect to the input image”
In support of the above argument, the Applicants state that, regarding the limitation of “when an image is input,….reduced noise with respect to the input image”, Brosch’s output of the neural network is distance values between surface elements and the object boundary, together with confidence information regarding the reliability of those distance predictions, see Brosch’s pars. [0092-0093]. Thus, Brosch teaches a different method to the claimed limitation.
Furthermore, the Applicants assert that, regarding the limitation of “perform a tilt-reduction process…with respect to a main direction”, Brosch teaches the tilt is applied to or corrected in the model space, not to the image data itself, wherein Brosch’s Par. [0036] discloses “estimate with one or several trained convolutional neural networks the displacement of the respective subvolume center, i.e., for instance, the mesh point…with respect to the desired model surface, i.e. the boundary of the object in the image…to adapt the surface model to the object in the image”.
Therefore, the Applicants believe that Brosch does not teach or suggest the limitations as mentioned.
Examiner’s reply:
The examiner respectfully disagrees with the Applicants’ arguments and find them to be non-persuasive and incommensurate with the scope of the claim. The Applicants are respectfully reminded that the claims are construed based on BRI (broadest reasonable interpretation) scope in light of the specification. Therefore, the examiner finds the claims to fall within the teachings of the prior art Brosch.
Regarding, the limitation of “when an image is input,….reduced noise with respect to the input image,” as stated above, the examiner understands the Applicants argue that the output of Brosch’s neural network being “distance values between surface elements and the object boundary, together with confidence information regarding the reliability of those distance predictions” hence, is not data of high-quality image having reduced noise with respect to the input image. As according to the argument, the examiner finds that Brosch’s Par. [0092] to disclose “the training unit is further adapted to determine actual distances for the surface elements of the modified training surface models, i.e. of the displaced and/or tiled surface elements….in the training image and which has been provided by the training data” indicating the input into the neural network being an input image, furthermore Par. [0094] further discloses “the training unit can also be adapted to determine simulated distances for the surface elements of the modified training surface models….the neural network providing unit is then adapted to provide a further convolutional neural network for determining confidence values for surface elements of a surface model of an object…regarded as being a confidence convolutional neural network, can be used during a segmentation of an object in an image as explained above” indicating that the confidence neural network being input the image, can be output a confidence value used to perform segmentation of an object in an image with higher confidence of the segmentation of the object, indicating that the output of the neural network is to have image with high quality with respect to the input image, and that the examiner finds the whole process including the use of the corresponding neural networks to the step of segmentation to result in an output image of higher confidence of object segmentation is part of the mathematical model to have an input of an image and output of image with better confidence in result, which was previously mapped in the rejection of the previously presented claim 2. Furthermore, for the added features that “the high-quality image is by having reduced noise”, the examiner still finds Brosch to teach, under Par. [0109], which discloses “with particular surface element, can be either predetermined, i.e., for instance, different networks for different organs or organ structures, or learned during training. In particular, a subset of triangles associated with a high boundary detection error after initial training may be selected and used to train a second neural network in order to further improve boundary detection…an extra neural network may be trained to provide confidence scores, i.e., the confidence values, that can be used to increase or decrease the external energy, i.e., the “image force”, associated with the detected boundary” indicating that the confidence scores can be used to further decrease the external energy of the image causing the error in boundary detection, therefore, the result of the image with higher confidence in detection with image resulted with less error (reduced noise) which is analogous to “the high-quality image is by having reduced noise”. Therefore, the proposed Borsch teaches this claimed limitation.
Regarding, the limitation of “perform a tilt-reduction process…with respect to a main direction”, the examiner understand the Applicants centrally argue that Brosch teaches the tilt is applied to or corrected in the model space, not to the image data itself. However, the Applicants cited the part of the reference wherein, “the step of tilting or displacement of elements of the surface model of the mesh for the purpose of training or deforming the model to match an object boundary”, the Applicants excluded that the matching to the object boundary is of an image itself, therefore, the result of the tilting and displacement is to have a model that can be matched correctly with the image (which is the output of the processing), hence, the image output here being processed a tilting, displacement for accurate matching, therefore, it is within the scope that the performing of the tilt-reduction process is on the image itself, since the mesh is derived from the image and the output is a matched output image with surface element has tilt reduced. Therefore, the prior art teaches the steps of the claims.
Therefore, the prior art rejections remain.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1, 3-4 and 6-7 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Tom Brosch et. al. (“US 2020/0410691 A1” hereinafter as “Brosch”).
