公开(公告)号：US11810299B1

公开(公告)日：2023-11-07

申请号：US18351699

申请日：2023-07-13

Applicant: MEDIAN TECHNOLOGIES

Inventor： Benoît Huet ,  Danny Francis ,  Pierre Baudot

IPC: G06T7/00 ,  G06V10/25 ,  G06V10/26 ,  G06V10/774 ,  G06V10/82 ,  G06T7/73 ,  G06V10/32 ,  G06V10/776 ,  G16H50/20

CPC classification number: G06T7/0012 ,  G06T7/73 ,  G06V10/25 ,  G06V10/26 ,  G06V10/32 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G16H50/20 ,  G06T2200/04 ,  G06T2207/10081 ,  G06T2207/10088 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30096 ,  G06V2201/03

Abstract: A method for generating a machine learning model for characterizing a plurality of Regions Of Interest ROIs based on a plurality of 3D medical images and an associated method for characterizing a Region Of Interest ROI based on at least one 3D medical image. The methods proposed here aim to provide complementary strategies to enable a classification of ROIs from 3D medical images which could take profit of the advantageous and complementarity of both 2D and 3D CNNs to improve the accuracy of the prediction. More precisely, the present disclosure proposes a 2D model that complements the 3D model so that the sensitivity/specificity of the diagnosis is improved by taking advantage of complementary notions.