公开(公告)号：US20220384042A1

公开(公告)日：2022-12-01

申请号：US17775139

申请日：2020-10-13

Applicant: Google LLC

Inventor： Andrew Beckmann Sellergren ,  Shravya Ramash Shetty ,  Siddhant Mittal ,  David Francis Steiner ,  Anna Majkowska ,  Gavin Elliott Duggan

IPC: G16H50/20 ,  G16H30/20

Abstract: The present disclosure provides systems and methods for training and/or employing machine-learned models (e.g., artificial neural networks) to diagnose chest conditions such as, as examples, pneumothorax, opacity, nodules or masses, and/or fractures based on chest radiographs. For example, one or more machine-learned models can receive and process a chest radiograph to generate an output. The output can indicate, for each of one or more chest conditions, whether the chest radiograph depicts the chest conditions (e.g., with some measure of confidence). The output of the machine-learned models can be provided to a medical professional and/or patient for use in providing treatment to the patient (e.g., to treat a detected condition).

公开(公告)号：US20230169652A1

公开(公告)日：2023-06-01

申请号：US18011888

申请日：2022-05-12

Applicant: Google LLC

Inventor： Sahar Kazemzadeh ,  Dong Jin Yu ,  Shahar Jamshy ,  Rory Pilgrim ,  Zaid Isam Nabulsi ,  Andrew Beckmann Sellergren ,  Yun Liu ,  Shruthi Prabhakara ,  Atilla Peter Kiraly

IPC: G06T7/00 ,  G06N3/0464 ,  G06N3/084 ,  G16H10/60 ,  G16H30/40 ,  G16H50/20 ,  G16H50/30 ,  G06T7/11 ,  A61B6/00

CPC classification number: G06T7/0012 ,  G06N3/0464 ,  G06N3/084 ,  G16H10/60 ,  G16H30/40 ,  G16H50/20 ,  G16H50/30 ,  G06T7/11 ,  A61B6/50 ,  G06T2207/10116 ,  G06T2207/30061 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Systems and methods for chest condition determination can leverage one or more machine-learned models to process radiograph data to determine risk data (e.g., a preliminary diagnosis). For example, systems and methods can utilize a pathology model to process a chest x-ray to generate a tuberculosis diagnosis. The one or more machine-learned models can segment the lungs, can detect features in the data, and can pool the segmentation and located features to determine the diagnosis.