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 (IDS) submitted on March 26, 2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement has been considered by the examiner.
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.
Claim 7 is rejected under 35 USC 101 as being directed to non-statutory subject matter. Claim 7 is directed to a computer program per se. See MPEP 2106 and 2106.03 for guidance. The claim does not fall within at least one of the four categories of patent eligible subject matter of a process, machine, manufacture, or composition of matter. “A computer program” as recited is not patent eligible subject matter because it is “software/data per se”. A recommended remedy for claiming a computer program is to have it embodied within a “non-transitory” computer readable medium. See also USPTO Published 2019 Patent Eligibility Guidance. per se which does not fall under the four statutory categories of invention.
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, 7, 8 and 9 are rejected under 35 U.S.C 103 as being unpatentable over Radhia et. al. “Machine learning for evolutive lymphoma and residual masses recognition in whole body diffusion weighted magnetic resonance images” (hereinafter Radhia) in view of Madabhushi US Patent Application Publication No. US-20180276498-A1 (hereinafter Madabhushi).
Regarding claim 1, Radhia discloses a computer-implemented method (Radhia in [Section – 2.3, Paragraph – 2] discloses, “we describe the series of post-processing procedures to build a computer-aided diagnosis (CAD) system based on machine learning techniques”), comprising: obtaining an apparent diffusion coefficient (ADC) map for a region of interest of a patient (Radhia in [Section – 2.3.2, Paragraph – 3] discloses about region of interest, “The binary mask obtained through the segmentation step is used to identify the region of interest (ROI) on the parametric constructed image ADC map”), the ADC map being determined based on a diffusion-weighted magnetic resonance imaging (MRI) measurement; obtaining an MRI image determined based on the diffusion-weighted MRI measurement or another MRI measurement (Radhia in [Section – 2.1, Paragraph – 1] discloses, “The database consists on a total of 1005 images distributed as follows: 335 images with b value = 0 s / mm 2 , 335 images for diffusion weighted image with b value = 600 s / mm 2 , and 335 images for conventional anatomic T2-weighted sequence”).
Radhia doesn’t disclose about the following limitation as further recited in the claim.
Madabhushi discloses about generating a prediction of a metastatic characterization using a deep convolutional neural network (Madabhushi in [0136] discloses, “The operations may also include classifying the region of tissue as likely to experience BCR or unlikely to experience BCR based, at least in part, on the joint probability ... the operations include generating a classification of the region of tissue as likely to experience cancer progression or unlikely to experience cancer recurrence based, at least in part, on the joint probability”. Madabhushi in [0019] discloses about BCR being associated with metastatic, “BCR is often associated with the presence of more aggressive metastatic prostate cancer and hence a worse prognosis”), one or more layers of the deep convolutional neural network obtaining, as a respective input, respective spatial context information determined based on the ADC map (Madabhushi in [0063] discloses, “The subset of Haralick features may be computed from spatial intensity co-occurrence matrices based on the second pre-treatment image, and quantifies intensity-based tumor heterogeneity. The subset of Gabor features quantifies signal response at multiple orientation and angles. The subset of CoLlAGe features quantifies gradient based tumor heterogeneity. CoLlAGe involves assigning an image voxel an entropy value associated with the co-occurrence matrix of gradient orientations computed around a voxel”. Furthermore, Madabhushi in [0064] discloses about CNN, “The radiomics machine learning component is configured as a random forest (RF) classifier having a depth of two and 1000 trees ... a convolutional neural network (CNN), or other type of machine learning or deep learning classifier”).
It would have been obvious to one of ordinary skill in art before the effective filling date of the claimed invention to integrate the technique of Madabhushi into the system of Radhia because it would allow the system to produce more accurate and reliable automated metastatic characterization prediction.
Summary of Citations (Madabhushi)
Paragraph [0019]; “BCR is often associated with the presence of more aggressive metastatic prostate cancer and hence a worse prognosis”.
Paragraph [0063]; “The subset of Haralick features may be computed from spatial intensity co-occurrence matrices based on the second pre-treatment image, and quantifies intensity-based tumor heterogeneity. The subset of Gabor features quantifies signal response at multiple orientation and angles. The subset of CoLlAGe features quantifies gradient based tumor heterogeneity. CoLlAGe involves assigning an image voxel an entropy value associated with the co-occurrence matrix of gradient orientations computed around a voxel”.
