公开(公告)号：US11875898B2

公开(公告)日：2024-01-16

申请号：US17331251

申请日：2021-05-26

申请人： MERATIVE US L.P.

发明人： Luyao Shi ,  David James Beymer ,  Ehsan Dehghan Marvast ,  Deepta Rajan

IPC分类号： G06T7/00 ,  G16H50/20 ,  G16H30/40 ,  G06F18/21

CPC分类号： G16H50/20 ,  G06F18/217 ,  G06T7/0014 ,  G16H30/40 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30061 ,  G06T2207/30101

摘要： Methods and systems for training computer-aided condition detection systems. One method includes receiving a plurality of images for a plurality of patients, some of the images including an annotation associated with a condition; iteratively applying a first deep learning network to each of the images to produce an attention map, a feature map, and an image-level probability of the condition for each of the images; iteratively applying a second deep learning network to each feature map produced by the first network to produce a plurality of outputs; training the first network based on the attention map produced for each image; and training the second network based on the output produced for each of the patients. The second network includes a plurality of convolution layers and a plurality of convolutional long short-term memory (LSTM) layers. Each of the outputs includes a patient-level probability of the condition for one of the patients.

公开(公告)号：US11967067B2

公开(公告)日：2024-04-23

申请号：US17319606

申请日：2021-05-13

申请人： Merative US L.P.

发明人： Shafiqul Abedin ,  Hongzhi Wang ,  Ehsan Dehghan Marvast ,  David James Beymer

IPC分类号： G06T7/00 ,  G06F18/2433 ,  G06N3/045 ,  G06N3/08 ,  G06T7/11 ,  G06V10/34 ,  G16H30/20 ,  G16H30/40 ,  G16H50/20

CPC分类号： G06T7/0012 ,  G06F18/2433 ,  G06N3/045 ,  G06N3/08 ,  G06T7/11 ,  G06V10/34 ,  G16H30/20 ,  G16H30/40 ,  G16H50/20 ,  G06T2207/20081 ,  G06T2207/20084

摘要： A candidate generator generates a set of candidate three-dimensional image patches from an input volume. A candidate classifier classifies the set of candidate three-dimensional image patches as containing or not containing disease. Classifying the set of candidate three-dimensional image patches comprises generating an attention mask for each given candidate three-dimensional image patch within the set of candidate three-dimensional image patches to form a set of attention masks, applying the set of attention masks to the set of candidate three-dimensional image patches to form a set of masked image patches, and classifying the set of masked image patches as containing or not containing the disease. The candidate classifier applies soft attention and hard attention to the three-dimensional image patches such that distinctive image regions are highlighted proportionally to their contribution to classification while completely removing image regions that may cause confusion.