DETAILED ACTION
Status of Claims
This action is in reply to the application filed on 1 August, 2024.
Claims 1 – 17 are currently pending and have been examined.
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 .
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
The following rejection is formatted in accordance with MPEP 2106.
Claim 16 is representative. Claim 16 recites:
An information processing method comprising:
causing a first processor to perform training of a learning model that receives biological information and outputs diagnosis information by using a combination of biological information including at least a medical image and diagnosis information related to the biological information; and
causing a second processor to acquire the learning model that is trained by the first processor, and
generate new diagnosis information related to new biological information, which is different from the biological information used for training of the learning model that is trained, by inputting the new biological information to the learning model that is trained.
Claim 17 recites medium with instructions executed by a processor, and Claim 1 recites a system that executes the steps of the method recited in Claim 16.
Claims 1 - 17 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e. a law of nature, a natural phenomenon, or an abstract idea), and does not include additional elements that either: 1) integrate the abstract idea into a practical application, or 2) that provide an inventive concept – i.e. element that amount to significantly more than the abstract idea. The Claims are directed to an abstract idea because, when considered as a whole, the plain focus of the claims is on an abstract idea.
STEP 1
The claims are directed to a system, a method and non-transitory computer readable medium which are included in the statutory categories of invention.
STEP 2A PRONG ONE
The claims, as illustrated by Claim 16, recite limitations that encompass an abstract idea including:
generate new diagnosis information related to new biological information, which is different from the biological information used for training of the learning model that is trained.
The claims, as illustrated by Claim 16, recite limitations that encompass an abstract idea within the “mental processes” grouping – concepts performed in the human mind including observation, evaluation, judgment and opinion. The claims recite training a model to output diagnosis information using a combination of biological information, acquiring the trained model, and applying the trained model to new biological information to generate new diagnosis information. The specification discloses that “image diagnosis using medical images” is known in the art. Making a diagnosis from medical images is age old, involving visually observing features in the image and judging whether the observed feature correlate with a diagnosis. Additionally, the specification discloses that it is known to analyze images using computer aided detection techniques. Analyzing images to generate a diagnosis, using well-known techniques as disclosed in the specification, is a process that, except for generic computer implementation steps, can be performed in the human mind.
Collecting information, including when limited to particular content, is within the realm of abstract ideas, and analyzing information by steps people go through in their minds, or by mathematical algorithms, without more, are mental processes within the abstract idea category (Electric Power Group v. Alstom S.A. (Fed Cir, 2015-1778, 8/1/2016).
As such, the claims recite an abstract idea within the mental process grouping.
The claims, as illustrated by Claim 1, recite limitations that encompass an abstract idea within the “certain methods of organizing human activity” grouping –
managing personal behavior or relationships or interactions between people including social activities, teaching, and following rules or instructions.
The claims recite generating a diagnosis based on biological information by training and applying a generic learning model. This process is typical in medicine, where a doctor orders medical images which are “read” by a human or by an algorithm to determine if any diagnosis is indicated, and is process that merely organizes this human activity. (See MPEP 2016.04 (a)(2) II C finding that “a mental process that a neurologist should follow when testing a patient for nervous system malfunctions” is a method of organizing human activity, In re Meyer, 688 F.2d 789, 791-93, 215 USPQ 193, 194-96 (CCPA 1982). As such, the claims recite an abstract idea within the certain methods of organizing human activity grouping.
STEP 2A PRONG TWO
The claims recite limitations that include additional elements beyond those that encompass the abstract idea above including:
causing a first processor to perform training of a learning model that receives biological information and outputs diagnosis information by using a combination of biological information including at least a medical image and diagnosis information related to the biological information; and
causing a second processor to acquire the learning model that is trained by the first processor, and generate new diagnosis information by inputting the new biological information to the learning model that is trained.
However, these additional elements do not integrate the abstract idea into a practical application of that idea in accordance with the MPEP. (see MPEP 2106.05)
The processor and learning model are recited at a high level of generality such that it amounts to no more than instructions to apply the abstract idea using a generic computer components. These elements merely add instructions to implement the abstract idea on a computer, and generally link the abstract idea to a particular technological environment.
