Patents by Inventor David James Beymer
David James Beymer has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11967067Abstract: A candidate generator generates a set of candidate three-dimensional image patches from an input volume. A candidate classifier classifies the set of candidate three-dimensional image patches as containing or not containing disease. Classifying the set of candidate three-dimensional image patches comprises generating an attention mask for each given candidate three-dimensional image patch within the set of candidate three-dimensional image patches to form a set of attention masks, applying the set of attention masks to the set of candidate three-dimensional image patches to form a set of masked image patches, and classifying the set of masked image patches as containing or not containing the disease. The candidate classifier applies soft attention and hard attention to the three-dimensional image patches such that distinctive image regions are highlighted proportionally to their contribution to classification while completely removing image regions that may cause confusion.Type: GrantFiled: May 13, 2021Date of Patent: April 23, 2024Inventors: Shafiqul Abedin, Hongzhi Wang, Ehsan Dehghan Marvast, David James Beymer
-
Patent number: 11875898Abstract: Methods and systems for training computer-aided condition detection systems. One method includes receiving a plurality of images for a plurality of patients, some of the images including an annotation associated with a condition; iteratively applying a first deep learning network to each of the images to produce an attention map, a feature map, and an image-level probability of the condition for each of the images; iteratively applying a second deep learning network to each feature map produced by the first network to produce a plurality of outputs; training the first network based on the attention map produced for each image; and training the second network based on the output produced for each of the patients. The second network includes a plurality of convolution layers and a plurality of convolutional long short-term memory (LSTM) layers. Each of the outputs includes a patient-level probability of the condition for one of the patients.Type: GrantFiled: May 26, 2021Date of Patent: January 16, 2024Assignee: Merative US L.P.Inventors: Luyao Shi, David James Beymer, Ehsan Dehghan Marvast, Deepta Rajan
-
Patent number: 11830187Abstract: Methods and systems for training computer-aided condition detection systems. One method includes receiving a plurality of images for a plurality of patients, some of the images including an annotation associated with a condition; iteratively applying a first deep learning network to each of the images to produce a segmentation map, a feature map, and an image-level probability of the condition for each of the images; iteratively applying a second deep learning network to each feature map produced by the first network to produce a plurality of outputs; training the first network based on the segmentation map produced for each image; and training the second network based on the output produced for each of the patients. The second network includes a plurality of convolution layers and a plurality of convolutional long short-term memory (LSTM) layers. Each of the outputs includes a patient-level probability of the condition for one of the patients.Type: GrantFiled: May 26, 2021Date of Patent: November 28, 2023Assignee: International Business Machines CorporationInventors: Luyao Shi, David James Beymer, Ehsan Dehghan Marvast, Deepta Rajan
-
Publication number: 20220383489Abstract: Methods and systems for training computer-aided condition detection systems. One method includes receiving a plurality of images for a plurality of patients, some of the images including an annotation associated with a condition; iteratively applying a first deep learning network to each of the images to produce a segmentation map, a feature map, and an image-level probability of the condition for each of the images; iteratively applying a second deep learning network to each feature map produced by the first network to produce a plurality of outputs; training the first network based on the segmentation map produced for each image; and training the second network based on the output produced for each of the patients. The second network includes a plurality of convolution layers and a plurality of convolutional long short-term memory (LSTM) layers. Each of the outputs includes a patient-level probability of the condition for one of the patients.Type: ApplicationFiled: May 26, 2021Publication date: December 1, 2022Inventors: Luyao Shi, David James Beymer, Ehsan Dehghan Marvast, Deepta Rajan
-
Publication number: 20220384035Abstract: Methods and systems for training computer-aided condition detection systems. One method includes receiving a plurality of images for a plurality of patients, some of the images including an annotation associated with a condition; iteratively applying a first deep learning network to each of the images to produce an attention map, a feature map, and an image-level probability of the condition for each of the images; iteratively applying a second deep learning network to each feature map produced by the first network to produce a plurality of outputs; training the first network based on the attention map produced for each image; and training the second network based on the output produced for each of the patients. The second network includes a plurality of convolution layers and a plurality of convolutional long short-term memory (LSTM) layers. Each of the outputs includes a patient-level probability of the condition for one of the patients.Type: ApplicationFiled: May 26, 2021Publication date: December 1, 2022Inventors: Luyao Shi, David James Beymer, Ehsan Dehghan Marvast, Deepta Rajan
-
Publication number: 20220375068Abstract: A candidate generator generates a set of candidate three-dimensional image patches from an input volume. A candidate classifier classifies the set of candidate three-dimensional image patches as containing or not containing disease. Classifying the set of candidate three-dimensional image patches comprises generating an attention mask for each given candidate three-dimensional image patch within the set of candidate three-dimensional image patches to form a set of attention masks, applying the set of attention masks to the set of candidate three-dimensional image patches to form a set of masked image patches, and classifying the set of masked image patches as containing or not containing the disease. The candidate classifier applies soft attention and hard attention to the three-dimensional image patches such that distinctive image regions are highlighted proportionally to their contribution to classification while completely removing image regions that may cause confusion.Type: ApplicationFiled: May 13, 2021Publication date: November 24, 2022Inventors: Shafiqul Abedin, Hongzhi Wang, Ehsan Dehghan Marvast, David James Beymer
