Training workflows for the PSN framework.

(a) PSNadaptive: the model is fine-tuned on cumulatively increasing fractions and tested on subsequent ones. (b) PSNsequence: the model is sequentially fine-tuned using the previously trained weights for each next fraction. DLg</su...

Full description

Saved in:

Bibliographic Details
Main Author:	Joonil Hwang (22278797) (author)
Other Authors:	Byung-Hee Kang (13264776) (author), Younghee Park (1430620) (author), Dong Hyeok Choi (12562048) (author), Jin Sung Kim (679262) (author), Seungryong Cho (4857196) (author), Eungman Lee (11219256) (author)
Published:	2025
Subjects:	Cell Biology Genetics Molecular Biology Biotechnology Cancer Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified swin unetr architecture streamlining workflow efficiency static personalization methods percentile hausdorff distance mean surface distance ethos therapy system dice similarity coefficient daily anatomical variations daily anatomical changes clinical target volume beam computed tomography anatomically complex regions 743 &# 8201 035 &# 8201 segmentation using cone efficient auto segmentation tuning via psn th </ sup div >< p psn framework uses improving segmentation precision dsc ), 95 psn framework specific segmentation segmentation performance training followed stage strategy specific network specific fine potentially reducing physician contours manual editing manual corrections initial pre hd ), findings support fifth fraction deformable registration continuously adapts clinically feasible adaptive radiotherapy
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!

Training workflows for the PSN framework.

Similar Items