In particular, the claims replace the knowledge and experience of a radiologist by applying established methods of machine learning to an abstract diagnostic process in a new data environment – i.e. applying a trained model to the biological information. The specification teaches that the learning model may be trained in a training phase to output diagnosis information using the biological information; using any suitable model and correctly labelled biological information acquired in the clinical server (@ 0056, 0061). Machine learning limitations reciting broad, functionally described, well-known techniques executed by generic and conventional computing devices does not provide a practical application of the abstract diagnostic process. “Today we hold only that patents that do no more than claim the application of generic machine learning to new data environments, without disclosing improvements to the machine learning models to be applied, are patent ineligible under §101.” (Recentive Analytics, Inc. v. Fox Corp. (Fed. Cir. 2025)).
Nothing in the claim recites specific limitations directed to an improved computer system, processor, memory, network, database or Internet. Similarly, the specification is silent with respect to these kinds of improvements. A general purpose computer that applies a judicial exception by use of conventional computer functions, as is the case here, does not qualify as a particular machine, nor does the recitation of a generic computer impose meaningful limits in the claimed process. (see Ultramercial, Inc. v. Hulu, LLC, 772 F.3d 709, 716-17 (Fed. Cir. 2014)). As such, the additional elements recited in the claim do not integrate the abstract diagnostic process into a practical application of that process.
STEP 2B
The additional elements identified above do not amount to significantly more than the abstract diagnostic process. Training and applying machine learning models are conventional techniques, even when applied in a new data environment; facts for which Examiner takes Official Notice. Acquiring information, such as a trained model, for example over a network, is a well-understood, routine and conventional computer function – i.e. receiving or transmitting data over a network as in Symantec, TLI, OIP and buySAFE.
The additional structural elements or combination of elements in the claims, other than the abstract idea per se, amount to no more than a recitation of generic computer structure (i.e. a first & second processor, computer-readable medium). Each of the above components are disclosed in the specification as being purely conventional and/or known in the industry. Because the specification describes these additional elements in general terms, without describing particulars, Examiner concludes that the claim limitations may be broadly, but reasonably construed, as reciting well-understood, routine and conventional computer components and techniques. The specification describes the elements in a manner that indicates that they are sufficiently well-known that the specification does not need to describe the particulars in order to satisfy U.S.C. 112. Considered as an ordered combination the limitations recited in the claims add nothing that is not already present when the steps are considered individually. As such, the additional elements recited in the claim do not provide significantly more than the abstract diagnostic process, or an inventive concept.
Claim 1 includes dependent claims 2 – 15 that further add additional features including:
those that merely serve to further narrow the abstract idea above such as:
attach accessory information to biological information (Claim 6);
further limiting the type of accessory information (Claim 13);
further limiting the type of diagnosis (Claim 15);
those that recite additional abstract ideas such as:
anonymizing records (Claim 7, 8, 9);
estimate similarity between accessory information (Claim 10);
training using pre-diagnosis information (Claim 14);
those that recite well-understood, routine and conventional activity or computer functions such as:
an input unit, storage unit, acquire information form the storage unit, display information on a display, receive input via the input unit (Claim 2, 4, 5, 8, 9, 12);
retrain the model based on new information (Claim 3, 5, 9);
those that recite insignificant extra-solution activities such as:
present results (Claim 11);
determine whether to retrain based on similarity (Claim 12);
or those that are an ancillary part of the abstract idea.
The limitations recited in the dependent claims, in combination with those recited in the independent claims add nothing that integrates the abstract idea into a practical application, or that amounts to significantly more. These elements merely narrow the abstract idea, recite additional abstract ideas, or append conventional activity to the abstract process. As such, the additional element do not integrate the abstract idea into a practical application, or provide an inventive concept that transforms the claims into a patent eligible invention.
The apparatus claims are no different from the method claims in substance. “The equivalence of the method, system and media claims is readily apparent.” “The only difference between the claims is the form in which they were drafted.” (Bancorp). The method claims recite the abstract idea implemented on a generic computer, while the apparatus claims recite generic computer components configured to implement the same idea. Specifically, Claims 1 – 15 and 17 merely add the generic hardware noted above that nearly every computer will include. The apparatus claim’s requirement that the same method be performed with a programmed computer does not alter the method’s patentability under U.S.C. 101 (In re Grams). Therefore, the claims are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
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.
Claims 1, 16 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Yoo: (US PGPUB 2020/0357098 A1) in view of Shibata: (US PGPUB 2020/0310934 A1).
