Patents by Inventor SeyedBehzad Bozorgtabar
SeyedBehzad Bozorgtabar 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: 10614575Abstract: A method of tracking a cell through a plurality of images includes selecting the cell in at least one image obtained at a first time, generating a track of the cell through a plurality of images, including the at least one image, obtained at different times using a backward tracking, and generating a cell tree lineage of the cell using the track.Type: GrantFiled: December 28, 2017Date of Patent: April 7, 2020Assignee: International Business Machines CorporationInventors: Seyedbehzad Bozorgtabar, Rahil Garnavi, Suman Sedai
-
Patent number: 10510150Abstract: A method of tracking a cell through a plurality of images includes selecting the cell in at least one image obtained at a first time, generating a track of the cell through a plurality of images, including the at least one image, obtained at different times using a backward tracking, and generating a cell tree lineage of the cell using the track.Type: GrantFiled: June 20, 2017Date of Patent: December 17, 2019Assignee: International Business Machines CorporationInventors: Seyedbehzad Bozorgtabar, Rahil Garnavi, Suman Sedai
-
Publication number: 20190328300Abstract: A teleconferencing system includes a first terminal configured to acquire an audio signal and a video signal. A teleconferencing server in communication with the first terminal and a second terminal is configured to receive the video signal and the audio signal from the first terminal, in real-time, and transmit the video signal and the audio signal to the second terminal. A symptom recognition server in communication with the first terminal and the teleconferencing server is configured to receive the video signal and the audio signal from the first terminal, asynchronously, analyze the video signal and the audio signal to detect one or more indicia of illness, generate a diagnostic alert on detecting the one or more indicia of illness, and transmit the diagnostic alert to the teleconferencing server for display on the second terminal.Type: ApplicationFiled: April 27, 2018Publication date: October 31, 2019Inventors: SEYEDBEHZAD BOZORGTABAR, NOEL FAUX, RAHIL GARNAVI, SUMAN SEDAI
-
Patent number: 10373312Abstract: A method for computer-aided diagnosis of skin lesions includes obtaining a dermoscopic image, convolving the dermoscopic image in a plurality of convolutional layers, obtaining deconvolved outputs of at least two convolutional layers of the plurality of convolutional layers, obtaining side-output feature maps by applying loss functions to the deconvolved outputs of the at least two convolutional layers, obtaining a first concatenated feature map by concatenating the side-output feature maps with different first weights, obtaining a second concatenated feature map by concatenating the side-output feature maps with different second weights, and producing a final score map by convolving the first and second concatenated feature maps in a final convolutional layer followed by a loss layer. Also disclosed: a computer-readable medium embodying instructions for the method, and an apparatus configured to implement the method.Type: GrantFiled: July 6, 2017Date of Patent: August 6, 2019Assignee: International Business Machines CorporationInventors: Mani Abedini, SeyedBehzad Bozorgtabar, Rajib Chakravorty, Sergey Demyanov, Rahil Garnavi, Zongyuan Ge
-
Patent number: 10283221Abstract: A method for risk assessment comprises receiving one or more images of a plurality of lesions captured from a body of a target person, generating one or more digital signatures based on the one or more images from the body of the target person, comparing the generated one or more digital signatures to digital signatures of respective reference persons, wherein the comparing comprises measuring similarities between the generated one or more digital signatures and the digital signatures of the respective reference persons, and determining a risk factor for the target person of developing a disease based on the measured similarities and predetermined risk factors of developing the disease for the reference persons.Type: GrantFiled: October 27, 2016Date of Patent: May 7, 2019Assignee: International Business Machines CorporationInventors: Mani Abedini, Seyedbehzad Bozorgtabar, Rajib Chakravorty, Rahil Garnavi
-
Patent number: 10229499Abstract: A dermoscopic lesion area is identified by: Obtaining a dermoscopic image and running a convolutional neural network image classifier on the dermoscopic image to obtain pixelwise lesion prediction scores. Segmenting the dermoscopic image into super-pixels, and computing for each super-pixel an average of the pixelwise prediction scores for pixels within that super-pixel. Computing a mean prediction score across the plurality of super-pixels. Assigning a confidence indicator of “1” to each super-pixel with a prediction score equal or greater than the mean prediction score, and a confidence indicator of “0” to each super-pixel with a prediction score less than the mean prediction score.Type: GrantFiled: December 29, 2017Date of Patent: March 12, 2019Assignee: International Business Machines CorporationInventors: Seyedbehzad Bozorgtabar, Rahil Garnavi, Pallab Roy, Suman Sedai
