公开(公告)号：US20240339217A1

公开(公告)日：2024-10-10

申请号：US18620434

申请日：2024-03-28

Applicant: Google LLC

Inventor： Peggy Yen Phuong Bui ,  Bianca Madalina Buisman ,  Quang Anh Duong ,  Anastasia Martynova ,  Ayush Jain ,  Yuan Liu ,  Jonathan David Krause ,  Amit Sanjay Talreja ,  Rajeev Vijay Rikhye ,  Mahvish A. Nagda ,  Pinal Bavishi ,  Christopher James Eicher ,  Abigail Ward ,  Jieming Yu ,  Louis Wang ,  Dounia Berrada ,  Dale Richard Webster ,  Harshit Kharbanda ,  Igor Bonaci ,  Kai Yu ,  Ke Lan ,  Kaan Yücer ,  Willa Angel Chen Miller ,  Lars Thomas Hansen

IPC: G16H50/20 ,  G06T7/00 ,  G16H30/40

CPC classification number: G16H50/20 ,  G06T7/0012 ,  G16H30/40 ,  G06T2207/20104 ,  G06T2207/30088

Abstract: Systems and methods for diagnostic visual search can include processing a search query with a plurality of classification models to determine a search query intent and predict potential diagnosis. The search query can include an image that is processed to determine the presence of a body part and may be processed to determine if the search query is descriptive of a diagnostic search query. Based on the intent determination, the image may then be processed by a conditions classification model to determine one or more predicted condition classifications. Condition information can then be obtained and provided based on the one or more predicted condition classifications.

公开(公告)号：US11894125B2

公开(公告)日：2024-02-06

申请号：US17286392

申请日：2018-10-17

Applicant: GOOGLE LLC

Inventor： Lily Hao Yi Peng ,  Dale R. Webster ,  Avinash Vaidyanathan Varadarajan ,  Pinal Bavishi

IPC: G16H30/40 ,  G16H50/20 ,  G06T7/00 ,  G06F18/214

CPC classification number: G16H30/40 ,  G06F18/2148 ,  G06T7/0012 ,  G16H50/20 ,  G06T2200/04 ,  G06T2207/10101 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30041

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.

公开(公告)号：US20210357696A1

公开(公告)日：2021-11-18

申请号：US17286392

申请日：2018-10-17

Applicant: GOOGLE LLC

Inventor： Lily Hao Yi Peng ,  Dale R. Webster ,  Avinash Vaidyanathan Varadarajan ,  Pinal Bavishi

IPC: G06K9/62 ,  G06T7/00 ,  G16H50/20 ,  G16H30/40

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.