CLAIMS 1, 16 and 17
Yoo discloses a remote medical diagnosis system that includes the following limitations:
causing a processor to perform training of a learning model that receives biological information and outputs diagnosis information by using a combination of biological information including at least a medical image and diagnosis information related to the biological information; and causing a processor to acquire the learning model that is trained by the processor, and generate new diagnosis information related to new biological information, which is different from the biological information used for training of the learning model that is trained, by inputting the new biological information to the learning model that is trained; (Yoo 0004, 0017, 0029 – 0031, 0064, 0126, 0148, 0154, 0158).
Yoo discloses a medical diagnosis system that includes analyzing images using an artificial intelligence neural network, trained in advance on a large amount of high quality medical images by deep learning. A user terminal receives the trained neural network that was trained in advance and applies new patient data to the model to generate a diagnosis output.
Yoo discloses a server and a user terminal in communication over a network, where the user terminal receives and executes the learning model, which has been “trained in advance” (@ 0005). However, Yoo does not expressly teach that a first processor trains the model, and a second processor acquires and executes the model. Shibata (@ Abstract, 0006, 0034, 0071, 0076, 0077); discloses a system and method for managing diagnostic models that includes a server (i.e. a first processing apparatus) operable to train the machine learning model using learning data, and an information processing apparatus (i.e. a second processing apparatus) configured to obtain the model form the server and execute the model locally. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing data of the claimed invention, to have modified the machine learning diagnostic system of Yoo so as to have included training and executing the model in different processors, in accordance with the teaching of Shibata, in order to allow for effective learning model management.
With respect to Claims 1 and 17, Yoo also discloses the following limitations:
A non-transitory computer-readable storage medium storing an information processing program; (Yoo 0163);
An information processing system comprising: a first information processing apparatus including at least one first processor; and a second information processing apparatus including at least one second processor; (Yoo 0145 – 0148).
Claims 2 – 5 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Yoo: (US PGPUB 2020/0357098 A1) in view of Shibata: (US PGPUB 2020/0310934 A1) in view of Zhang et al.: (US PGPUB 2019/0096060 A1).
CLAIM 2
The combination of Yoo/Shibata discloses the limitations above relative to Claim 1. With respect to the following limitations:
the first information processing apparatus further includes an input unit; (Zhang 0049, 0068, 0073, 0094 – 0096, Figure 5 # 506); and
the first processor is configured to: acquire the biological information stored in the storage unit from the second information processing apparatus; (Zhang 0006, 0017, 0040, 0047);
display the biological information on a display; (Zhang 0012, 0024, 0041, 0042); and
receive, via the input unit, an input for diagnosis information related to the displayed biological information; (Zhang 0006, 0012, 0024, 0049, 0062, 0068, 0071);
the second information processing apparatus further includes a storage unit that stores the biological information; (Zhang 0047, 0059).
Yoo discloses an artificial neural network that is trained using accumulated training data, but does not expressly disclose the recited training data generation steps – i.e. acquire and display images, and enter a diagnosis. Zhang discloses a system and method for annotating medical images in order to train an image classification model (@ 0009), that includes acquiring a medical image to be annotated from storage, outputting the image to a user terminal (i.e. displaying), and receiving a diagnosis classification entered by a user via a terminal device input, and storing the result. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing data of the claimed invention, to have modified the machine learning diagnostic system of Yoo/Shibata so as to have included a manual process for generating medical image classification training data, in accordance with the teaching of Zhang, in order to improve the accuracy of the classifier.
CLAIMS 3 - 5
The combination of Yoo/Shibata discloses the limitations above relative to Claim 1. With respect to the following limitations:
wherein the first processor is configured to: acquire a combination of the new biological information and the new diagnosis information; and perform retraining of the learning model by using the combination of the new biological information and the new diagnosis information; (Zhang 0014, 0015, 0026, 0063, 0074, 0091);
wherein: the second information processing apparatus further includes an input unit, and the second processor is configured to: display the generated new diagnosis information on a display; and receive, via the input unit, a correction for the new diagnosis information; (Zhang 0012; 0024, 0068, 0071 – 0073);
acquire a combination of the new biological information and the new diagnosis information; and perform, in a case where the new diagnosis information is corrected, retraining of the learning model by using a combination of the new biological information and the corrected new diagnosis information; (Zhang 0014, 0015, 0068).
Yoo discloses an artificial neural network that is trained using accumulated training data, but does not expressly disclose the recited retraining steps using new or corrected information. Zhang discloses a system and method for annotating medical images that includes retraining the model using newly generated information, including receiving corrected information from a user and retraining using the corrected information. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing data of the claimed invention, to have modified the machine learning diagnostic system of Yoo/Shibata so as to have included retraining the classifier using new or corrected information, in accordance with the teaching of Zhang, in order to improve the accuracy of the classifier.
