公开(公告)号：US10939874B2

公开(公告)日：2021-03-09

申请号：US16104131

申请日：2018-08-16

Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA

Inventor： Kyung Hyun Sung ,  William Hsu ,  Shiwen Shen ,  Xinran Zhong

IPC: A61B5/00 ,  A61B5/055 ,  G06T7/00 ,  G06K9/42 ,  G06K9/52 ,  G06K9/62 ,  G06K9/66 ,  A61B5/20 ,  A61B5/08

Abstract: An automatic classification method for distinguishing between indolent and clinically significant carcinoma using multiparametric MRI (mp-MRI) imaging is provided. By utilizing a convolutional neural network (CNN), which automatically extracts deep features, the hierarchical classification framework avoids deficiencies in current schemes in the art such as the need to provide handcrafted features predefined by a domain expert and the precise delineation of lesion boundaries by a human or computerized algorithm. This hierarchical classification framework is trained using previously acquired mp-MRI data with known cancer classification characteristics and the framework is applied to mp-MRI images of new patients to provide identification and computerized cancer classification results of a suspicious lesion.

公开(公告)号：US20190183429A1

公开(公告)日：2019-06-20

申请号：US16104131

申请日：2018-08-16

Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA

Inventor： Kyung Hyun Sung ,  William Hsu ,  Shiwen Shen ,  Xinran Zhong

IPC: A61B5/00 ,  A61B5/055 ,  G06K9/42 ,  G06K9/52 ,  G06K9/62 ,  G06K9/66

CPC classification number: A61B5/7267 ,  A61B5/055 ,  A61B5/08 ,  A61B5/201 ,  A61B5/4244 ,  A61B5/4381 ,  G06K9/42 ,  G06K9/527 ,  G06K9/6269 ,  G06K9/66

Abstract: An automatic classification method for distinguishing between indolent and clinically significant carcinoma using multiparametric MRI (mp-MRI) imaging is provided. By utilizing a convolutional neural network (CNN), which automatically extracts deep features, the hierarchical classification framework avoids deficiencies in current schemes in the art such as the need to provide handcrafted features predefined by a domain expert and the precise delineation of lesion boundaries by a human or computerized algorithm. This hierarchical classification framework is trained using previously acquired mp-MRI data with known cancer classification characteristics and the framework is applied to mp-MRI images of new patients to provide identification and computerized cancer classification results of a suspicious lesion.