Regarding claim 1, Brosch discloses a medical image processing device that processes tomographic image data of a living tissue (Par. [0109] discloses the field of relevant radiation therapy for this invention includes tomography images of organs [living tissue]), the device comprising: a control unit that includes at least one processor and at least one memory storing computer program code, the computer program code, when executed by the at least one processor, causing the at least one processor to (Par. [0003] discloses the method for computer processing which includes the use of a computer, which has a processor to execute instructions stored in a memory to carry out the invention ): acquire a tomographic image in which a layer of the living tissue appears (Par. [0036] disclose the invention includes identifying surface [layer] of the surface element of the organ); perform a tilt-reduction process on the acquired tomographic image to reduce a tilt of the layer of the living tissue with respect to a main direction (Par. [0036] discloses the training unit is to displace a surface element and tilt a surface element for modifying the surface element [to reduce the deviation/tilt according to 0093], wherein the deviation is a distance from the respective distance to actual distance and the distance is determined based on a direction according to Par. [0015] which is analogous to the main direction as claimed; therefore, the result of the tilting and displacement is to have a model that can be matched correctly with the image (which is the output of the processing), hence, the image output here being processed a tilting, displacement for accurate matching, therefore, it is within the scope that the performing of the tilt-reduction process is on the image itself, since the mesh is derived from the image and the output is a matched output image with surface element has tilt reduced. Therefore, the prior art teaches the steps of the claims); and acquire medical data by inputting, into a mathematical model, a tilt-reduced image that is the tomographic image on which the tilt-reduction process was performed (Par. [0092] discloses the image is being input image into the machine learning model to calculate the deviation/tile to modify the surface element to reduce the deviation/tile, using convolutional neural network [mathematical model]), wherein the mathematical model is trained by a machine learning algorithm to output medical data by processing an input image (Par. [0093] discloses the neural network is trained using machine learning on the medical image); wherein when an image is input, the mathematical model is configured to output, as the medical data, data of a high-quality image having reduced noise with respect to the input image (Par. [0092] to disclose “the training unit is further adapted to determine actual distances for the surface elements of the modified training surface models, i.e. of the displaced and/or tiled surface elements….in the training image and which has been provided by the training data” indicating the input into the neural network being an input image, furthermore Par. [0094] further discloses “the training unit can also be adapted to determine simulated distances for the surface elements of the modified training surface models….the neural network providing unit is then adapted to provide a further convolutional neural network for determining confidence values for surface elements of a surface model of an object…regarded as being a confidence convolutional neural network, can be used during a segmentation of an object in an image as explained above” indicating that the confidence neural network being input the image, can be output a confidence value used to perform segmentation of an object in an image with higher confidence of the segmentation of the object, indicating that the output of the neural network is to have image with high quality with respect to the input image, and that the examiner finds the whole process including the use of the corresponding neural networks to the step of segmentation to result in an output image of higher confidence of object segmentation is part of the mathematical model to have an input of an image and output of image with better confidence in result, which was previously mapped in the rejection of the previously presented claim 2. Furthermore, for the added features that “the high-quality image is by having reduced noise”, the examiner still finds Brosch to teach, under Par. [0109], which discloses “with particular surface element, can be either predetermined, i.e., for instance, different networks for different organs or organ structures, or learned during training. In particular, a subset of triangles associated with a high boundary detection error after initial training may be selected and used to train a second neural network in order to further improve boundary detection…an extra neural network may be trained to provide confidence scores, i.e., the confidence values, that can be used to increase or decrease the external energy, i.e., the “image force”, associated with the detected boundary” indicating that the confidence scores can be used to further decrease the external energy of the image causing the error in boundary detection, therefore, the result of the image with higher confidence in detection with image resulted with less error (reduced noise) which is analogous to “the high-quality image is by having reduced noise”).
Regarding claim 3, Brosch discloses the medical image processing device according to claim 1, wherein the at least one processor is further caused to restore an arrangement of the medical data to an original arrangement of the medical data prior to the tilt-reduction process being performed by performing (Par. [0107] discloses generation of training data by displacing and tile the surface elements by known amounts for generating the modified training surface models for training, using back propagation, therefore, it can be understood as the training data being generated prior to performing modifying and reducing the tile by the neural network, the synthesizing of training image restore the images into original tiled images for training purpose, therefore, it can be understood as restoring an arrangement to original tiled arrangement by a known amount; since the displacement here is being known being acquired from Par. [0106]), on the acquired medical data output from the mathematical model, an opposite process to the tilt-reduction process (the process as discussed as disclosed in [0107] is an opposite process to the tile reduction process using back propagation).
Regarding claim 4, Brosch discloses the medical image processing device according to claim 1, wherein the at least one processor is further caused to: extract, from the tomographic image, an image region in which the tissue appears (Par. [0015] discloses the organ region is extracted from the tomographic image); and input, into the mathematical model, the image region of the tomographic image on which the tilt-reduction process was performed (Par. [0015-0016] discloses the surface element is obtained, which is used to perform the tilt reduction process of Par. [0092]).