CLAIM 15
The combination of Yoo/Shibata discloses the limitations above relative to Claim 1. With respect to the following limitations:
wherein the diagnosis information includes at least one of information indicating a position and a size of a region-of-interest included in the medical image or information indicating an opinion of the region-of-interest; (Zhang 0006, 0017, 0051, 0065).
Yoo discloses an artificial neural network that is trained using accumulated training data, but does not expressly disclose the recited position and size of a region of interest. Zhang discloses a system and method for annotating medical images that includes framing a lesion based on detected position and size. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing data of the claimed invention, to have modified the machine learning diagnostic system of Yoo/Shibata so as to have included training the classifier using the position and size of an region of interest, in accordance with the teaching of Zhang, in order to improve the accuracy of the classifier.
Claims 6, 13 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Yoo: (US PGPUB 2020/0357098 A1) in view of Shibata: (US PGPUB 2020/0310934 A1) in view of Bregman-Amitai et al.: (US PGPUB 2019/0239843 A1).
CLAIMS 6 and 13
The combination of Yoo/Shibata discloses the limitations above relative to Claim 1. With respect to the following limitations:
wherein accessory information is attached to the biological information, the accessory information indicating information related to at least one of a subject from which the biological information is acquired or an imaging apparatus used for acquisition of the biological information; (Bregman-Amitai 0005, 0006, 0015 – 0017, 0036, 0037, 0050, 0054, 0082, 0102, 0129);
wherein the accessory information includes information indicating at least one of a name, a gender, an age, a medical history, and an identification number of the subject, or an imaging condition used for acquiring the biological information; (Bregman-Amitai 0005, 0006, 0036, 0037, 0102, 0129, 0144, 0147).
Yoo discloses an artificial neural network that is trained using accumulated training data, but does not expressly disclose information related to the subject. Bregman-Amitai discloses a system and method for classifying medical images using a trained model (@ 0036), where the training parameters used to train the model include patient related information such as demographics (i.e. age, gender, age, etc.). Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing data of the claimed invention, to have modified the machine learning diagnostic system of Yoo/Shibata so as to have included training the classifier using demographic information, in accordance with the teaching of Bregman-Amitai, in order to improve the accuracy of the classifier.
CLAIM 14
The combination of Yoo/Shibata discloses the limitations above relative to Claim 1. With respect to the following limitations:
the biological information includes pre-diagnosis information indicating information obtained by performing diagnosis in advance in relation to the medical image included in the biological information, and the first processor is configured to perform training of the learning model that receives the biological information and outputs the diagnosis information by using a combination of the medical image included in the biological information, the pre-diagnosis information, and the diagnosis information related to the biological information; (Bregman-Amitai 0003, 0056, 0139, 0266).
Yoo discloses an artificial neural network that is trained using accumulated training data, but does not expressly disclose pre-diagnosis information. Bregman-Amitai discloses a system and method for classifying medical images using a trained model (@ 0036), where the training parameters used to train the model include patient related information obtained from a medical record. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing data of the claimed invention, to have modified the machine learning diagnostic system of Yoo/Shibata so as to have included training the classifier using information in the medical record, in accordance with the teaching of Bregman-Amitai, in order to improve the accuracy of the classifier.
Claims 7 and 8 are rejected under 35 U.S.C. 103 as being unpatentable over Yoo: (US PGPUB 2020/0357098 A1) in view of Shibata: (US PGPUB 2020/0310934 A1) in view of Bregman-Amitai et al.: (US PGPUB 2019/0239843 A1) in view of Zlotnick et al.: (US PGPUB 2019/0171914 A1).
CLAIM 7
The combination of Yoo/Shibata/Bregman-Amitai discloses the limitations above relative to Claim 6. With respect to the following limitations:
a third information processing apparatus including at least one third processor, wherein the third processor is configured to anonymize at least a part of the accessory information attached to the biological information; (Zlotnick 0003, 0048, 0053, 0054, 0062, 0063, 0071, 0074).
Yoo/Shibata/Bregman-Amitai discloses an artificial neural network that is trained using accumulated training data including accessory information; but does not disclose anonymizing. Zlotnick discloses a system and method for classifying medical images by a reviewer for training a machine learning model. Data that can personally identify the respective patient is anonymized. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing data of the claimed invention, to have modified the machine learning diagnostic system of Yoo/Shibata/Bregman-Amitai so as to have included anonymizing information associated with the medical image, in accordance with the teaching of Zlotnick, in order to protect patient information.
