Patents by Inventor Lily Hao Yi Peng

Lily Hao Yi Peng 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: 11894125
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a fundus image processing machine learning models that is configured to process one or more fundus images captured by a fundus camera to generate a predicted label. One of the methods includes generating training data, comprising: receiving sets of one or more training fundus images captured by a fundus camera; receiving, for each of the sets, a ground truth label assigned to a different image of the eye of the patient corresponding to the set that has been captured using a different imaging modality; and generating, for each set of training fundus images, a training example that includes the set of training fundus images in association with the ground truth label assigned to the different image of the patients eye; and training the machine learning model on the training examples in the training data.
    Type: Grant
    Filed: October 17, 2018
    Date of Patent: February 6, 2024
    Assignee: Google LLC
    Inventors: Lily Hao Yi Peng, Dale R. Webster, Avinash Vaidyanathan Varadarajan, Pinal Bavishi
  • Publication number: 20230386652
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing one or more utterances; processing the input acoustic sequence using a speech recognition model to generate a transcription of the input acoustic sequence, wherein the speech recognition model comprises a domain-specific language model; and providing the generated transcription of the input acoustic sequence as input to a domain-specific predictive model to generate structured text content that is derived from the transcription of the input acoustic sequence.
    Type: Application
    Filed: August 15, 2023
    Publication date: November 30, 2023
    Inventors: Christopher S. Co, Navdeep Jaitly, Lily Hao Yi Peng, Katherine Irene Chou, Ananth Sankar
  • Patent number: 11823385
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing fundus images using fundus image processing machine learning models.
    Type: Grant
    Filed: June 13, 2022
    Date of Patent: November 21, 2023
    Assignee: Google LLC
    Inventors: Christopher Semturs, Dale R. Webster, Avinash Vaidyanathan Varadarajan, Akinori Mitani, Lily Hao Yi Peng
  • Patent number: 11763936
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing one or more utterances; processing the input acoustic sequence using a speech recognition model to generate a transcription of the input acoustic sequence, wherein the speech recognition model comprises a domain-specific language model; and providing the generated transcription of the input acoustic sequence as input to a domain-specific predictive model to generate structured text content that is derived from the transcription of the input acoustic sequence.
    Type: Grant
    Filed: December 4, 2020
    Date of Patent: September 19, 2023
    Assignee: Google LLC
    Inventors: Christopher S. Co, Navdeep Jaitly, Lily Hao Yi Peng, Katherine Irene Chou, Ananth Sankar
  • Publication number: 20230260126
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing fundus images using fundus image processing machine learning models. One of the methods includes obtaining a model input comprising one or more fundus images, each fundus image being an image of a fundus of an eye of a patient; processing the model input using a fundus image processing machine learning model, wherein the fundus image processing machine learning model is configured to process the model input comprising the one or more fundus image to generate a model output; and processing the model output to generate health analysis data.
    Type: Application
    Filed: April 24, 2023
    Publication date: August 17, 2023
    Inventors: Lily Hao Yi Peng, Dale R. Webster, Philip Charles Nelson, Varun Gulshan, Marc Adlai Coram, Martin Christian Stumpe, Derek Janme Wu, Arunachalam Narayanaswamy, Avinash Vaidyanathan Varadarajan, Katharine Blumer, Yun Liu, Ryan Poplin
  • Patent number: 11636601
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing fundus images using fundus image processing machine learning models. One of the methods includes obtaining a model input comprising one or more fundus images, each fundus image being an image of a fundus of an eye of a patient; processing the model input using a fundus image processing machine learning model, wherein the fundus image processing machine learning model is configured to process the model input comprising the one or more fundus image to generate a model output; and processing the model output to generate health analysis data.
    Type: Grant
    Filed: March 25, 2021
    Date of Patent: April 25, 2023
    Assignee: Google LLC
    Inventors: Lily Hao Yi Peng, Dale R. Webster, Philip Charles Nelson, Varun Gulshan, Marc Adlai Coram, Martin Christian Stumpe, Derek Janme Wu, Arunachalam Narayanaswamy, Avinash Vaidyanathan Varadarajan, Katharine Blumer, Yun Liu, Ryan Poplin
  • Publication number: 20220309665
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing fundus images using fundus image processing machine learning models.
    Type: Application
    Filed: June 13, 2022
    Publication date: September 29, 2022
    Inventors: Christopher Semturs, Dale R. Webster, Avinash Vaidyanathan Varadarajan, Akinori Mitani, Lily Hao Yi Peng
  • Patent number: 11361435
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing fundus images using fundus image processing machine learning models.
    Type: Grant
    Filed: March 30, 2020
    Date of Patent: June 14, 2022
    Assignee: Google LLC
    Inventors: Christopher Semturs, Dale R. Webster, Avinash Vaidyanathan Varadarajan, Akinori Mitani, Lily Hao Yi Peng
  • Publication number: 20210357696
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a fundus image processing machine learning models that is configured to process one or more fundus images captured by a fundus camera to generate a predicted label. One of the methods includes generating training data, comprising: receiving sets of one or more training fundus images captured by a fundus camera; receiving, for each of the sets, a ground truth label assigned to a different image of the eye of the patient corresponding to the set that has been captured using a different imaging modality; and generating, for each set of training fundus images, a training example that includes the set of training fundus images in association with the ground truth label assigned to the different image of the patients eye; and training the machine learning model on the training examples in the training data.