-
Patent number: 10223788Abstract: A dermoscopic lesion area is identified by: Obtaining a dermoscopic image and running a convolutional neural network image classifier on the dermoscopic image to obtain pixelwise lesion prediction scores. Segmenting the dermoscopic image into super-pixels, and computing for each super-pixel an average of the pixelwise prediction scores for pixels within that super-pixel. Computing a mean prediction score across the plurality of super-pixels. Assigning a confidence indicator of “1” to each super-pixel with a prediction score equal or greater than the mean prediction score, and a confidence indicator of “0” to each super-pixel with a prediction score less than the mean prediction score.Type: GrantFiled: February 24, 2017Date of Patent: March 5, 2019Assignee: International Business Machines CorporationInventors: Seyedbehzad Bozorgtabar, Rahil Garnavi, Pallab Roy, Suman Sedai
-
Patent number: 10181188Abstract: A structure-preserving composite model for skin lesion segmentation includes partitioning a dermoscopic image into superpixels at a first scale. Each superpixel is a vertex on a graph defined by color coordinates and spatial coordinates, and represents a number of pixels of the dermoscopic image according to the first scale. Further, constructing a plurality of k background templates by k-means clustering selected ones of the superpixels in space and color. Additionally, generating sparse representations of the plurality of superpixels based on the plurality of background templates. Also, calculating a reconstruction error for each superpixel by comparison of its sparse representation to its original color coordinates and spatial coordinates. Furthermore, outputting a confidence map that identifies each pixel of the dermoscopic image as belonging or not belonging to a skin lesion, based on the reconstruction errors of the representative superpixels.Type: GrantFiled: February 17, 2017Date of Patent: January 15, 2019Assignee: International Business Machines CorporationInventors: Mani Abedini, SeyedBehzad Bozorgtabar, Rahil Garnavi
-
Patent number: 10176574Abstract: A structure-preserving composite model for skin lesion segmentation includes partitioning a dermoscopic image into superpixels at a first scale. Each superpixel is a vertex on a graph defined by color coordinates and spatial coordinates, and represents a number of pixels of the dermoscopic image according to the first scale. Further, constructing a plurality of k background templates by k-means clustering selected ones of the superpixels in space and color. Additionally, generating sparse representations of the plurality of superpixels based on the plurality of background templates. Also, calculating a reconstruction error for each superpixel by comparison of its sparse representation to its original color coordinates and spatial coordinates. Furthermore, outputting a confidence map that identifies each pixel of the dermoscopic image as belonging or not belonging to a skin lesion, based on the reconstruction errors of the representative superpixels.Type: GrantFiled: December 31, 2017Date of Patent: January 8, 2019Assignee: International Business Machines CorporationInventors: Mani Abedini, SeyedBehzad Bozorgtabar, Rahil Garnavi
-
Publication number: 20180365842Abstract: A method of tracking a cell through a plurality of images includes selecting the cell in at least one image obtained at a first time, generating a track of the cell through a plurality of images, including the at least one image, obtained at different times using a backward tracking, and generating a cell tree lineage of the cell using the track.Type: ApplicationFiled: December 28, 2017Publication date: December 20, 2018Inventors: SEYEDBEHZAD BOZORGTABAR, RAHIL GARNAVI, SUMAN SEDAI
-
Publication number: 20180365841Abstract: A method of tracking a cell through a plurality of images includes selecting the cell in at least one image obtained at a first time, generating a track of the cell through a plurality of images, including the at least one image, obtained at different times using a backward tracking, and generating a cell tree lineage of the cell using the track.Type: ApplicationFiled: June 20, 2017Publication date: December 20, 2018Inventors: SEYEDBEHZAD BOZORGTABAR, RAHIL GARNAVI, SUMAN SEDAI
-
Publication number: 20180130203Abstract: A method for computer-aided diagnosis of skin lesions includes obtaining a dermoscopic image, convolving the dermoscopic image in a plurality of convolutional layers, obtaining deconvolved outputs of at least two convolutional layers of the plurality of convolutional layers, obtaining side-output feature maps by applying loss functions to the deconvolved outputs of the at least two convolutional layers, obtaining a first concatenated feature map by concatenating the side-output feature maps with different first weights, obtaining a second concatenated feature map by concatenating the side-output feature maps with different second weights, and producing a final score map by convolving the first and second concatenated feature maps in a final convolutional layer followed by a loss layer. Also disclosed: a computer-readable medium embodying instructions for the method, and an apparatus configured to implement the method.Type: ApplicationFiled: July 6, 2017Publication date: May 10, 2018Inventors: Mani Abedini, SeyedBehzad Bozorgtabar, Rajib Chakravorty, Sergey Demyanov, Rahil Garnavi, Zongyuan Ge