CLAIM 8
The combination of Yoo/Shibata/Bregman-Amitai/Zlotnick discloses the limitations above relative to Claim 7. With respect to the following limitations:
the second information processing apparatus further includes a storage unit that stores the biological information and the accessory information; (Bregman-Amitai 0006, 0015 – 0017, 0036, 0037, 0061, 0080, 0083, 0101, 0103, 0275).
Yoo discloses an artificial neural network that is trained using accumulated training data, but does not expressly disclose information related to the subject. Bregman-Amitai discloses a system and method for classifying medical images using a trained model (@ 0036), where the training parameters used to train the model include patient related information such as demographics (i.e. age, gender, age, etc.). Further; Zlotnick discloses the following limitations:
the third processor is configured to: acquire the accessory information from the second information processing apparatus; and anonymize at least a part of the accessory information, the second processor is configured to: acquire the accessory information after anonymization from the third information processing apparatus; and store, in the storage unit, the biological information, the accessory information before anonymization, and the accessory information after anonymization in association with each other, and the first processor is configured to acquire the biological information to which the accessory information after anonymization is attached; (Zlotnick 0003, 0053, 0062, 0063, 0071, 0074).
Zlotnick discloses a system and method for classifying medical images by a reviewer for training a machine learning model. Data that can personally identify the respective patient is anonymized by a separate processor. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing data of the claimed invention, to have modified the machine learning diagnostic system of Yoo/Shibata/Bregman-Amitai so as to have included anonymizing information associated with the medical image, in accordance with the teaching of Zlotnick, in order to protect patient information.
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Yoo: (US PGPUB 2020/0357098 A1) in view of Shibata: (US PGPUB 2020/0310934 A1) in view of Bregman-Amitai et al.: (US PGPUB 2019/0239843 A1) in view of Zlotnick et al.: (US PGPUB 2019/0171914 A1) in view of Zhang et al.: (US PGPUB 2019/0096060 A1).
CLAIM 9
The combination of Yoo/Shibata/Bregman-Amitai/Zlotnick discloses the limitations above relative to Claim 7. With respect to the following limitations:
Bregman-Amitai teaches:
the third processor is configured to: acquire accessory information attached to the new biological information from the second information processing apparatus; (Bregman-Amitai 0005, 0006, 0015 – 0017, 0036, 0037, 0060, 0101, 0117, 0132);
and Zlotnick teaches
anonymize at least a part of the accessory information; the first processor is configured to: acquire the new biological information to which the accessory information after anonymization is attached; (Zlotnick 0003, 0053, 0062, 0063, 0071, 0074).
The combination of Yoo/Shibata/Bregman-Amitai/Zlotnick, as shown above, discloses a system and method for classifying medical images by a reviewer; and used for training a machine learning model; where the medical images include accessory information (i.e. that can personally identify the respective patient), including for new medical images; and where the accessory information is anonymized by a separate processor. The combination of Yoo/Shibata/Bregman-Amitai/Zlotnick does not disclose the following limitations; however, Zhang does:
perform retraining of the learning model by using a combination of the new biological information and the new diagnosis information; (Zhang 0014, 0015, 0068).
Zhang discloses a system and method for annotating medical images that includes retraining the model using newly generated information, including receiving corrected information from a user and retraining using the corrected information. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing data of the claimed invention, to have modified the machine learning diagnostic system of Yoo/Shibata/Bregman-Amitai/Zlotnick so as to have included retraining the classifier using new or corrected information, in accordance with the teaching of Zhang, in order to improve the accuracy of the classifier.
Claims 10 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Yoo: (US PGPUB 2020/0357098 A1) in view of Shibata: (US PGPUB 2020/0310934 A1) in view of Bregman-Amitai et al.: (US PGPUB 2019/0239843 A1) in view of Sirotin et al.: (US PGPUB 2021/0279499 A1).
CLAIMS 10 and 11
The combination of Yoo/Shibata/Bregman-Amitai discloses the limitations above relative to Claim 6. With respect to the following limitations:
wherein the second processor is configured to estimate a similarity between the accessory information attached to the biological information used for training of the learning model and the accessory information attached to the new biological information; present the generated new diagnosis information and the estimated similarity; (Sirotin 0173, 0192 – 0201, 0211 – 0213).
