US 11,810,312 B2
Multiple instance learning method
Sang Hyun Park, Daegu (KR); and Philip Chikontwe, Daegu (KR)
Assigned to DAEGU GYEONGBUK INSTITUTE OF SCIENCE AND TECHNOLOGY, Daegu (KR)
Filed by DAEGU GYEONGBUK INSTITUTE OF SCIENCE AND TECHNOLOGY, Daegu (KR)
Filed on Apr. 21, 2021, as Appl. No. 17/236,191.
Claims priority of application No. 10-2020-0047888 (KR), filed on Apr. 21, 2020; and application No. 10-2021-0051331 (KR), filed on Apr. 20, 2021.
Prior Publication US 2021/0334994 A1, Oct. 28, 2021
Int. Cl. G06T 7/593 (2017.01); G06N 20/00 (2019.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01)
CPC G06T 7/593 (2017.01) [G06N 20/00 (2019.01); G06T 2207/10081 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30061 (2013.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01)] 17 Claims
OG exemplary drawing
 
1. A multiple instance learning device for analyzing 3D images, comprising:
a memory in which a multiple instance learning model is stored; and
at least one processor electrically connected to the memory,
wherein the multiple instance learning model comprises:
a convolution block configured to derive a feature map for each of 2D instances of a 3D image inputted to the multiple instance learning model;
a spatial attention block configured to derive spatial attention maps of the instances from the feature maps derived from the convolution block;
an instance attention block configured to receive a result of combining the feature maps and the spatial attention maps and derive an attention score for each instance, and derive an aggregated embedding for the 3D image by aggregating embeddings of the instances according to the attention scores; and
an output block configured to output an analysis result for the 3D image based on the aggregated embedding.