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 .
Information Disclosure Statement
The IDS received 09/24/2024 has been fully considered.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-5, 8-12, and 15-18 are rejected under 35 U.S.C. 103 as being unpatentable over Mandabhushi (US 10861156 B2) in view of Lefebvre (US 7657070 B2).
With respect to claim 1, Mandabhushi teaches a method for processing an electronic image of a slide containing a specimen (see figure 8 element 108), the method comprising:
receiving a target electronic image of a slide corresponding to a target specimen (see figure 8 element 108), the specimen comprising a tissue sample from a patient (“Digital pathology (DP) is a part of both clinical diagnostic workflows and computational pathology. DP refers to the digitization of tissue slides, including the digitization of histology slides” page 15 col 1 lines 21-24);
applying a first machine learning model to the target electronic image to predict a presence of a feature correlating with a need for additional testing (“Embodiments thus facilitate identifying those DP slides that might require additional scrutiny faster and more accurately than existing approaches to DP QC.” Page 17 col 5 lines 54-56), wherein the first machine learning model is trained by processing a plurality of training images (“In this example, embodiments may be employed to select a set of DP images from a plurality of DP images (i.e., from a cohort) for analysis or downstream computation (e.g., for training a machine learning classifier)” page 18 col 7 lines 52-55) and training data associated with the training images to predict a likelihood that a new stain is desired for the slide (“In this example, embodiments split the plurality of DP images into sub-cohorts based on the application of the first HistoQC pipeline. Since different modules may function differently at different magnifications, the plurality of DP images may be divided into a first magnification cohort (e.g., 20×), and a second magnification cohort (e.g., 40×). Embodiments may define cohorts further based on the number of internal storage format levels (i.e., “levels”), or image properties, including lightness, stain intensity, or other image properties, of the DP image.” Page 18 col 8 lines 7-16 and “In this example, the first, low-computation cost pipeline may also detect gross defects in a DP image, including gross defects that require fewer computational resources to detect than more subtle defects, and reject a DP image with a gross defect from further downstream computation or diagnostic use, without providing the DP image to the higher-computational cost HistoQC pipeline” pages 18-19 cols 8 (lines 62-67) – 9 (lines 1-2) and “For example, a module “getIntensityThresholdPercent” may apply a threshold to a DP image. In this example, “getIntensityThresholdPercent:tissue” applies a higher threshold to remove the background of the slide, while “getIntensityThresholdPercent:darkTissue” applies a lower threshold to identify regions in the DP image that contain artifacts, including folded tissue or overstaining.” Page 19 col 9 lines 5-11 and “Additionally, more subtle artifacts, which might not even be perceivable to a human eye, such as variations in stain, slide thickness, compression, texture differences in tissue presentation, differences in microns per pixel, or blurring, that may not affect a pathologist's diagnostic interpretation, or which are impossible or unlikely to be perceived during manual QC, may still have implications for subsequent computational image analysis and machine learning algorithms.” Pages 15-16 cols 2 (lines 60-67) – 3 (line 1));
generating, using a second machine learning model (“A HistoQC pipeline may employ a module multiple times with different settings or parameters, or different HistoQC pipelines (e.g., a first, low-cost HistoQC pipeline, and a second, different, higher-cost HistoQC pipeline) may employ a module multiple times with different settings or parameters. A HistoQC pipeline may define values for parameters associated with a module.” Page 19 col 9 lines 11-18; model as module), a predicted likelihood that a new stain is desired for the slide based on the prediction generated by the first machine learning model (“In this example, embodiments split the plurality of DP images into sub-cohorts based on the application of the first HistoQC pipeline. Since different modules may function differently at different magnifications, the plurality of DP images may be divided into a first magnification cohort (e.g., 20×), and a second magnification cohort (e.g., 40×). Embodiments may define cohorts further based on the number of internal storage format levels (i.e., “levels”), or image properties, including lightness, stain intensity, or other image properties, of the DP image.” Page 18 col 8 lines 7-16 and “In this example, the first, low-computation cost pipeline may also detect gross defects in a DP image, including gross defects that require fewer computational resources to detect than more subtle defects, and reject a DP image with a gross defect from further downstream computation or diagnostic use, without providing the DP image to the higher-computational cost HistoQC pipeline” pages 18-19 cols 8 (lines 62-67) – 9 (lines 1-2) and “For example, a module “getIntensityThresholdPercent” may apply a threshold to a DP image. In this example, “getIntensityThresholdPercent:tissue” applies a higher threshold to remove the background of the slide, while “getIntensityThresholdPercent:darkTissue” applies a lower threshold to identify regions in the DP image that contain artifacts, including folded tissue or overstaining.” Page 19 col 9 lines 5-11 and “Additionally, more subtle artifacts, which might not even be perceivable to a human eye, such as variations in stain, slide thickness, compression, texture differences in tissue presentation, differences in microns per pixel, or blurring, that may not affect a pathologist's diagnostic interpretation, or which are impossible or unlikely to be perceived during manual QC, may still have implications for subsequent computational image analysis and machine learning algorithms.” Pages 15-16 cols 2 (lines 60-67) – 3 (line 1)); and based on the prediction of the second machine learning model, determining that slide is undesirable and should remain unused (see figure 8). Mandabhushi however does not teach automatically order an additional slide to be prepared.