-
Publication number: 20180122072Abstract: A structure-preserving composite model for skin lesion segmentation includes partitioning a dermoscopic image into superpixels at a first scale. Each superpixel is a vertex on a graph defined by color coordinates and spatial coordinates, and represents a number of pixels of the dermoscopic image according to the first scale. Further, constructing a plurality of k background templates by k-means clustering selected ones of the superpixels in space and color. Additionally, generating sparse representations of the plurality of superpixels based on the plurality of background templates. Also, calculating a reconstruction error for each superpixel by comparison of its sparse representation to its original color coordinates and spatial coordinates. Furthermore, outputting a confidence map that identifies each pixel of the dermoscopic image as belonging or not belonging to a skin lesion, based on the reconstruction errors of the representative superpixels.Type: ApplicationFiled: December 31, 2017Publication date: May 3, 2018Inventors: Mani Abedini, SeyedBehzad Bozorgtabar, Rahil Garnavi
-
Publication number: 20180122071Abstract: A dermoscopic lesion area is identified by: Obtaining a dermoscopic image and running a convolutional neural network image classifier on the dermoscopic image to obtain pixelwise lesion prediction scores. Segmenting the dermoscopic image into super-pixels, and computing for each super-pixel an average of the pixelwise prediction scores for pixels within that super-pixel. Computing a mean prediction score across the plurality of super-pixels. Assigning a confidence indicator of “1” to each super-pixel with a prediction score equal or greater than the mean prediction score, and a confidence indicator of “0” to each super-pixel with a prediction score less than the mean prediction score.Type: ApplicationFiled: December 29, 2017Publication date: May 3, 2018Inventors: SEYEDBEHZAD BOZORGTABAR, RAHIL GARNAVI, PALLAB ROY, SUMAN SEDAI
-
Publication number: 20180121626Abstract: A method for risk assessment comprises receiving one or more images of a plurality of lesions captured from a body of a target person, generating one or more digital signatures based on the one or more images from the body of the target person, comparing the generated one or more digital signatures to digital signatures of respective reference persons, wherein the comparing comprises measuring similarities between the generated one or more digital signatures and the digital signatures of the respective reference persons, and determining a risk factor for the target person of developing a disease based on the measured similarities and predetermined risk factors of developing the disease for the reference persons.Type: ApplicationFiled: October 27, 2016Publication date: May 3, 2018Inventors: Mani Abedini, Seyedbehzad Bozorgtabar, Rajib Chakravorty, Rahil Garnavi
-
Publication number: 20180061046Abstract: A dermoscopic lesion area is identified by: Obtaining a dermoscopic image and running a convolutional neural network image classifier on the dermoscopic image to obtain pixelwise lesion prediction scores. Segmenting the dermoscopic image into super-pixels, and computing for each super-pixel an average of the pixelwise prediction scores for pixels within that super-pixel. Computing a mean prediction score across the plurality of super-pixels. Assigning a confidence indicator of “1” to each super-pixel with a prediction score equal or greater than the mean prediction score, and a confidence indicator of “0” to each super-pixel with a prediction score less than the mean prediction score.Type: ApplicationFiled: February 24, 2017Publication date: March 1, 2018Inventors: SEYEDBEHZAD BOZORGTABAR, RAHIL GARNAVI, PALLAB ROY, SUMAN SEDAI
-
Publication number: 20170243345Abstract: A structure-preserving composite model for skin lesion segmentation includes partitioning a dermoscopic image into superpixels at a first scale. Each superpixel is a vertex on a graph defined by color coordinates and spatial coordinates, and represents a number of pixels of the dermoscopic image according to the first scale. Further, constructing a plurality of k background templates by k-means clustering selected ones of the superpixels in space and color. Additionally, generating sparse representations of the plurality of superpixels based on the plurality of background templates. Also, calculating a reconstruction error for each superpixel by comparison of its sparse representation to its original color coordinates and spatial coordinates. Furthermore, outputting a confidence map that identifies each pixel of the dermoscopic image as belonging or not belonging to a skin lesion, based on the reconstruction errors of the representative superpixels.Type: ApplicationFiled: February 17, 2017Publication date: August 24, 2017Inventors: Mani Abedini, SeyedBehzad Bozorgtabar, Rahil Garnavi