Paragraph [0064]; “The radiomics machine learning component is configured as a random forest (RF) classifier having a depth of two and 1000 trees ... a convolutional neural network (CNN), or other type of machine learning or deep learning classifier”.
Paragraph [0136]; “The operations may also include classifying the region of tissue as likely to experience BCR or unlikely to experience BCR based, at least in part, on the joint probability ... the operations include generating a classification of the region of tissue as likely to experience cancer progression or unlikely to experience cancer recurrence based, at least in part, on the joint probability”.
Summary of Citations (Radhia)
[Section – 2.1, Paragraph – 1]; “The database consists on a total of 1005 images distributed as follows: 335 images with b value = 0 s / mm 2 , 335 images for diffusion weighted image with b value = 600 s / mm 2 , and 335 images for conventional anatomic T2-weighted sequence”.
[Section – 2.3, Paragraph – 2]; “we describe the series of post-processing procedures to build a computer-aided diagnosis (CAD) system based on machine learning techniques”.
[Section – 2.3.2, Paragraph – 3]; “The binary mask obtained through the segmentation step is used to identify the region of interest (ROI) on the parametric constructed image ADC map”.
Regarding claim 7, Madabhushi in the combination discloses computer program comprising program code, when executed by at least one processor, causes the at least one processor to perform the method of claim 1 (Madhabushi in [0118] discloses, “Processor 1002 can be a variety of various processors including dual microprocessor and other multi-processor architectures. Processor 1002 may be configured to perform steps of methods claimed and described herein”).
Summary of Citations (Madabhushi)
Paragraph [0118]; “Processor 1002 can be a variety of various processors including dual microprocessor and other multi-processor architectures. Processor 1002 may be configured to perform steps of methods claimed and described herein”.
Regarding claim 8, is a non-transitory computer readable storage medium claim
corresponds to method claim 1. Therefore, the rejection analysis of claim 1 is applied in claim 8.
Regarding claim 9, Madabhushi discloses about processing device comprising: a processor; and a memory, the processor being configured to load program code from the memory and to cause the processing device to perform the method of claim 1 (Madabhushi in [0118] discloses, “Processor 1002 can be a variety of various processors including dual microprocessor and other multi-processor architectures. Processor 1002 may be configured to perform steps of methods claimed and described herein. Memory 1004 can include volatile memory and/or non-volatile memory”).
Summary of Citations (Madabhushi)
Paragraph [0118]; “Processor 1002 can be a variety of various processors including dual microprocessor and other multi-processor architectures. Processor 1002 may be configured to perform steps of methods claimed and described herein. Memory 1004 can include volatile memory and/or non-volatile memory”.
Claim 2 is rejected under 35 U.S.C 103 as being unpatentable over Radhia in view of Madabhushi and further in view of Bradely US Patent Application Publication No. US-20230401697-A1 (hereinafter Bradely).
Regarding claim 2, Radhia in the combination discloses the computer-implemented method of claim 1.
Radhia and Madabhushi in the combination doesn’t disclose about the following limitation as further recited in the claim.
Bradely discloses for each of the one or more layers of the deep convolutional neural network (Bradely in [0039] discloses, “Feature vectors are extracted from intermediate convolutional layers within the CNN models before being pooled and concatenated into final vectors, rather than only using vectors from the final convolutional layers. Using intermediate layers captures different levels of spatial visual patterns”), determining the respective spatial context information by encoding the ADC map using one or more convolutional layers (Bradely in [0036] discloses, “encoding temporal and spatial information into a multi-dimensional input; such as a subtraction of pre-contrast and post-contrast images, maximum intensity projection (MIP) images, or formulation of apparent diffusion coefficient (ADC) maps”).
It would have been obvious to one of ordinary skill in art before the effective filling date of the claimed invention to integrate the technique of Bradely into the system of Radhia in view of Madabhushi because it would allow the system to focus on only medically relevant region that is important for metastasis detection.
