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 .
Double Patenting
A rejection based on double patenting of the “same invention” type finds its support in the language of 35 U.S.C. 101 which states that “whoever invents or discovers any new and useful process... may obtain a patent therefor...” (Emphasis added). Thus, the term “same invention,” in this context, means an invention drawn to identical subject matter. See Miller v. Eagle Mfg. Co., 151 U.S. 186 (1894); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Ockert, 245 F.2d 467, 114 USPQ 330 (CCPA 1957).
A statutory type (35 U.S.C. 101) double patenting rejection can be overcome by canceling or amending the claims that are directed to the same invention so they are no longer coextensive in scope. The filing of a terminal disclaimer cannot overcome a double patenting rejection based upon 35 U.S.C. 101.
Claims 1-20 are provisionally rejected under 35 U.S.C. 101 as claiming the same invention as claims 1-13, 16-17, and 20 of copending Application No. 18/955,620 (reference application). This is a provisional statutory double patenting rejection since the claims directed to the same invention have not in fact been patented.
In regards to Claim 1, please see the table below illustrating the shared limitations:
Instant claim from 18/955,628
Reference claims 1 and 5 from 18/955,620
Claim 1: A method for validating an autonomous diagnosis of a patient, the method comprising: receiving a high-resolution image of a body part;
Claim 1: A method for autonomously diagnosing a disease of a patient, the method comprising: receiving a high-resolution image of a body part;
dividing the high-resolution image into a plurality of tiles;
dividing the high-resolution image into a plurality of tiles;
inputting a representation of each of the plurality of tiles into an encoder portion of a model, the model configured to perform a disease diagnosis based on the representations, and the encoder having an attention mechanism; obtaining a plurality of tokens representative of an attention of the encoder based on the attention mechanism, each token associated with a position of a tile of the plurality of tiles;
generating a plurality of embeddings comprising of an embedding for each tile of the plurality of tiles, each embedding having a position encoding corresponding to its tile’s position in the image; inputting the plurality of embeddings into a linear projection model whose output feeds a transformer; and receiving, as output from a model comprising the transformer, a diagnosis of a disease of the body part (The Examiner notes that the plurality of embeddings which are input into a linear projection model and output to a transformer are analogous to the instant claims “encoder having an attention mechanism”. Additionally, the output from the model comprising the transformer is analogous to instant claims “obtaining a plurality of tokens”. [See specifically Fig. 4 from the instant application and the reference application]).
and generating for display a heat map corresponding to the image of the body part, the heat map comprising a two-dimensional image having pixels corresponding to tiles each with an amplitude based on a level of attention represented in the plurality of tokens corresponding to the tiles.
Claim 5 (which inherits the limitations from claim 1): generating for display a heat map corresponding to the image of the body part, the heat map comprising a two-dimensional image of tokens having an amplitude based on an attention level output by the attention mechanism.
Instant claims 6, 11, and 16 are the non-transitory computer-readable medium for validating an autonomous diagnosis of a patient, method, and non-transitory computer-readable medium claims, respectively, corresponding to claim 1, and corresponds to the combination of claims 7 and 11, 13 and 16, and 17 and 20, respectively from reference application 18/955,620. Thereby, instant claims 6, 11, and 16 are hereby rejected similarly to claim 1.
In regards to Claim 2, please see the table below illustrating the shared limitations:
Instant claim from 18/955,628
Reference claim 2 from 18/955,620
Claim 2: The method of claim 1, further comprising: determining that the high-resolution image is high-resolution based on it having a resolution above a threshold resolution, wherein images having a resolution below the threshold resolution are used to perform diagnosis based on extracting features from the images using a feature extraction model and inputting the extracted features into a diagnostic model.
Claim 2: The method of claim 1, further comprising: determining that the high-resolution image is high-resolution based on it having a resolution above a threshold resolution, wherein images having a resolution below the threshold resolution are used to perform diagnosis based on extracting features from the images using a feature extraction model, and inputting the extracted features into a diagnostic model.
Instant claim 7 is the non-transitory computer-readable medium claim corresponding to claim 2, and corresponds to claim 8 from reference application 18/955,620. Thereby, instant claim 7 is hereby rejected similarly to claim 2.
In regards to Claim 3, please see the table below illustrating the shared limitations:
Instant claim from 18/955,628
Reference claim 3 from 18/955,620
Claim 3: The method of claim 1, wherein each tile is at least partially overlapping with at least one other tile
Claim 3: The method of claim 1, wherein each tile is at least partially overlapping with at least one other tile.
