US 12,322,151 B2
DA-BD-LSTM-dense-UNet for liver lesion segmentation
Philip Leung Ho Yu, Hong Kong (HK); Keith Chiu, Hong Kong (HK); Man Fung Yuen, Hong Kong (HK); and Wai Kay Walter Seto, Hong Kong (HK)
Assigned to THE UNIVERSITY OF HONG KONG, Hong Kong (HK)
Appl. No. 17/916,589
Filed by THE UNIVERSITY OF HONG KONG, Hong Kong (HK)
PCT Filed Mar. 23, 2021, PCT No. PCT/CN2021/082361
§ 371(c)(1), (2) Date Oct. 3, 2022,
PCT Pub. No. WO2021/197135, PCT Pub. Date Oct. 7, 2021.
Claims priority of provisional application 63/004,563, filed on Apr. 3, 2020.
Prior Publication US 2023/0154141 A1, May 18, 2023
Int. Cl. G06V 10/40 (2022.01); G06V 10/44 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/454 (2022.01) [G06V 10/82 (2022.01); G06V 2201/031 (2022.01)] 24 Claims
OG exemplary drawing
 
1. A liver cancer analysis system, comprising:
a memory that stores computer executable components; and
a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise:
a learning component that learns a plurality of diverse features of a liver sample for uploading and calculates relationships between encoded features and upsampled features in encoding and decoding paths;
a response filter component that diminishes responses of unrelated background regions and magnify responses of salient regions progressively; and
a weighting component that determines relative contributions of the encoded features and the upsampled features.