Summary of Citations (Bradely)
Paragraph [0036]; “encoding temporal and spatial information into a multi-dimensional input; such as a subtraction of pre-contrast and post-contrast images, maximum intensity projection (MIP) images, or formulation of apparent diffusion coefficient (ADC) maps”.
Paragraph [0039]; “Feature vectors are extracted from intermediate convolutional layers within the CNN models before being pooled and concatenated into final vectors, rather than only using vectors from the final convolutional layers. Using intermediate layers captures different levels of spatial visual patterns”.
Claims 3, 4, 5, 11 and 12 are rejected under 35 U.S.C 103 as being unpatentable over Radhia in view of Madabhushi and further in view of Blackledge Patent Application Publication No. WO-2023099569-A1 (hereinafter Blackledge).
Regarding claim 3, Radhia discloses a computer-implemented method (Radhia in [Section – 2.3, Paragraph – 2] discloses, “we describe the series of post-processing procedures to build a computer-aided diagnosis (CAD) system based on machine learning techniques”), comprising: obtaining an apparent diffusion coefficient (ADC) map for a region of interest of a patient (Radhia in [Section – 2.3.2, Paragraph – 3] discloses about region of interest, “The binary mask obtained through the segmentation step is used to identify the region of interest (ROI) on the parametric constructed image ADC map”), the ADC map being determined based on a diffusion-weighted magnetic resonance imaging (MRI) measurement; obtaining an MRI image determined based on the diffusion-weighted MRI measurement or another MRI measurement (Radhia in [Section – 2.1, Paragraph – 1] discloses, “The database consists on a total of 1005 images distributed as follows: 335 images with b value = 0 s / mm 2 , 335 images for diffusion weighted image with b value = 600 s / mm 2 , and 335 images for conventional anatomic T2-weighted sequence”).
Radhia doesn’t disclose about the following limitation as further recited in the claim.
Madabhushi discloses about generating a prediction of a metastatic characterization using a deep convolutional neural network (Madabhushi in [0136] and [0064] discloses about CNN, “The operations may also include classifying the region of tissue as likely to experience BCR or unlikely to experience BCR based, at least in part, on the joint probability ... the operations include generating a classification of the region of tissue as likely to experience cancer progression or unlikely to experience cancer recurrence based, at least in part, on the joint probability”. Madabhushi in [0019] discloses about BCR being associated with metastatic, “BCR is often associated with the presence of more aggressive metastatic prostate cancer and hence a worse prognosis”).
Radhia and Madabhushi in the combination doesn’t disclose about the following limitation as further recited in the claim.
Blackledge discloses the deep convolutional neural network comprising multiple layers and one or more attention gates prioritizing amongst activations of a respective layer of the deep convolutional neural network based on a respective self-attention map that captures a spatial context of the respective layer; and determining a reliability of the prediction based on a comparison between each self-attention map of the one or more attention gates and a representation of the ADC map (Blackledge in [0020] discloses, “providing a set of training samples, each sample including an ADC map or data from which the ADC map is derivable, and a corresponding actual uncertainty map which maps values of actual uncertainty at the respective positions across the object, each actual uncertainty value being an actual measure, at a respective position, of the standard deviation in the corresponding ADC value at that position; and training the neural network to minimise a cost function that measures similarity between (i) the predicted uncertainty map outputted by the neural network when the ADC map of a given sample or the data from which the ADC map is derivable are inputted into the neural network, and (ii) the actual uncertainty map of that sample”. Furthermore, Blackledge in [0048] discloses about spatial region was applied to neural network map, “these regions were subsequently verified and (where needed) corrected by a radiologist. Resultant regions of interest (ROIs) were transferred onto both the gold standard <fADC maps, and onto those generated by the deep-learning algorithm, crADc anc* °ADC”).
It would have been obvious to one of ordinary skill in art before the effective filling date of the claimed invention to integrate the technique of Blackledge into the system of Radhia in view of Madabhushi because it would allow the system to increase the reliability of the predicted output.
Summary of Citations (Blackledge)
Paragraph [0020]; “providing a set of training samples, each sample including an ADC map or data from which the ADC map is derivable, and a corresponding actual uncertainty map which maps values of actual uncertainty at the respective positions across the object, each actual uncertainty value being an actual measure, at a respective position, of the standard deviation in the corresponding ADC value at that position; and training the neural network to minimise a cost function that measures similarity between (i) the predicted uncertainty map outputted by the neural network when the ADC map of a given sample or the data from which the ADC map is derivable are inputted into the neural network, and (ii) the actual uncertainty map of that sample”.
