Patents by Inventor Aditya Khosla
Aditya Khosla 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: 11915823Abstract: In some aspects, the described systems and methods provide for validating performance of a model trained on a plurality of annotated pathology images. A pathology image is accessed. Frames are generated using the pathology image. Each frame in the set includes a distinct portion of the pathology image. Reference annotations are received from one or more users. The reference annotations describe at least one of a plurality of tissue or cellular characteristic categories for one or more frames in the set. Each frame in the set is processed using the trained model to generate model predictions. The model predictions describe at least one of the tissue or cellular characteristic categories for the processed frame. Performance of the trained model is validated based on determining a degree of association between the reference annotations and the model predictions for each frame and/or across all frames in the set of frames.Type: GrantFiled: November 10, 2022Date of Patent: February 27, 2024Assignee: PathAI, Inc.Inventors: Harsha Vardhan Pokkalla, Hunter L. Elliott, Dayong Wang, Benjamin P. Glass, Ilan N. Wapinski, Jennifer K. Kerner, Andrew H. Beck, Aditya Khosla, Sai Chowdary Gullapally, Ramprakash Srinivasan
-
Patent number: 11908139Abstract: In some aspects, the described systems and methods provide for a method for training a statistical model to predict tissue characteristics for a pathology image. The method includes accessing annotated pathology images. Each of the images includes an annotation describing a tissue characteristic category for a portion of the image. A set of training patches and a corresponding set of annotations are defined using an annotated pathology image. Each of the training patches in the set includes values obtained from a respective subset of pixels in the annotated pathology image and is associated with a corresponding patch annotation determined based on an annotation associated with the respective subset of pixels. The statistical model is trained based on the set of training patches and the corresponding set of patch annotations. The trained statistical model is stored on at least one storage device.Type: GrantFiled: July 13, 2023Date of Patent: February 20, 2024Assignee: PathAI, Inc.Inventors: Andrew H. Beck, Aditya Khosla
-
Patent number: 11756198Abstract: In some aspects, the described systems and methods provide for a method for training a statistical model to predict tissue characteristics for a pathology image. The method includes accessing annotated pathology images. Each of the images includes an annotation describing a tissue characteristic category for a portion of the image. A set of training patches and a corresponding set of annotations are defined using an annotated pathology image. Each of the training patches in the set includes values obtained from a respective subset of pixels in the annotated pathology image and is associated with a corresponding patch annotation determined based on an annotation associated with the respective subset of pixels. The statistical model is trained based on the set of training patches and the corresponding set of patch annotations. The trained statistical model is stored on at least one storage device.Type: GrantFiled: December 6, 2021Date of Patent: September 12, 2023Assignee: PathAI, Inc.Inventors: Andrew H. Beck, Aditya Khosla
-
Patent number: 11657505Abstract: In some aspects, the described systems and methods provide for a method for training a model to predict survival time for a patient. The method includes accessing annotated pathology images associated with a first group of patients in a clinical trial. Each of the annotated pathology images is associated with survival data for a respective patient. Each of the annotated pathology images includes an annotation describing a tissue characteristic category for a portion of the image. Values for one or more features are extracted from each of the annotated pathology images. A model is trained based on the survival data and the extracted values for the features. The trained model is stored on a storage device.Type: GrantFiled: May 24, 2021Date of Patent: May 23, 2023Assignee: PathAI, Inc.Inventors: Andrew H. Beck, Aditya Khosla
-
Patent number: 11527319Abstract: In some aspects, the described systems and methods provide for validating performance of a model trained on a plurality of annotated pathology images. A pathology image is accessed. Frames are generated using the pathology image. Each frame in the set includes a distinct portion of the pathology image. Reference annotations are received from one or more users. The reference annotations describe at least one of a plurality of tissue or cellular characteristic categories for one or more frames in the set. Each frame in the set is processed using the trained model to generate model predictions. The model predictions describe at least one of the tissue or cellular characteristic categories for the processed frame. Performance of the trained model is validated based on determining a degree of association between the reference annotations and the model predictions for each frame and/or across all frames in the set of frames.Type: GrantFiled: September 11, 2020Date of Patent: December 13, 2022Assignee: PathAI, Inc.Inventors: Harsha Vardhan Pokkalla, Hunter L. Elliott, Dayong Wang, Benjamin P. Glass, Ilan N. Wapinski, Jennifer K. Kerner, Andrew H. Beck, Aditya Khosla, Sai Chowdary Gullapally, Ramprakash Srinivasan