-
Patent number: 11417424Abstract: Systems and methods for developing a disease detection model. One method includes training the model using an image study and an associated disease label mined from a radiology report. The image study including a sequence of a plurality of two-dimensional slices of a three-dimensional image volume, and the model including a convolutional neural network layer and a convolutional long short-term memory layer. Training the model includes individually extracting a set of features from each of the plurality of two-dimensional slices using the convolutional neural network layer, sequentially processing the features extracted by the convolutional neural network layer for each of the plurality of two-dimensional slices using the convolutional long short-term memory layer, processing output from the convolutional long short-term memory layer for each of the plurality of two-dimensional slices to generate a probability of the disease, and updating the model based on comparing the probability to the label.Type: GrantFiled: October 11, 2019Date of Patent: August 16, 2022Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Nathaniel Mason Braman, Ehsan Dehghan Marvast, David James Beymer
-
Patent number: 11195273Abstract: Systems and methods for developing a disease detection model. One method includes training the model using an image study and an associated disease label mined from a radiology report. The image study including a sequence of a plurality of two-dimensional slices of a three-dimensional image volume, and the model including a convolutional neural network layer and a convolutional long short-term memory layer.Type: GrantFiled: October 11, 2019Date of Patent: December 7, 2021Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Nathaniel Mason Braman, Ehsan Dehghan Marvast, David James Beymer
-
Publication number: 20210110913Abstract: Systems and methods for developing a disease detection model. One method includes training the model using an image study and an associated disease label mined from a radiology report. The image study including a sequence of a plurality of two-dimensional slices of a three-dimensional image volume, and the model including a convolutional neural network layer and a convolutional long short-term memory layer. Training the model includes individually extracting a set of features from each of the plurality of two-dimensional slices using the convolutional neural network layer, sequentially processing the features extracted by the convolutional neural network layer for each of the plurality of two-dimensional slices using the convolutional long short-term memory layer, processing output from the convolutional long short-term memory layer for each of the plurality of two-dimensional slices to generate a probability of the disease, and updating the model based on comparing the probability to the label.Type: ApplicationFiled: October 11, 2019Publication date: April 15, 2021Inventors: Nathaniel Mason Braman, Ehsan Dehghan Marvast, David James Beymer
-
Publication number: 20210110532Abstract: Systems and methods for developing a disease detection model. One method includes training the model using an image study and an associated disease label mined from a radiology report. The image study including a sequence of a plurality of two-dimensional slices of a three-dimensional image volume, and the model including a convolutional neural network layer and a convolutional long short-term memory layer.Type: ApplicationFiled: October 11, 2019Publication date: April 15, 2021Inventors: Nathaniel Mason Braman, Ehsan Dehghan Marvast, David James Beymer
-
Patent number: 8917917Abstract: A method for recognizing heart diseases in a cardiac echo video of a heart with an unknown disease using a spatio-temporal disease model derived from a training echo video, comprising the steps of: generating a plurality of training models for heart diseases, wherein the cardiac echo videos are each derived from a known viewpoint and the disease of the heart is known; analyzing the video of the heart with the unknown disease by fitting a model of shape and motion for each frame and combining the results across the frames; and, reporting the disease using a classification method for choosing among the diseases of interest.Type: GrantFiled: September 14, 2012Date of Patent: December 23, 2014Assignee: International Business Machines CorporationInventors: David James Beymer, Fei Wang, Tanveer Fathima Mahmood
-
Patent number: 8750375Abstract: According to one embodiment of the present invention, a method for echocardiogram view classification is provided. According to one embodiment of the present invention, a method comprises: obtaining a plurality of video images of a subject; aligning the plurality images; using the aligned images to generate a motion magnitude image; filtering the motion magnitude image using an edge map on image intensity; detecting features on the motion magnitude image, retaining only those features which lie in the neighborhood of intensity edges; encoding the remaining features by generating, x, y image coordinates, a motion magnitude histogram in a window around the feature point, and a histogram of intensity values near the feature point; and using the encoded features to classify the video images of the subject into a predetermined classification.Type: GrantFiled: June 19, 2010Date of Patent: June 10, 2014Assignee: International Business Machines CorporationInventors: David James Beymer, Ritwik K Kumar, Tanveer Fathima Syeda-Mahmood, Fei Wang
-
Patent number: 8737702Abstract: Systems and methods providing automated extraction of information contained in video data and uses thereof are described. In particular, systems and associated methods are described that provide techniques for extracting data embedded in video, for example measurement-value pairs of medical videos, for use in a variety of applications, for example video indexing, searching and decision support applications.Type: GrantFiled: July 23, 2010Date of Patent: May 27, 2014Assignee: International Business Machines CorporationInventors: Arnon Amir, David James Beymer, Karen W. Brannon, Sangeeta T. Doraiswamy, Tanveer Fathima Syeda-Mahmood