Paragraph [0048]; “these regions were subsequently verified and (where needed) corrected by a radiologist. Resultant regions of interest (ROIs) were transferred onto both the gold standard <fADC maps, and onto those generated by the deep-learning algorithm, crADc anc* °ADC”.
Summary of Citations (Madabhushi)
Paragraph [0019]; “BCR is often associated with the presence of more aggressive metastatic prostate cancer and hence a worse prognosis”.
Paragraph [0064]; “The radiomics machine learning component is configured as a random forest (RF) classifier having a depth of two and 1000 trees ... a convolutional neural network (CNN), or other type of machine learning or deep learning classifier”.
Paragraph [0136]; “The operations may also include classifying the region of tissue as likely to experience BCR or unlikely to experience BCR based, at least in part, on the joint probability ... the operations include generating a classification of the region of tissue as likely to experience cancer progression or unlikely to experience cancer recurrence based, at least in part, on the joint probability”.
Summary of Citations (Radhia)
[Section – 2.1, Paragraph – 1]; “The database consists on a total of 1005 images distributed as follows: 335 images with b value = 0 s / mm 2 , 335 images for diffusion weighted image with b value = 600 s / mm 2 , and 335 images for conventional anatomic T2-weighted sequence”.
[Section – 2.3, Paragraph – 2]; “we describe the series of post-processing procedures to build a computer-aided diagnosis (CAD) system based on machine learning techniques”.
[Section – 2.3.2, Paragraph – 3]; “The binary mask obtained through the segmentation step is used to identify the region of interest (ROI) on the parametric constructed image ADC map”.
Regarding claim 4, Radhia discloses computer-implemented method (Radhia in [Section – 2.3, Paragraph – 2] discloses, “we describe the series of post-processing procedures to build a computer-aided diagnosis (CAD) system based on machine learning techniques”), comprising: obtaining an apparent diffusion coefficient (ADC) map for a region of interest of a patient (Radhia in [Section – 2.3.2, Paragraph – 3] discloses about region of interest, “The binary mask obtained through the segmentation step is used to identify the region of interest (ROI) on the parametric constructed image ADC map”), the ADC map being determined based on a diffusion-weighted magnetic resonance imaging (MRI) measurement (Radhia in [Section – 2.1, Paragraph – 1] discloses, “The database consists on a total of 1005 images distributed as follows: 335 images with b value = 0 s / mm 2 , 335 images for diffusion weighted image with b value = 600 s / mm 2 , and 335 images for conventional anatomic T2-weighted sequence”).
Radhia doesn’t disclose about the following limitation as further recited in the claim.
Madabhushi discloses about performing a training process of a deep convolutional neural network to make predictions of a metastatic characterization based on MRI images of the region of interest (Madabhushi in [0136] and [0064] discloses about CNN, “The operations may also include classifying the region of tissue as likely to experience BCR or unlikely to experience BCR based, at least in part, on the joint probability ... the operations include generating a classification of the region of tissue as likely to experience cancer progression or unlikely to experience cancer recurrence based, at least in part, on the joint probability”. Madabhushi in [0019] discloses about BCR being associated with metastatic, “BCR is often associated with the presence of more aggressive metastatic prostate cancer and hence a worse prognosis”).
Radhia and Madabhushi in the combination doesn’t disclose about the following limitation as further recited in the claim.