-
Publication number: 20220375606Abstract: Techniques for performing diagnostic assessments based on digital pathology data are disclosed. In one particular embodiment, the techniques may be realized as a method for performing a diagnostic assessment based on digital pathology data comprising obtaining first digital pathology data comprising intensity information, the first digital pathology data being associated with a plurality of regions of interest in a biological sample; applying first machine learning models to the first digital pathology data, the first machine learning models identifying first regions of interest among the plurality of regions of interest based on the intensity information; applying second machine learning models to the first digital pathology data, the second machine learning models identifying at least one pattern associated with at least one of the first regions of interest; generating a diagnostic assessment based on the first regions of interest and the at least one pattern.Type: ApplicationFiled: May 18, 2022Publication date: November 24, 2022Inventors: Benjamin GLASS, Surya Teja CHAVALI, Syed Ashar JAVED, Shamira Sridharan WEAVER, Murray RESNICK, Ilan WAPINSKI, Michael MONTALTO, Andrew Hanno BECK, Aditya KHOSLA
-
Patent number: 11195279Abstract: In some aspects, the described systems and methods provide for a method for training a statistical model to predict tissue characteristics for a pathology image. The method includes accessing annotated pathology images. Each of the images includes an annotation describing a tissue characteristic category for a portion of the image. A set of training patches and a corresponding set of annotations are defined using an annotated pathology image. Each of the training patches in the set includes values obtained from a respective subset of pixels in the annotated pathology image and is associated with a corresponding patch annotation determined based on an annotation associated with the respective subset of pixels. The statistical model is trained based on the set of training patches and the corresponding set of patch annotations. The trained statistical model is stored on at least one storage device.Type: GrantFiled: April 7, 2020Date of Patent: December 7, 2021Assignee: PathAI, Inc.Inventors: Andrew H. Beck, Aditya Khosla
-
Patent number: 11080855Abstract: In some aspects, the described systems and methods provide for a method for predicting tissue characteristics for a pathology image. A statistical model trained on multiple annotated pathology images is used. Each of the training pathology images includes an annotation describing tissue characteristics for one or more portions of the image. The method includes accessing a pathology image for predicting tissue characteristics. A trained statistical model is retrieved from a storage device. A set of patches is defined from the pathology image. Each of the patches in the set includes a subset of pixels from the corresponding pathology image. The set of patches is processed using the trained statistical model to predict respective annotations for each patch in the set. The predicted annotations are stored on the storage device.Type: GrantFiled: June 6, 2018Date of Patent: August 3, 2021Assignee: Path AI, Inc.Inventors: Andrew H. Beck, Aditya Khosla
-
Patent number: 11017532Abstract: In some aspects, the described systems and methods provide for a method for training a model to predict survival time for a patient. The method includes accessing annotated pathology images associated with a first group of patients in a clinical trial. Each of the annotated pathology images is associated with survival data for a respective patient. Each of the annotated pathology images includes an annotation describing a tissue characteristic category for a portion of the image. Values for one or more features are extracted from each of the annotated pathology images. A model is trained based on the survival data and the extracted values for the features. The trained model is stored on a storage device.Type: GrantFiled: April 23, 2020Date of Patent: May 25, 2021Assignee: PathAI, Inc.Inventors: Andrew H. Beck, Aditya Khosla
-
