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 information disclosure statement(s) (IDS) submitted has/have been considered by the examiner and placed in the application file.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim(s) 3 and 6 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention.
Claim(s) 3 and 6 recite “the initial values of the first region of interest and the second region of interest in the first weighting information and the second weighting information.” It lacks proper antecedent basis because claim 5 sets initial values of the first weighting information and the second weighting information, not initial values of the regions of interest. There is insufficient antecedent basis for this limitation, and it is unclear whether these are the same initial values recited in claim 5 or a further set.
Claim 6 further recites “to be relatively higher than those of the other regions.” There is insufficient antecedent basis for “the other regions.”
Appropriate correction is required.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 2, 4, 5, 7, 9 and 10 is/are rejected under 35 U.S.C. 103 as being unpatentable Sashida et al., US 2021/0012491 A1, (hereinafter “KONICA”) in view of Fu et al., “Look Closer to See Better,” (hereinafter “RA-CNN”) and Teramoto et al., “Automated classification of benign and malignant cells from lung cytological images using attention‑based multiple instance learning,” (hereinafter “TERAMOTO”).
Claim 1.
KONICA discloses a classification apparatus, comprising at least one processor, the at least one
processor (KONICA ¶ 61: “The controller 21 includes a central processing unit (CPU).”) carrying out:
an acquisition means for process of acquiring a pathological image which includes
a specimen cell as a subject (KONICA ¶ 58: “The image processing apparatus 2A analyzes the
microscope image sent from the microscope-image obtaining apparatus 1A, performs cell discrimination for the cell image.”); and
a classification process of,
generating a first (KONICA ¶ 104: “the controller 21 as the image processor generates multiple processed images on the basis of the cell image.” )
generating a second (KONICA ¶ 90: “A tissue section includes various regions, such as a tumor region, an interstitial region, and a vitreous region. These regions have different stainabilities with the same staining reagent.”; KONICA ¶ 113: “the image processing is performed on the respective regions to obtain multiple processed images.” This teaches that a separate processed image is produced for each differing region.),
PNG
media_image1.png
651
423
media_image1.png
Greyscale
PNG
media_image2.png
583
441
media_image2.png
Greyscale
generating a feature quantity of the first weighted input image using a first feature analysis model that has been trained to generate the feature quantity of the first weighted input image upon receipt of input of the first weighted input image; generating a feature quantity of the second weighted input image using a second feature analysis model that has been trained to generate the feature quantity of the second weighted input image upon receipt of input of the second weighted input image (KONICA ¶ 105: “the controller 21 as the feature quantity extractor extracts feature quantities from the multiple processed images.” This teaches extraction of a feature quantity from each processed image separately. RA-CNN § 3.3: “the feature descriptor at a specific scale generated from the fully-connected layers in classification net.” This teaches a separate trained feature analysis model per branch, each producing its own feature descriptor.),
PNG
media_image3.png
418
882
media_image3.png
Greyscale
and
classifying the specimen cell as a input of the feature quantity of the first weighted input image and the feature quantity of the second weighted input image (RA-CNN § 3.3: ”we first normalize each descriptor independently, and concatenate them together into a fully-connected fusion layer with softmax function for the final classification.” This teaches a single classification model receiving the separately extracted feature quantities of both branches.).
KONICA does not teach "weighting information," a "weighted input image," or a generative model trained to generate weighting information "for emphasizing" a region of interest. KONICA processes the cell image using user-entered auxiliary information (KONICA ¶ 103: "a user inputs auxiliary information with the operation unit 22 as an auxiliary
information inputter." This teaches that KONICA obtains the region-specific information
by manual entry rather than from a trained model.). However, RA-CNN teaches a trained
network that generates a mask which is applied to the image itself (RA-CNN Sec. 3.1, Eq. (4):
“the cropping operation can be implemented by an element-wise multiplication between
the original image at coarser scales and an attention mask.” This teaches generating a
weighted input image by processing the image with the generated weighting information. RA-CNN Sec. 3.4: "we fix parameters in convolutional/classification layers, and switch to
ranking loss to optimize the two APNs." This teaches two separate trained attention
proposal networks, corresponding to the recited first and second generative model.).
KONICA and RA-CNN do not specifically teach classification of a specimen cell as "a benign cell or a malignant cell." However, TERAMOTO teaches benign versus malignant classification of stained cytology images (TERAMOTO p. 2: “1252 microscopic images of benign cells and 1805 of malignant cells were acquired.”; TERAMOTO p. 2: “stained using the Papanicolaou method.” Papanicolaou stained cytology specimens.).
One of ordinary skill in the art would have found it obvious to apply the cell image
discrimination of KONICA and separate trained feature analysis model per branch of RA-CNN to classifying a specimen cell as benign or malignant in cytological images as taught by TERAMOTO. Replacing the manual auxiliary information inputter of KONICA with an automatically learned attention proposal network as taught by RA-CNN is suggested since KONICA teaches that “a user inputs auxiliary information with the operation unit 22 as an auxiliary information inputter” (¶ 103), and RA-CNN suggests that “the proposed APN is automatically learned by discovering the most discriminative regions to classification, instead of regressing human-defined bounding box.” The modification would have produced the predictable classification benefits by replacing KONICA's manual auxiliary information inputter with an automatically learned attention proposal network for feature quantities of the cell discrimination; see MPEP 2143(G).
Claims 2 and 5.
KONICA , RA-CNN, and TERAMOTO discloses the classification apparatus according to claim 1, wherein: at least cytoplasm of the specimen cell is stained (TERAMOTO p.2: “stained using the Papanicolaou method.” This teaches a staining method for cytoplasm.); and the first region of interest and the second region of interest are different in staining intensity from each other (KONICA ¶90: “A tissue section includes various regions, such as a tumor region, an interstitial region, and a vitreous region. These regions have different stainabilities with the same staining reagent.”; KONICA ¶115: “an image is processed on the basis of staining conditions to obtain multiple processed images.”).
Claim 4.
KONICA , RA-CNN, and TERAMOTO discloses the training apparatus counterpart of claim 1 and is rejected for the reasons given for claim 1. Regarding acquiring classification information which indicates whether the specimen cell is a benign cell or a malignant cell, TERAMOTO teaches labelled training data (TERAMOTO p. 2: “1252 microscopic images of benign cells and 1805 of malignant cells.”).
Regarding the claim limitations of updating parameters of the recited models based on comparison between a classification result and the classification information, RA-CNN teaches this (RA-CNN Sec. 3.4: “we keep APN parameters unchanged, and optimize the softmax losses at three scales to converge. Then we fix parameters in convolutional/classification layers, and switch to ranking loss to optimize the two APNs.” This teaches alternating updates in which both the attention networks and the classification networks have their parameters updated.).
Claim 7.
The combination of KONICA, RA-CNN, and TERAMOTO renders claim(s) 7 obvious for at least the reasons discussed above for claim 1, mutatis mutandis.
Claims 9 and 10.
The combination of KONICA , RA-CNN, and TERAMOTO renders claim(s) 9 and 10 obvious for at least the reasons discussed above for claims 1 and 4, respectively. Claims 9 and 10 additionally recite a non-transitory storage medium storing a program for causing a computer to function … (KONICA Claim 10).
Allowable Subject Matter
Claims 3 and 6 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims, and, regarding claim 6, if the rejection under 35 U.S.C. 112(b) set forth above is overcome.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Ross Varndell whose telephone number is (571)270-1922. The examiner can normally be reached M-F, 9-5 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, O’Neal Mistry can be reached at (313)446-4912. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Ross Varndell/Primary Examiner, Art Unit 2674
Prosecution Insights