Lefebvre teaches determining to automatically order an additional slide to be prepared (see figure 1 and “Generation of additional microscope slides can be instructed automatically depending on the determination of the interpretation system (such as additional staining, or additional sectioning, staining coverslipping, or additional sample gathering, processing, embedding, sectioning, coverslipping etc.)” page 10 col 2 lines 62-66).
Lefebvre is analogous art in the same field of endeavor as the claimed invention. Lefebvre is directed towards “…a system of processing and examining biological specimens in a laboratory environment.“ (page 10 col 1 field of invention). A person of ordinary skill in the art before the effective filing date of the claimed invention would have found it obvious to utilize the modular quality assessment processes of Mandabhushi in combination with the interpretation based slide processing of Lefebvre by substituting its processes in place of the similar mask based quality assessment process of Mandabhusi, with the expectation that doing so would lead to increases in accuracy of automation and reduction in the amount of time and transport that specimens go through during the examination process, reducing inconvenience and degradation (“…increases automation and accuracy involved in automation, reduces the amount of transport of processed specimens in the examination process, and reduces lag times, inconvenience and potential for degradation involved in iterative diagnostic and processing steps.” Page 10 col 2 lines 18-20 And “The present invention alleviates to a great extent the disadvantages of the known systems and methods of automated biological specimen processing and examination by providing an automated system in which biological specimens are processed with feedback data provided via networked communications, and wherein diagnostic image data is created and delivered to desired people, such as diagnosticians, and further instructions can be generated for iterative processing and review, without the necessity of individual slide review, if desired.” Page 10 col. 2 lines 26-30).
With respect to claim 2, Mandabhushi and Lefebvre teach the method of claim 1. Mandabhushi teaches wherein determining to automatically order an additional slide to be prepared comprises determining that the predicted likelihood of the second machine learning model is greater than or equal to a predetermined amount (“For example, a module “getIntensityThresholdPercent” may apply a threshold to a DP image. In this example, “getIntensityThresholdPercent:tissue” applies a higher threshold to remove the background of the slide, while “getIntensityThresholdPercent:darkTissue” applies a lower threshold to identify regions in the DP image that contain artifacts, including folded tissue or overstaining.” Page 19 col 9 lines 5-11 and “Additionally, more subtle artifacts, which might not even be perceivable to a human eye, such as variations in stain, slide thickness, compression, texture differences in tissue presentation, differences in microns per pixel, or blurring, that may not affect a pathologist's diagnostic interpretation, or which are impossible or unlikely to be perceived during manual QC, may still have implications for subsequent computational image analysis and machine learning algorithms.” Pages 15-16 cols 2 (lines 60-67) – 3 (line 1)). Lefebvre teaches automatically ordering the additional slide to be prepared (see figure 1 and “Generation of additional microscope slides can be instructed automatically depending on the determination of the interpretation system (such as additional staining, or additional sectioning, staining coverslipping, or additional sample gathering, processing, embedding, sectioning, coverslipping etc.)” page 10 col 2 lines 62-66).
With respect to claim 3, Mandabhushi and Lefebvre teaches the method of claim 1. Lefebvre further teaches wherein automatically ordering the additional slide comprises ordering a new stain to be prepared for the slide corresponding to the target specimen (“Generation of additional microscope slides can be instructed automatically depending on the determination of the interpretation system (such as additional staining, or additional sectioning, staining coverslipping, or additional sample gathering, processing, embedding, sectioning, coverslipping etc.)” page 10 col 2 lines 62-66).