Blackledge discloses the deep convolutional neural network comprising multiple layers and one or more attention gates prioritizing amongst activations of the respective layer of the deep convolutional neural network based on respective self-attention maps that capture a spatial context of the respective layer, wherein the training process is based on first ground-truth data indicative of the metastatic characterization, and the training process is further based on second ground-truth data to train the one or more attention gates, the second ground-truth data being based on the ADC map (Blackledge in [0020] discloses, “providing a set of training samples, each sample including an ADC map or data from which the ADC map is derivable, and a corresponding actual uncertainty map which maps values of actual uncertainty at the respective positions across the object, each actual uncertainty value being an actual measure, at a respective position, of the standard deviation in the corresponding ADC value at that position; and training the neural network to minimise a cost function that measures similarity between (i) the predicted uncertainty map outputted by the neural network when the ADC map of a given sample or the data from which the ADC map is derivable are inputted into the neural network, and (ii) the actual uncertainty map of that sample” wherein ADC map or data is the first ground truth and outputted by the neural network when the ADC map of a given sample is the second ground truth. Furthermore, Blackledge in [0048] discloses about spatial region was applied to neural network map, “these regions were subsequently verified and (where needed) corrected by a radiologist. Resultant regions of interest (ROIs) were transferred onto both the gold standard <fADC maps, and onto those generated by the deep-learning algorithm, crADc anc* °ADC”).
Summary of Citations (Blackledge)
Paragraph [0020]; “providing a set of training samples, each sample including an ADC map or data from which the ADC map is derivable, and a corresponding actual uncertainty map which maps values of actual uncertainty at the respective positions across the object, each actual uncertainty value being an actual measure, at a respective position, of the standard deviation in the corresponding ADC value at that position; and training the neural network to minimise a cost function that measures similarity between (i) the predicted uncertainty map outputted by the neural network when the ADC map of a given sample or the data from which the ADC map is derivable are inputted into the neural network, and (ii) the actual uncertainty map of that sample”.
Paragraph [0048]; “these regions were subsequently verified and (where needed) corrected by a radiologist. Resultant regions of interest (ROIs) were transferred onto both the gold standard <fADC maps, and onto those generated by the deep-learning algorithm, crADc anc* °ADC”.
Summary of Citations (Madabhushi)
Paragraph [0019]; “BCR is often associated with the presence of more aggressive metastatic prostate cancer and hence a worse prognosis”.
Paragraph [0063]; “The subset of Haralick features may be computed from spatial intensity co-occurrence matrices based on the second pre-treatment image, and quantifies intensity-based tumor heterogeneity. The subset of Gabor features quantifies signal response at multiple orientation and angles. The subset of CoLlAGe features quantifies gradient based tumor heterogeneity. CoLlAGe involves assigning an image voxel an entropy value associated with the co-occurrence matrix of gradient orientations computed around a voxel”.
Paragraph [0064]; “The radiomics machine learning component is configured as a random forest (RF) classifier having a depth of two and 1000 trees ... a convolutional neural network (CNN), or other type of machine learning or deep learning classifier”.
Paragraph [0136]; “The operations may also include classifying the region of tissue as likely to experience BCR or unlikely to experience BCR based, at least in part, on the joint probability ... the operations include generating a classification of the region of tissue as likely to experience cancer progression or unlikely to experience cancer recurrence based, at least in part, on the joint probability”.
Summary of Citations (Radhia)
[Section – 2.1, Paragraph – 1]; “The database consists on a total of 1005 images distributed as follows: 335 images with b value = 0 s / mm 2 , 335 images for diffusion weighted image with b value = 600 s / mm 2 , and 335 images for conventional anatomic T2-weighted sequence”.
[Section – 2.3, Paragraph – 2]; “we describe the series of post-processing procedures to build a computer-aided diagnosis (CAD) system based on machine learning techniques”.
[Section – 2.3.2, Paragraph – 3]; “The binary mask obtained through the segmentation step is used to identify the region of interest (ROI) on the parametric constructed image ADC map”.
Regarding claim 5, Blackledge in the combination discloses the computer-implemented method of claim 4, further comprising: for each of the one or more attention gates, re-sampling the ADC map to a spatial grid associated with the respective one of the one or more attention gates to determine a respective portion of the second ground-truth data (Blackledge in [0020] discloses, “training the neural network to minimise a cost function that measures similarity between (i) the predicted uncertainty map outputted by the neural network when the ADC map of a given sample or the data from which the ADC map is derivable are inputted into the neural network, and (ii) the actual uncertainty map of that sample” wherein ADC map or data is the first ground truth and outputted by the neural network when the ADC map of a given sample is the second ground truth. Furthermore, Blackledge in [0048] discloses about spatial region was applied to neural network map, “these regions were subsequently verified and (where needed) corrected by a radiologist. Resultant regions of interest (ROIs) were transferred onto both the gold standard <fADC maps, and onto those generated by the deep-learning algorithm, crADc anc* °ADC”).