Yoo/Shibata/Bregman-Amitai discloses an artificial neural network that is trained using demographic data; but does not calculating a similarity score. Sirotin discloses a system and method to detect features in an image that includes estimating and displaying a similarity score between demographic parameters in a current image and the demographic parameters used to train the models. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing data of the claimed invention, to have modified the machine learning diagnostic system of Yoo/Shibata/Bregman-Amitai so as to have included calculating similarity between features and trained features, in accordance with the teaching of Zlotnick, in order to allow selection of the most appropriate model.
Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over Yoo: (US PGPUB 2020/0357098 A1) in view of Shibata: (US PGPUB 2020/0310934 A1) in view of Bregman-Amitai et al.: (US PGPUB 2019/0239843 A1) in view of Sirotin et al.: (US PGPUB 2021/0279499 A1) in view of Zhang et al.: (US PGPUB 2019/0096060 A1) and in view of de Sousa Moura et al.: (US PGPUB 2019/0267121 A1).
CLAIM 12
The combination of Yoo/Shibata/Bregman-Amitai/Sirotin discloses the limitations above relative to Claim 10. With respect to the following limitations:
acquire a combination of the new biological information, the new diagnosis information, and the similarity; (Sirotin 0173, 0192 – 0201, 0211 – 0213)
Sirotin discloses determining similarity for newly acquired images. Further, Zhang discloses the following limitations:
determine whether or not to perform retraining of the learning model by using the combination of the new biological information and the new diagnosis information; (Zhang 0014, 0015, 0026, 0063, 0068 – 0074, 0091).
Zhang discloses a system and method for annotating medical images that includes retraining the model using newly generated information. In particular, Zhang teaches determining whether a classification applied to a medical image is correct and whether it may be used for retraining. The classification is corrected before the image is used for retraining. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing data of the claimed invention, to have modified the machine learning diagnostic system of Yoo/Shibata/Bregman-Amitai so as to have included acquiring similarity information, in accordance with the teaching of Sirotin, and determining whether to retrain the classifier using new or corrected information, in accordance with the teaching of Zhang, in order to improve the accuracy of the classifier.
Zhang discloses determining whether to use newly acquired information for retraining, but not based on demographic similarity. De Sousa Moura (@ 0003, 0024 – 0029, 0047, 0048), discloses a medical recommendation system that includes retraining machine learning models with new data based on demographic similarity. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing data of the claimed invention, to have modified the machine learning diagnostic system of Yoo/Shibata/Bregman-Amitai/Sirotin/Zhang so as to have included retraining based on demographic similarity, in accordance with the teaching of de Sousa Moura, in order to improve the accuracy of the classifier.
CONCLUSION
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US PGPUB 2009/0080731 A1 to Krishnapuram et al. discloses a system and method for training a classifier to identify a diagnosis for a medical image.
US PGPUB 2019/0102878 A1 to Zhang et al. discloses a system and method for analyzing a medical image using a trained neural network.
US PGPUB 2023/0214994 A1 discloses training an AI system to classify medical images including a difficulty metric associated with demographic data for the medical image
Any inquiry of a general nature or relating to the status of this application or concerning this communication or earlier communications from the Examiner should be directed to John A. Pauls whose telephone number is (571) 270-5557. The Examiner can normally be reached on Mon. - Fri. 8:00 - 5:00 Eastern. If attempts to reach the examiner by telephone are unsuccessful, the Examiner’s supervisor, Robert Morgan can be reached at (571) 272-6773.
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 http://portal.uspto.gov/external/portal/pair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866.217.9197.
Official replies to this Office action may now be submitted electronically by registered users of the EFS-Web system. Information on EFS-Web tools is available on the Internet at: http://www.uspto.gov/patents/process/file/efs/guidance/index.jsp. An EFS-Web Quick-Start Guide is available at: http://www.uspto.gov/ebc/portal/efs/quick-start.pdf.
Alternatively, official replies to this Office action may still be submitted by any one of fax, mail, or hand delivery. Faxed replies should be directed to the central fax at (571) 273-8300. Mailed replies should be addressed to “Commissioner for Patents, PO Box 1450, Alexandria, VA 22313-1450.” Hand delivered replies should be delivered to the “Customer Service Window, Randolph Building, 401 Dulany Street, Alexandria, VA 22314.”
/JOHN A PAULS/Primary Examiner, Art Unit 3683
Date: 22 September, 2025