Results of liver segmentation task LiTS → Synapse

<div><p>In unsupervised transfer learning for medical image segmentation, where existing algorithms face the challenge of error propagation due to inaccessible source domain data. In response to this scenario, source-free domain transfer algorithm with reduced style sensitivity (SFDT-RSS...

Full description

Saved in:

Bibliographic Details
Main Author:	Jian Lin (323268) (author)
Other Authors:	Xiaomin Yu (39962) (author), Zhengxian Wang (5690084) (author), Chaoqiong Ma (306091) (author)
Published:	2024
Subjects:	Microbiology Genetics Evolutionary Biology Science Policy Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified proposed algorithm utilizes medical image segmentation global perception ability error propagation due domain transfer phase single image style unsupervised transfer learning reduced style sensitivity 64 %, 3 21 %, 3 existing algorithms face 83 %, 2 source domain model rss initially pre style sensitivity existing algorithms 01 %, unsupervised cross xlink "> transformer architecture trained model subsequently adapts source model reducing reliance generalization capability experimental results
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!

Results of liver segmentation task LiTS → Synapse

Similar Items