公开(公告)号：US20220230310A1

公开(公告)日：2022-07-21

申请号：US17665932

申请日：2022-02-07

Applicant: Genentech, Inc.

Inventor： Luke XIE ,  Kai Henrik BARCK ,  Omid BAZGIR

IPC: G06T7/00 ,  G06V10/764 ,  G06T7/70 ,  G06T7/10 ,  G06T7/62 ,  G06V10/75 ,  G06V20/64

Abstract: The present disclosure relates to techniques for segmenting objects within medical images using a deep learning network that is localized with object detection based on a derived contrast mechanism. Particularly, aspects are directed to localizing an object of interest within a first medical image having a first characteristic, projecting a bounding box or segmentation mask of the object of interest onto a second medical image having a second characteristic to define a portion of the second medical image, and inputting the portion of the second medical image into a deep learning model that is constructed as a detector using a weighted loss function capable of segmenting the portion of the second medical image and generating a segmentation boundary around the object of interest. The segmentation boundary may be used to calculate a volume of the object of interest for determining a diagnosis and/or a prognosis of a subject.

公开(公告)号：US20240221162A1

公开(公告)日：2024-07-04

申请号：US18610181

申请日：2024-03-19

Applicant: Genentech, Inc.

Inventor： Luke XIE ,  Kai Henrick Barck ,  Omid Bazgir

IPC: G06T7/00 ,  G06T7/10 ,  G06T7/62 ,  G06T7/70 ,  G06V10/75 ,  G06V10/764 ,  G06V20/64

CPC classification number: G06T7/0012 ,  G06T7/10 ,  G06T7/62 ,  G06T7/70 ,  G06V10/758 ,  G06V10/764 ,  G06V20/64 ,  G06T2200/04 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: The present disclosure relates to techniques for segmenting objects within medical images using a deep learning network that is localized with object detection based on a derived contrast mechanism. Particularly, aspects are directed to localizing an object of interest within a first medical image having a first characteristic, projecting a bounding box or segmentation mask of the object of interest onto a second medical image having a second characteristic to define a portion of the second medical image, and inputting the portion of the second medical image into a deep learning model that is constructed as a detector using a weighted loss function capable of segmenting the portion of the second medical image and generating a segmentation boundary around the object of interest. The segmentation boundary may be used to calculate a volume of the object of interest for determining a diagnosis and/or a prognosis of a subject.