With respect to claim 4, Mandabhushi and Lefebvre teach the method of claim 1. Lefebvre further teaches wherein automatically ordering the additional slide comprises ordering a recut for the slide corresponding to the target specimen (“Generation of additional microscope slides can be instructed automatically depending on the determination of the interpretation system (such as additional staining, or additional sectioning, staining coverslipping, or additional sample gathering, processing, embedding, sectioning, coverslipping etc.)” page 10 col 2 lines 62-66).
With respect to claim 5, Mandabhushi and Lefebvre teaches the method of claim 1. Lefebvre further teaches it comprising: outputting an alert on a display indicating that the additional slide is being prepared (“In another aspect of the invention, image data may be transmitted through an information path (such as a network or plural networks) to an interpretation module, which communicates with one or more databases and conducts pattern recognition to assist in the automated interpretation. Once the interpretation has generated results, the system may then route the material to undergo additional testing, request additional material to be tested, or route the material to a diagnostician or storage facility. In one example, the diagnostician may be notified that results are available for their consideration by electronic notification, such as by an e-mail, computer screen pop-up announcement, banner announcement, pager message or automated phone call. The diagnostician may consider the image data, the interpretation report, and/or other data, and may agree with the interpretation, disagree, provide other diagnosis, or order additional procedures. The diagnostician or a technician also can optionally intervene and override recommendations of additional procedures by the interpretation module” page 11 col 3 lines 33-51).
With respect to claim 8, Mandabhushi and Lefebvre teach a system for processing an electronic image corresponding to a specimen and all additional limitations in consideration of substantially similar claim 1, due to claim 1 being directed towards the method conducted by the system. Mandabhushi further teaches the system comprising: at least one memory storing instructions (“The set of modules may have a computational cost (e.g., time, processor cycles, memory)” page 18 col. 7 lines 16-17); and at least one processor (“The set of modules may have a computational cost (e.g., time, processor cycles, memory)” page 18 col. 7 lines 16-17).
With respect to claim 9, Mandabhushi and Lefebvre teach the system of claim 8 and all other claim limitations in consideration of substantially similar claim 2, due to claim 2 being directed towards the method conducted by the system.
With respect to claim 10, Mandabhushi and Lefebvre teach the system of claim 8, and all other claim limitations in consideration of substantially similar claim 3, due to claim 3 being directed towards the method conducted by the system.
With respect to claim 11, Mandabhushi and Lefebvre teach the system of claim 8, and all other claim limitations in consideration of substantially similar claim 4, due to claim 4 being directed towards the method conducted by the system.
With respect to claim 12, Mandabhushi and Lefebvre teach the system of claim 8, and all other claim limitations in consideration of substantially similar claim 5, due to claim 5 being directed towards the method conducted by the system.
With respect to claim 15, Mandabhushi and Lefebvre teach all claim limitations in consideration of substantially similar claim 1, due to claim 1 being directed towards a method analogous to the instructions provided within. Additionally, Mandabhushi teaches a non-transitory computer-readable medium storing instructions (“The set of modules may have a computational cost (e.g., time, processor cycles, memory)” page 18 col. 7 lines 16-17) that, when executed by processor, cause the processor to perform a method for processing an electronic image corresponding to a specimen (“The set of modules may have a computational cost (e.g., time, processor cycles, memory)” page 18 col. 7 lines 16-17),
With respect to claim 16, Mandabhushi and Lefebvre teach the non-transitory computer-readable medium of claim 15, and all additional limitations in consideration of substantially similar claim 2, due to claim 2 being directed towards the method conducted by instructions stored within the medium.
With respect to claim 17, Mandabhushi and Lefebvre teach the non-transitory computer-readable medium of claim 15, and all additional limitations in consideration of both claims 3 and 4, due both being substantially similar to the respective alternative limitations of ordering a new stain or ordering a recut present within.
With respect to claim 18, Mandabhushi and Lefebvre teach the non-transitory computer-readable medium of claim 15 and all additional limitations in consideration of claim 5, due to the claim 5 being directed towards the method conducted by instructions stored within the medium
Claims 6-7, 13-14, and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Mandabhushi and Lefebvre as applied to claim 1 above, and further in view of Zhang (US 10302645 B2).
With respect to claim 6, Mandabhushi and Lefebvre teach the method of claim 1, but do not explicitly teach additional limitations. Zhang further teaches wherein the feature correlating with a need for additional testing comprises a feature predictive of a cancer (“The above methods can be used to stratify patients into those who need repeat biopsy or intensive follow-up and those who do not. The above methods also can be used to distinguish prostate cancer from a benign condition, such as benign prostatic hyperplasia (BPH). Such methods can be used in conjunction with other methods, such as histological tissue evaluation, prostate-specific antigen (PSA) detection, nomogram (e.g., Katan nomogram), methylation, and mutation. In this regard, the methods also can be used to confirm diagnosis after radical prostatectomy and to distinguish prostate cancer from a pre-cancerous lesion (e.g., atypical small acinar proliferation in the prostate (ASAP), low-grade prostate intra-epithelial neoplasia (PIN), and high-grade PIN) in the prostate and a pre-cancerous lesion in the prostate from a benign condition, such as BPH.” Page 18 col 19 lines 63-67 and col 20 lines 1-10).