-
Patent number: 8712122Abstract: Continuous wave Doppler images in a data base comprising cardiac echo studies are processed to separate Doppler frames. The frames are pre-processed to extract envelope curves and their corner shape features. Shape patterns in Doppler images from echo studies of patients with known cardiac (valvular) diseases are employed to infer the similarity in valvular disease labels for purposes of automated clinical decision support. Specifically, similarity in appearance of Doppler images from the same disease class is modeled as a constrained non-rigid translation transform of velocity envelopes embedded in these images. Shape similarity between two Doppler images is then judged by recovering the alignment transform using a variant of dynamic shape warping. Since different diseases appear as characteristic shape patterns in Doppler images, measuring the similarity in the shape pattern conveyed within the velocity region of two Doppler images can infer the similarity in their diagnosis labels.Type: GrantFiled: March 31, 2011Date of Patent: April 29, 2014Assignee: International Business Machines CorporationInventors: Tanveer F. Syeda-Mahmood, David James Beymer
-
Patent number: 8594398Abstract: A method for recognizing heart diseases in a cardiac echo video of a heart with an unknown disease using a spatio-temporal disease model derived from a training echo video, comprising the steps of: generating a plurality of training models for heart diseases, wherein the cardiac echo videos are each derived from a known viewpoint and the disease of the heart is known; analyzing the video of the heart with the unknown disease by fitting a model of shape and motion for each frame and combining the results across the frames; and, reporting the disease using a classification method for choosing among the diseases of interest.Type: GrantFiled: June 26, 2009Date of Patent: November 26, 2013Assignee: International Business Machines CorporationInventors: David James Beymer, Fei Wang, Tanveer Fathima Mahmood
-
Patent number: 8577109Abstract: Systems and methods providing automated extraction of information contained in video data and uses thereof are described. In particular, systems and associated methods are described that provide techniques for extracting data embedded in video, for example measurement-value pairs of medical videos, for use in a variety of applications, for example video indexing, searching and decision support applications.Type: GrantFiled: August 27, 2012Date of Patent: November 5, 2013Assignee: International Business Machines CorporationInventors: Arnon Amir, David James Beymer, Karen W. Brannon, Sangeeta T. Doraiswamy, Tanveer Fathima Syeda-Mahmood
-
Publication number: 20130054268Abstract: Systems and methods for removing or suppressing information in images and video frames is described herein. In particular, systems and methods provide for removing information from images capable of identifying individuals related to the image. For example, embodiments provide for the removal of protected health information (PHI) from source images, including medical images, video frames, and documents converted to images or video frames. In addition, embodiments operate on actual images and video frames as opposed to data extracted from such sources. In particular, embodiments provide for the creation of a PHI filter for an individual of interest comprised of identifying information. Images are filtered using the PHI filter and information potentially identifying the individual of interest is located and removed from the image.Type: ApplicationFiled: August 26, 2011Publication date: February 28, 2013Applicant: International Business Machines CorporationInventors: David James Beymer, Varun Bhagwan, Tyrone W. A. Grandison, Daniel Frederick Gruhl
-
Publication number: 20130011033Abstract: A method for recognizing heart diseases in a cardiac echo video of a heart with an unknown disease using a spatio-temporal disease model derived from a training echo video, comprising the steps of: generating a plurality of training models for heart diseases, wherein the cardiac echo videos are each derived from a known viewpoint and the disease of the heart is known; analyzing the video of the heart with the unknown disease by fitting a model of shape and motion for each frame and combining the results across the frames; and, reporting the disease using a classification method for choosing among the diseases of interest.Type: ApplicationFiled: September 14, 2012Publication date: January 10, 2013Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: David James Beymer, Fei Wang, Tanveer Fathima Mahmood
-
Publication number: 20120321189Abstract: Systems and methods providing automated extraction of information contained in video data and uses thereof are described. In particular, systems and associated methods are described that provide techniques for extracting data embedded in video, for example measurement-value pairs of medical videos, for use in a variety of applications, for example video indexing, searching and decision support applications.Type: ApplicationFiled: August 27, 2012Publication date: December 20, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Arnon Amir, David James Beymer, Karen W. Brannon, Sangeeta T. Doraiswamy, Tanveer Fathima Syeda-Mahmood
-
Publication number: 20120288171Abstract: According to one embodiment of the present invention, a method for echocardiogram view classification is provided. According to one embodiment of the present invention, a method comprises: obtaining a plurality of video images of a subject; aligning the plurality images; using the aligned images to generate a motion magnitude image; filtering the motion magnitude image using an edge map on image intensity; detecting features on the motion magnitude image, retaining only those features which lie in the neighborhood of intensity edges; encoding the remaining features by generating, x, y image coordinates, a motion magnitude histogram in a window around the feature point, and a histogram of intensity values near the feature point; and using the encoded features to classify the video images of the subject into a predetermined classification.Type: ApplicationFiled: July 27, 2012Publication date: November 15, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: David James Beymer, Ritwik Kailash Kumar, Tanveer Fathima Syeda-Mahmood, Fei Wang