Patent number: 10650929Abstract: In some aspects, the described systems and methods provide for a method for training a model to predict survival time for a patient. The method includes accessing annotated pathology images associated with a first group of patients in a clinical trial. Each of the annotated pathology images is associated with survival data for a respective patient. Each of the annotated pathology images includes an annotation describing a tissue characteristic category for a portion of the image. Values for one or more features are extracted from each of the annotated pathology images. A model is trained based on the survival data and the extracted values for the features. The trained model is stored on a storage device.Type: GrantFiled: June 6, 2018Date of Patent: May 12, 2020Assignee: PathAI, Inc.Inventors: Andrew H. Beck, Aditya Khosla
-
Patent number: 10650520Abstract: In some aspects, the described systems and methods provide for a method for training a statistical model to predict tissue characteristics for a pathology image. The method includes accessing annotated pathology images. Each of the images includes an annotation describing a tissue characteristic category for a portion of the image. A set of training patches and a corresponding set of annotations are defined using an annotated pathology image. Each of the training patches in the set includes values obtained from a respective subset of pixels in the annotated pathology image and is associated with a corresponding patch annotation determined based on an annotation associated with the respective subset of pixels. The statistical model is trained based on the set of training patches and the corresponding set of patch annotations. The trained statistical model is stored on at least one storage device.Type: GrantFiled: June 6, 2018Date of Patent: May 12, 2020Assignee: PathAI, Inc.Inventors: Andrew H. Beck, Aditya Khosla
-
Publication number: 20190095406Abstract: The invention provides enhancements for the use of favorites during a Web browsing session. A first enhancement identifies when a user is adding a favorite to his favorites list and auto-suggests a category under which the favorite could be stored. A second enhancement allows a user to review his favorites list and see a summary of feed content (RSS or other standard) on each feed enabled page on his favorites list, without requiring the user to link to the page in question. A third enhancement allows the user to view an manipulate the feed in an independent display window.Type: ApplicationFiled: November 21, 2018Publication date: March 28, 2019Inventors: Timothy O'SHAUGHNESSY, Aditya Khosla, Brock Laporte, Alberto Cobas, Colin Chang
-
Patent number: 10169306Abstract: The invention provides enhancements for the use of favorites during a Web browsing session. A first enhancement identifies when a user is adding a favorite to his favorites list and auto-suggests a category under which the favorite could be stored. A second enhancement allows a user to review his favorites list and see a summary of feed content (RSS or other standard) on each feed enabled page on his favorites list, without requiring the user to link to the page in question. A third enhancement allows the user to view an manipulate the feed in an independent display window.Type: GrantFiled: February 9, 2016Date of Patent: January 1, 2019Assignee: Oath Inc.Inventors: Timothy John O'Shaughnessy, Aditya Khosla, Brock Laporte, Alberto Cobas, Colin Chang
-
Patent number: 9846902Abstract: Product order and shipping information received via email messages is automatically aggregated for ready user review. Once the user is authenticated, authorization to access their email mailbox is obtained and the email message headers of their entails are analyzed to identify those messages of interest. The bodies of the email messages of interest are parsed to extract the product order and shipping information which is stored and presented for display to the user typically grouped by individual product thus greatly simplifying user review of orders. The aggregated product order and shipping information can be augmented with additional information such as shipping status, delivery status, a product image, and/or a last date that the product can be returned.Type: GrantFiled: January 12, 2012Date of Patent: December 19, 2017Assignee: Slice Technologies, Inc.Inventors: Scott J. Brady, Benjamin A. Suppe, Eric J. Botto, Harpinder Singh Madan, Ievgen Mastierov, Aditya Khosla, Dmytry B. Mykhaylov, Georgii Verbytskyi, Alexander Lototsky, Michael Mantel
-
Patent number: 9754042Abstract: The invention provides two enhancements for the use of favorites during a Web browsing session. A first enhancement identifies when a user is adding a favorite to his favorites list and auto-suggests a category under which the favorite could be stored. A second enhancement allows a user to review his favorites list and see a summary of feed content (RSS or other standard) on each feed enabled page on his favorites list, without requiring the user to link to the page in question.Type: GrantFiled: May 20, 2014Date of Patent: September 5, 2017Assignee: Oath Inc.Inventors: Aditya Khosla, Brock Laporte, Alberto Cobas, Colin Chang, Joseph Van Valen