Zhang is analogous art in the same field of endeavor as the claimed invention. Zhang is directed towards cancer diagnosis using tissue slides and a microscope (“A method of prostate FFPE slide IF-FISH procedure is provided. For the assay of simultaneous FISH and Immunofluorescence (IF) on the same FFPE prostate solid tumor tissue slides, a specimen pre-treatment/antigen retrieval protocol was developed and optimized for best results on the FFPE tissue for IF-FISH. “ page 13 col. 10 lines 43-48). A person of ordinary skill in the art before the effective filing date of the claimed invention would have found it obvious to combined Mandabhushi and Lefebvre with Zhang by utilizing the combined system’s slide quality assessment scheme in accordance with Zhang’s teachings of automated slide processing advantages (“While deparaffinization, pretreatment, staining, and routine slide washing also can be conducted in accordance with methods known in the art, use of an automated system, however, such as the VP 2000 Process (Abbott Molecular, Inc., Des Plaines, Ill.), decreases the amount of time needed to prepare slides for evaluation.” Page 17 col. 17 lines 22-27) with the expectation that doing so would lead to faster slide preparation (“While deparaffinization, pretreatment, staining, and routine slide washing also can be conducted in accordance with methods known in the art, use of an automated system, however, such as the VP 2000 Process (Abbott Molecular, Inc., Des Plaines, Ill.), decreases the amount of time needed to prepare slides for evaluation.” Page 17 col. 17 lines 22-27).
With respect to claim 7, Mandabhushi, Lefebvre, and Zhang teach the method of claim 6. Zhang further teaches wherein the feature predictive of a cancer is an atypical small acinar proliferation (ASAP) (“The above methods can be used to stratify patients into those who need repeat biopsy or intensive follow-up and those who do not. The above methods also can be used to distinguish prostate cancer from a benign condition, such as benign prostatic hyperplasia (BPH). Such methods can be used in conjunction with other methods, such as histological tissue evaluation, prostate-specific antigen (PSA) detection, nomogram (e.g., Katan nomogram), methylation, and mutation. In this regard, the methods also can be used to confirm diagnosis after radical prostatectomy and to distinguish prostate cancer from a pre-cancerous lesion (e.g., atypical small acinar proliferation in the prostate (ASAP), low-grade prostate intra-epithelial neoplasia (PIN), and high-grade PIN) in the prostate and a pre-cancerous lesion in the prostate from a benign condition, such as BPH.” Page 18 col 19 lines 63-67 and col 20 lines 1-10).
With respect to claim 13, Mandabhushi and Lefebvre teach the system of claim 8, and in view of Zhang teach all additional claim limitations in consideration of substantially similar claim 6, due to claim 6 being directed towards the method conducted by the system.
With respect to claim 14, Mandabhushi, Lefebvre, and Zhang teach the system of claim 13 and all additional limitations in consideration of substantially similar claim 7, due to claim 7 being directed towards the method conducted by the system.
With respect to claim 19, Mandabhushi and Lefebvre teach the non-transitory computer-readable medium of claim 15, and in view of Zhang teach all additional limitations in consideration of substantially similar claim 6, due to claim 6 being directed toward the method conducted by the instructions stored in the medium.
With respect to claim 20, Mandabhushi, Lefebvre, and Zhang teach the non-transitory computer-readable medium of claim 19, and all additional limitations in consideration of substantially similar claim 7, due to claim 7 being directed towards the method conducted by the instructions stored in the medium.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Sorenksen (US 8571286 B2) - discloses an automated slide quality assessment system
Any inquiry concerning this communication or earlier communications from the examiner should be directed to REBECCA C WILLIAMS whose telephone number is (571)272-7074. The examiner can normally be reached M-F 7:30am - 4:00pm.
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, Andrew W Bee can be reached at (571)270-5183. 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.
/REBECCA COLETTE WILLIAMS/Examiner, Art Unit 2677
/ANDREW W BEE/Supervisory Patent Examiner, Art Unit 2677
Prosecution Insights