Instant claim 8 is the non-transitory computer-readable medium claim corresponding to claim 3, and corresponds to claim 9 from reference application 18/955,620. Thereby, instant claim 8 is hereby rejected similarly to claim 3.
In regards to Claim 4, please see the table below illustrating the shared limitations:
Instant claim from 18/955,628
Reference claim 4 from 18/955,620
Claim 4: The method of claim 1, wherein each tile is overlapping with at least half of at least one other tile.
Claim 4: The method of claim 1, wherein each tile is overlapping with at least half of at least one other tile.
Instant claim 9 is the non-transitory computer-readable medium claim corresponding to claim 4, and corresponds to claim 10 from reference application 18/955,620. Thereby, instant claim 9 is hereby rejected similarly to claim 4.
In regards to Claim 5, please see the table below illustrating the shared limitations:
Instant claims from 18/955,628
Reference claim 6 from 18/955,620
Claim 5: The method of claim 1, wherein the pixels of the heat map are arranged to reflect a collection of tiles that contributed to the diagnosis of the disease of the body part.
Claim 6: The method of claim 5 (The Examiner notes that the combination of claims 1 and 5 of the reference application correspond to claim 1 from the instant application.), wherein the heat map reflects a collection of tiles that contributed to the diagnosis of the disease of the body part.
Instant claim 10 is the non-transitory computer-readable medium claim corresponding to claim 5, and corresponds to claim 12 from reference application 18/955,620. Thereby, instant claim 10 is hereby rejected similarly to claim 5.
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.
Claims 1, 5-6, 10-11, 15-16 and 20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Thakrar et al. (“Semantic Retrieval of Similar Radiological Images using Vision Transformers, DOI: 10.1101/2023.02.16.23286056, Publication Year: 2023; hereinafter “Thakrar”).
Regarding Claim 1, Thakrar discloses a method for validating an autonomous diagnosis of a patient, the method comprising (see Fig. 1):
receiving a high-resolution image of a body part (Materials and Methods – Datasets, Thakrar discloses obtaining X-ray and CT scan of the lung.);
dividing the high-resolution image into a plurality of tiles (Materials and Methods – Model Training, Thakrar discloses using a vision transformer (ViT) which includes obtaining sample image patches from an image.);
inputting a representation of each of the plurality of tiles into an encoder portion of a model, the model configured to perform a disease diagnosis based on the representations, and the encoder having an attention mechanism (Materials and Methods, Thakrar discloses obtaining patches from the input image, which are input into the ViT to determine a classification relating to cardiomegaly, opacity, or emphysema. The Examiner notes that in the original description of a ViT from Dosovitskiy et al. (see document C1 referenced in IDS filed 01/07/2025), the image patches are converted into flattened linear vectors through linear projection (i.e., “a representation”) to generate an embedding, which is then input into an encoder.);
PNG
media_image1.png
632
668
media_image1.png
Greyscale
[AltContent: textbox (Visual Transformer (ViT) Architecture, obtained from https://en.wikipedia.org/wiki/Vision_transformer)]obtaining a plurality of tokens representative of an attention of the encoder based on the attention mechanism, each token associated with a position of a tile of the plurality of tiles (Fig. 1, Thakrar discloses a ViT which includes a transformer encoder. The Examiner notes that the input into the transformer includes positional embeddings, and additionally that the output from the transformer in a ViT also includes “a plurality of tokens”. (see additionally the image from Wikipedia).); and
generating for display a heat map corresponding to the image of the body part, the heat map comprising a two-dimensional image having pixels corresponding to tiles each with an amplitude based on a level of attention represented in the plurality of tokens corresponding to the tiles (Supplemental Figure 2, Thakrar discloses generating a cardiomegaly saliency map using Grad-CAM, which shows regions of high importance and low importance (i.e., based on a level of attention).).
Claims 6, 11, and 16 are the non-transitory computer-readable medium for validating an autonomous diagnosis of a patient, method, and non-transitory computer-readable medium claims, respectively, corresponding to claim 1, and are similarly rejected (see Materials and Methods – Model Training).
Regarding Claim 5, Thakrar discloses the method of claim 1, wherein the pixels of the heat map are arranged to reflect a collection of tiles that contributed to the diagnosis of the disease of the body part (Note the Grad-CAM method used to generate the cardiomegaly saliency map presented in Supplemental Figure 2.).