-
Publication number: 20170147979Abstract: Product order and shipping information received via email messages is automatically aggregated for ready user review. Once the user is authenticated, authorization to access their email mailbox is obtained and the email message headers of their entails are analyzed to identify those messages of interest. The bodies of the email messages of interest are parsed to extract the product order and shipping information which is stored and presented for display to the user typically grouped by individual product thus greatly simplifying user review of orders. The aggregated product order and shipping information can be augmented with additional information such as shipping status, delivery status, a product image, and/or a last date that the product can be returned.Type: ApplicationFiled: January 31, 2017Publication date: May 25, 2017Applicant: Slice Technologies, Inc,Inventors: Scott J. Brady, Benjamin A. Suppe, Eric J. Botto, Harpinder Singh Madan, Ievgen Mastierov, Aditya Khosla, Dmytro B. Mykhaylov, Georgii Verbytskyi, Alexander Lototsky, Michael Mantel
-
Patent number: 9641474Abstract: Product order and shipping information received via email messages is automatically aggregated for ready user review. Once the user is authenticated, authorization to access their email mailbox is obtained and the email message headers of their emails are analyzed to identify those messages of interest. The bodies of the email messages of interest are parsed to extract the product order and shipping information which is stored and presented for display to the user typically grouped by individual product thus greatly simplifying user review of orders.Type: GrantFiled: August 12, 2014Date of Patent: May 2, 2017Assignee: Slice Technologies, Inc.Inventors: Scott J. Brady, Benjamin A. Suppe, Eric J. Botto, Harpinder Singh Madan, Ievgen Mastierov, Aditya Khosla, Dmytry B. Mykhaylov, Georgii Verbytskyi
-
Patent number: 9563915Abstract: Product order and shipping information received via email messages is automatically aggregated for ready user review. Once the user is authenticated, authorization to access their email mailbox is obtained and the email message headers of their entails are analyzed to identify those messages of interest. The bodies of the email messages of interest are parsed to extract the product order and shipping information which is stored and presented for display to the user typically grouped by individual product thus greatly simplifying user review of orders. The aggregated product order and shipping information can be augmented with additional information such as shipping status, delivery status, a product image, and/or a last date that the product can be returned.Type: GrantFiled: April 13, 2015Date of Patent: February 7, 2017Assignee: Slice Technologies, Inc.Inventors: Scott J. Brady, Benjamin A. Suppe, Eric J. Botto, Harpinder Singh Madan, Ievgen Mastierov, Aditya Khosla, Dmytry B. Mykhaylov, Georgii Verbytskyi, Alexander Lototsky, Michael Mantel
-
Patent number: 9508054Abstract: Product order and shipping information received via email messages is automatically aggregated for ready user review. Once the user is authenticated, authorization to access their email mailbox is obtained and the email message headers of their emails are analyzed to identify those messages of interest. The bodies of the email messages of interest are parsed to extract the product order and shipping information which is stored and presented for display to the user typically grouped by individual product thus greatly simplifying user review of orders. The aggregated product order and shipping information can be augmented with additional information such as shipping status, delivery status, a product image, and/or a last date that the product can be returned.Type: GrantFiled: April 13, 2015Date of Patent: November 29, 2016Assignee: Slice Technologies, Inc.Inventors: Scott J. Brady, Benjamin A. Suppe, Eric J. Botto, Harpinder Singh Madan, Ievgen Mastierov, Aditya Khosla, Dmytry B. Mykhaylov, Georgii Verbytskyi, Alexander Lototsky, Michael Mantel
-
Publication number: 20160154773Abstract: The invention provides enhancements for the use of favorites during a Web browsing session. A first enhancement identifies when a user is adding a favorite to his favorites list and auto-suggests a category under which the favorite could be stored. A second enhancement allows a user to review his favorites list and see a summary of feed content (RSS or other standard) on each feed enabled page on his favorites list, without requiring the user to link to the page in question. A third enhancement allows the user to view an manipulate the feed in an independent display window.Type: ApplicationFiled: February 9, 2016Publication date: June 2, 2016Inventors: Timothy John O'Shaughnessy, Aditya Khosla, Brock Laporte, Alberto Cobas, Colin Chang