Regarding claim 6, Brosch discloses a non-transitory, computer readable storage medium storing a medical image processing program executed by a medical image processing device that processes tomographic image data of a living tissue, the program, when executed by at least one processor of the medical image processing device, causing the at least one processor to (Par. [0003] discloses the method for computer processing which includes the use of a computer, which has a processor to execute instructions stored in a memory or a RAM/ROM [non-transitory storage medium] to carry out the invention): acquire a tomographic image in which a layer of the living tissue appears (Par. [0036] disclose the invention includes identifying surface [layer] of the surface element of the organ); perform a tilt-reduction process on the acquired tomographic image to reduce a tilt of the layer of the living tissue with respect to a main direction (Par. [0036] discloses the training unit is to displace a surface element and tilt a surface element for modifying the surface element [to reduce the deviation/tilt according to 0093], wherein the deviation is a distance from the respective distance to actual distance and the distance is determined based on a direction according to Par. [0015] which is analogous to the main direction as claimed); and acquire medical data by inputting, into a mathematical model, a tilt-reduced image that is the tomographic image on which the tilt-reduction process was performed (Par. [0092] discloses the image is being input image into the machine learning model to calculate the deviation/tile to modify the surface element to reduce the deviation/tile, using convolutional neural network [mathematical model]), wherein the mathematical model is trained by a machine learning algorithm to output medical data by processing an input image (Par. [0093] discloses the neural network is trained using machine learning on the medical image) ; wherein when an image is input, the mathematical model is configured to output, as the medical data, data of a high-quality image having reduced noise with respect to the input image (Par. [0092] to disclose “the training unit is further adapted to determine actual distances for the surface elements of the modified training surface models, i.e. of the displaced and/or tiled surface elements….in the training image and which has been provided by the training data” indicating the input into the neural network being an input image, furthermore Par. [0094] further discloses “the training unit can also be adapted to determine simulated distances for the surface elements of the modified training surface models….the neural network providing unit is then adapted to provide a further convolutional neural network for determining confidence values for surface elements of a surface model of an object…regarded as being a confidence convolutional neural network, can be used during a segmentation of an object in an image as explained above” indicating that the confidence neural network being input the image, can be output a confidence value used to perform segmentation of an object in an image with higher confidence of the segmentation of the object, indicating that the output of the neural network is to have image with high quality with respect to the input image, and that the examiner finds the whole process including the use of the corresponding neural networks to the step of segmentation to result in an output image of higher confidence of object segmentation is part of the mathematical model to have an input of an image and output of image with better confidence in result, which was previously mapped in the rejection of the previously presented claim 2. Furthermore, for the added features that “the high-quality image is by having reduced noise”, the examiner still finds Brosch to teach, under Par. [0109], which discloses “with particular surface element, can be either predetermined, i.e., for instance, different networks for different organs or organ structures, or learned during training. In particular, a subset of triangles associated with a high boundary detection error after initial training may be selected and used to train a second neural network in order to further improve boundary detection…an extra neural network may be trained to provide confidence scores, i.e., the confidence values, that can be used to increase or decrease the external energy, i.e., the “image force”, associated with the detected boundary” indicating that the confidence scores can be used to further decrease the external energy of the image causing the error in boundary detection, therefore, the result of the image with higher confidence in detection with image resulted with less error (reduced noise) which is analogous to “the high-quality image is by having reduced noise”).