Claims 10, 15, and 20 are the non-transitory computer-readable medium for validating an autonomous diagnosis of a patient, method, and non-transitory computer-readable medium claims, respectively, corresponding to claim 5, and are similarly rejected (see Materials and Methods – Model Training).
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 2, 7, 12, and 17 are rejected as being unpatentable over Thakrar in view of Prasad et al. (US 2023/0334656; hereinafter “Prasad”).
Regarding Claim 2, Thakrar discloses the method of claim 1.
Thakrar does not explicitly disclose further comprising: determining that the high-resolution image is high-resolution based on it having a resolution above a threshold resolution, wherein images having a resolution below the threshold resolution are used to perform diagnosis based on extracting features from the images using a feature extraction model and inputting the extracted features into a diagnostic model.
Prasad discloses determining that the high-resolution image is high-resolution based on it having a resolution above a threshold resolution ([0028], [0035-0036], Prasad discloses a baseline resolution, and images above the baseline are considered high resolution images and images below the baseline resolution are considered to be ), wherein images having a resolution below the threshold resolution are used to perform diagnosis based on extracting features from the images using a feature extraction model and inputting the extracted features into a diagnostic model ([0065], Prasad discloses extracting features from low-resolution images, which are then input into a classifier model.).
Thakrar and Prasad are considered to be analogous to the claimed invention as they are in the same field of processing medical images using deep learning methods. Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Thakrar such that it incorporates the identification and processing of low resolution images as disclosed by Prasad. The motivation for this combination being the ability to adjust the processing methodology such that it is optimized based on the resolution of the image.
Claims 7, 12, and 17 are the non-transitory computer-readable medium for validating an autonomous diagnosis of a patient, method, and non-transitory computer-readable medium claims, respectively, corresponding to claim 2 , and are similarly rejected (see Materials and Methods – Model Training).
Claims 3-4, 8-9, 13-14, and 18-19 are rejected as being unpatentable over Thakrar in view of Kirsten et al. (US 2023/0343119; hereinafter “Kirsten”).
Regarding Claim 3, Thakrar discloses the method of claim 1.
Thakrar does not disclose wherein each tile is at least partially overlapping with at least one other tile.
Kirsten discloses wherein each tile is at least partially overlapping with at least one other tile ([0037], Kirsten discloses dividing a 256x256 image into a plurality of image patches, wherein the image patches are overlapping with a stride of 128.).
Thakrar and Kirsten are considered to be analogous to the claimed invention as they are in the same field of processing images by tiling the images prior to being input into a deep learning model. Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Thakrar such that it incorporates the specific overlapping tiling process disclosed by Kirsten. The motivation for this combination being the ability to maintain context from surrounding image patches during processing.
Claims 8, 13, and 18 are the non-transitory computer-readable medium for validating an autonomous diagnosis of a patient, method, and non-transitory computer-readable medium claims, respectively, corresponding to claim 1, and are similarly rejected (see Materials and Methods – Model Training).
Regarding Claim 4, Thakrar discloses the method of claim 1.
Thakrar does not disclose wherein each tile is overlapping with at least half of at least one other tile.
Kirsten discloses wherein each tile is overlapping with at least half of at least one other tile ([0037], Kirsten discloses dividing a 256x256 image into a plurality of image patches, wherein the image patches are overlapping with a stride of 128 (i.e., half).).
Thakrar and Kirsten are considered to be analogous to the claimed invention as they are in the same field of processing images by tiling the images prior to being input into a deep learning model. Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Thakrar such that it incorporates the specific overlapping tiling process disclosed by Kirsten. The motivation for this combination being the ability to maintain context from surrounding image patches during processing.
Claims 9, 14, and 19 are the non-transitory computer-readable medium for validating an autonomous diagnosis of a patient, method, and non-transitory computer-readable medium claims, respectively, corresponding to claim 1, and are similarly rejected (see Materials and Methods – Model Training).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PROMOTTO TAJRIAN ISLAM whose telephone number is (703)756-5584. The examiner can normally be reached Monday - Friday 8:30 am - 5:00 pm 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, Chan Park can be reached at (571) 272-7409. 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.
/PROMOTTO TAJRIAN ISLAM/
Examiner, Art Unit 2669
/SUMATI LEFKOWITZ/Supervisory Patent Examiner, Art Unit 2672
Prosecution Insights