    Type: Application
    Filed: October 17, 2018
    Publication date: November 18, 2021
    Inventors: Lily Hao Yi Peng, Dale R. Webster, Avinash Vaidyanathan Varadarajan, Pinal Bavishi
  • Publication number: 20210209762
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing fundus images using fundus image processing machine learning models. One of the methods includes obtaining a model input comprising one or more fundus images, each fundus image being an image of a fundus of an eye of a patient; processing the model input using a fundus image processing machine learning model, wherein the fundus image processing machine learning model is configured to process the model input comprising the one or more fundus image to generate a model output; and processing the model output to generate health analysis data.
    Type: Application
    Filed: March 25, 2021
    Publication date: July 8, 2021
    Inventors: Lily Hao Yi Peng, Dale R. Webster, Philip Charles Nelson, Varun Gulshan, Marc Adlai Coram, Martin Christian Stumpe, Derek Janme Wu, Arunachalam Narayanaswamy, Avinash Vaidyanathan Varadarajan, Katharine Blumer, Yun Liu, Ryan Poplin
  • Patent number: 10970841
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing fundus images using fundus image processing machine learning models. One of the methods includes obtaining a model input comprising one or more fundus images, each fundus image being an image of a fundus of an eye of a patient; processing the model input using a fundus image processing machine learning model, wherein the fundus image processing machine learning model is configured to process the model input comprising the one or more fundus image to generate a model output; and processing the model output to generate health analysis data.
    Type: Grant
    Filed: August 18, 2017
    Date of Patent: April 6, 2021
    Assignee: Google LLC
    Inventors: Lily Hao Yi Peng, Dale R. Webster, Philip Charles Nelson, Varun Gulshan, Marc Adlai Coram, Martin Christian Stumpe, Derek Janme Wu, Arunachalam Narayanaswamy, Avinash Vaidyanathan Varadarajan, Katharine Blumer, Yun Liu, Ryan Poplin
  • Publication number: 20210090724
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing one or more utterances; processing the input acoustic sequence using a speech recognition model to generate a transcription of the input acoustic sequence, wherein the speech recognition model comprises a domain-specific language model; and providing the generated transcription of the input acoustic sequence as input to a domain-specific predictive model to generate structured text content that is derived from the transcription of the input acoustic sequence.
    Type: Application
    Filed: December 4, 2020
    Publication date: March 25, 2021
    Inventors: Christopher S. Co, Navdeep Jaitly, Lily Hao Yi Peng, Katherine Irene Chou, Ananth Sankar
  • Patent number: 10860685
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing one or more utterances; processing the input acoustic sequence using a speech recognition model to generate a transcription of the input acoustic sequence, wherein the speech recognition model comprises a domain-specific language model; and providing the generated transcription of the input acoustic sequence as input to a domain-specific predictive model to generate structured text content that is derived from the transcription of the input acoustic sequence.
    Type: Grant
    Filed: November 28, 2016
    Date of Patent: December 8, 2020
    Assignee: Google LLC
    Inventors: Christopher S. Co, Navdeep Jaitly, Lily Hao Yi Peng, Katherine Irene Chou, Ananth Sankar
  • Publication number: 20200311933
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing fundus images using fundus image processing machine learning models.
    Type: Application
    Filed: March 30, 2020
    Publication date: October 1, 2020
    Inventors: Christopher Semturs, Dale R. Webster, Avinash Vaidyanathan Varadarajan, Akinori Mitani, Lily Hao Yi Peng
  • Publication number: 20190180441
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing fundus images using fundus image processing machine learning models. One of the methods includes obtaining a model input comprising one or more fundus images, each fundus image being an image of a fundus of an eye of a patient; processing the model input using a fundus image processing machine learning model, wherein the fundus image processing machine learning model is configured to process the model input comprising the one or more fundus image to generate a model output; and processing the model output to generate health analysis data.
    Type: Application
    Filed: August 18, 2017
    Publication date: June 13, 2019
    Inventors: Lily Hao Yi Peng, Dale R. Webster, Philip Charles Nelson, Varun Gulshan, Marc Adlai Coram, Martin Christian Stumpe, Derek Janme Wu, Arunachalam Narayanaswamy, Avinash Vaidyanathan Varadarajan, Katharine Blumer, Yun Liu, Ryan Poplin
  • Publication number: 20180150605
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing one or more utterances; processing the input acoustic sequence using a speech recognition model to generate a transcription of the input acoustic sequence, wherein the speech recognition model comprises a domain-specific language model; and providing the generated transcription of the input acoustic sequence as input to a domain-specific predictive model to generate structured text content that is derived from the transcription of the input acoustic sequence.
    Type: Application
    Filed: November 28, 2016
    Publication date: May 31, 2018
    Inventors: Christopher S. Co, Navdeep Jaitly, Lily Hao Yi Peng, Katherine Irene Chou, Ananth Sankar