Summary of Citations (Blackledge)
Paragraph [0020]; “providing a set of training samples, each sample including an ADC map or data from which the ADC map is derivable, and a corresponding actual uncertainty map which maps values of actual uncertainty at the respective positions across the object, each actual uncertainty value being an actual measure, at a respective position, of the standard deviation in the corresponding ADC value at that position; and training the neural network to minimise a cost function that measures similarity between (i) the predicted uncertainty map outputted by the neural network when the ADC map of a given sample or the data from which the ADC map is derivable are inputted into the neural network, and (ii) the actual uncertainty map of that sample”.
Paragraph [0048]; “these regions were subsequently verified and (where needed) corrected by a radiologist. Resultant regions of interest (ROIs) were transferred onto both the gold standard <fADC maps, and onto those generated by the deep-learning algorithm, crADc anc* °ADC”.
Regarding claim 11, Blackledge in the combination discloses processing device comprising: a processor; and a memory, the processor being configured to load program code from the memory and to cause the processing device to perform the method of claim 3 (Blackledge in [0079] discloses about the memory and in [0080] discloses about the processor loading program code).
Summary of Citations (Blackledge)
Paragraph [0079]; “read only memory (ROM), random access memory (RAM), magnetic RAM, core memory, magnetic disk storage mediums, optical storage mediums, flash memory devices and/or other machine readable mediums for storing information”.
Paragraph [0080]; “the program code or code segments to perform the necessary tasks may be stored in a computer readable medium. One or more processors may perform the necessary tasks. A code segment may represent a procedure, a function, a subprogram, a program”.
Regarding claim 12, Blackledge in the combination discloses processing device comprising: a processor; and a memory, the processor being configured to load program code from the memory and to cause the processing device to perform the method of claim 4 (Blackledge in [0079] discloses about the memory and in [0080] discloses about the processor loading program code).
Summary of Citations (Blackledge)
Paragraph [0079]; “read only memory (ROM), random access memory (RAM), magnetic RAM, core memory, magnetic disk storage mediums, optical storage mediums, flash memory devices and/or other machine readable mediums for storing information”.
Paragraph [0080]; “the program code or code segments to perform the necessary tasks may be stored in a computer readable medium. One or more processors may perform the necessary tasks. A code segment may represent a procedure, a function, a subprogram, a program”.
Claims 6 and 10 are rejected under 35 U.S.C 103 as being unpatentable over Radhia in view of Madabhushi and Blackledge further in view of Li Patent Application Publication No. CN-111260548-A (hereinafter Li).
Regarding claim 6, Radhia in the combination discloses the computer-implemented method of claim 4.
Radhia, Madabhushi and Blackledge in the combination doesn’t disclose about the following limitation as further recited in the claim.
Li discloses a loss of the training process associated with the second ground-truth data is a masked regression loss (Li in [0008 – 0009] discloses, “inputting a target image, a foreground mask image and a background image into a convolutional neural network, and performing fusion training on the target image and the background image to obtain a fused output image; calculating linear regression loss of the output image according to the foreground mask map”).
It would have been obvious to one of ordinary skill in art before the effective filling date of the claimed invention to integrate the technique of Li into the system of Radhia in view of Madabhushi and Blackledge because it would improve training of the attention gate focusing on medically relevant image region.
Summary of Citations (Li)
Paragraph [0008 – 0009]; inputting a target image, a foreground mask image and a background image into a convolutional neural network, and performing fusion training on the target image and the background image to obtain a fused output image; calculating linear regression loss of the output image according to the foreground mask map”.
Regarding claim 10, claim 10, which is similar in scope to claim 6, thus rejected under the same rationale.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner
should be directed to ZAID MUHAMMAD SALEH whose telephone number is (703)756-1684.
The examiner can normally be reached M-F 8 am - 5 pm ET. 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, Vu Le can be
reached on (571)272-7332. 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.
/ZAID MUHAMMAD SALEH/
Examiner, Art Unit 2668
07/09/2026
/VU LE/Supervisory Patent Examiner, Art Unit 2668
Prosecution Insights