Regarding claim 7, Brosch discloses a medical image processing method implemented by a medical image processing device that processes tomographic image data of a living tissue, the method comprising: (Par. [0003] discloses the method for computer processing which includes the use of a computer, which has a processor to execute instructions stored in a memory to carry out the invention): acquiring a tomographic image in which a layer of the living tissue appears (Par. [0036] disclose the invention includes identifying surface [layer] of the surface element of the organ); performing a tilt-reduction process on the acquired tomographic image to reduce a tilt of the layer of the living tissue with respect to a main direction ([0036] discloses the training unit is to displace a surface element and tilt a surface element for modifying the surface element [to reduce the deviation/tilt according to 0093], wherein the deviation is a distance from the respective distance to actual distance and the distance is determined based on a direction according to [0015] which is analogous to the main direction as claimed); and acquiring medical data by inputting, into a mathematical model, a tilt-reduced image that is the tomographic image on which the tilt-reduction process was performed ([0092] discloses the image is being input image into the machine learning model to calculate the deviation/tile to modify the surface element to reduce the deviation/tile, using convolutional neural network [mathematical model]), wherein the mathematical model is trained by a machine learning algorithm to output medical data by processing an input image ([0093] discloses the neural network is trained using machine learning on the medical image) ; wherein when an image is input, the mathematical model is configured to output, as the medical data, data of a high-quality image having reduced noise with respect to the input image (Par. [0092] to disclose “the training unit is further adapted to determine actual distances for the surface elements of the modified training surface models, i.e. of the displaced and/or tiled surface elements….in the training image and which has been provided by the training data” indicating the input into the neural network being an input image, furthermore Par. [0094] further discloses “the training unit can also be adapted to determine simulated distances for the surface elements of the modified training surface models….the neural network providing unit is then adapted to provide a further convolutional neural network for determining confidence values for surface elements of a surface model of an object…regarded as being a confidence convolutional neural network, can be used during a segmentation of an object in an image as explained above” indicating that the confidence neural network being input the image, can be output a confidence value used to perform segmentation of an object in an image with higher confidence of the segmentation of the object, indicating that the output of the neural network is to have image with high quality with respect to the input image, and that the examiner finds the whole process including the use of the corresponding neural networks to the step of segmentation to result in an output image of higher confidence of object segmentation is part of the mathematical model to have an input of an image and output of image with better confidence in result, which was previously mapped in the rejection of the previously presented claim 2. Furthermore, for the added features that “the high-quality image is by having reduced noise”, the examiner still finds Brosch to teach, under Par. [0109], which discloses “with particular surface element, can be either predetermined, i.e., for instance, different networks for different organs or organ structures, or learned during training. In particular, a subset of triangles associated with a high boundary detection error after initial training may be selected and used to train a second neural network in order to further improve boundary detection…an extra neural network may be trained to provide confidence scores, i.e., the confidence values, that can be used to increase or decrease the external energy, i.e., the “image force”, associated with the detected boundary” indicating that the confidence scores can be used to further decrease the external energy of the image causing the error in boundary detection, therefore, the result of the image with higher confidence in detection with image resulted with less error (reduced noise) which is analogous to “the high-quality image is by having reduced noise”).
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 5 is rejected under 35 U.S.C. 103 as being unpatentable over Tom Brosch et. al. (“US 2020/0410691 A1” hereinafter as “Brosch”) in view of Terry Fritz Helmuth Fritz (Foreign Patent Document “CN 1765330 A” hereinafter as “Fritz”).
Regarding claim 5, Brosch discloses the medical image processing device according to claim 1 (as discussed above in claim 1).
However, Brosch does not explicitly disclose wherein the tomographic image is formed of a plurality of small regions each extending in a direction intersecting the main direction, and the at least one processor is further caused to align positions of the plurality of small regions with each other by moving the plurality of small regions in the direction intersecting the main direction.
In the same field of tissue tomography image tilt correction (page 2, 4th to the last par., and page 3, 2nd par., Fritz) Fritz discloses wherein the tomographic image is formed of a plurality of small regions each extending in a direction intersecting the main direction (page 3, 2nd par., disclose the image for processing includes tomography image, moreover, the image includes different directions according to page 3, 4th par., with different axes and a longitudinal direction extend from the horizontal axis, moreover, the image includes these axes and different regions corresponding to the directions as disclosed in page 3, 4th par., and page 5, 2nd par.), and the at least one processor is further caused to align positions of the plurality of small regions with each other by moving the plurality of small regions in the direction intersecting the main direction (the correction of the tilt of the organ layer based on the image according to page 3, 4th to the last par., includes correcting the mismatch of the image with reference axial direction by matching the image frame according to the reference axial direction by moving the regions or the axes and different corresponding directions and regions such as disclosed in page 16, 3rd to the last par.; the directions crossing each other according to page 3, 2nd to the last par.).
Thus, it would have been obvious for a person of ordinary skill in the art before the effective filing date to modify Brosch to perform obtaining of a tomographic image of a living tissue, wherein the tomographic image is formed of a plurality of small regions each extending in a direction intersecting the main direction, and the at least one processor is further caused to align positions of the plurality of small regions with each other by moving the plurality of small regions in the direction intersecting the main direction as taught by Fritz to arrive at the claimed invention discussed above. Such a modification is the result of combing prior art elements according to known methods to yield predictable results. The motivation for the proposed modification would have been to process tissue image correctly with reduced nose and tilt effectively based on directions and intersecting (abstract, and page 2, 4th to the last par., Fritz)
Conclusion
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 PHUONG HAU CAI whose telephone number is (571)272-9424. The examiner can normally be reached M-F 8:30 am - 5:00pm.
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, Chineyere Wills-Burns can be reached at (571) 272-9752. 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.
/PHUONG HAU CAI/Examiner, Art Unit 2673
/CHINEYERE WILLS-BURNS/Supervisory Patent Examiner, Art Unit 2673
Prosecution Insights