Unsupervised segmentation and quantification of COVID-19 lesions on computed Tomography scans using CycleGAN

Marc Connell,Yi Xin,Sarah E. Gerard,Jacob Herrmann,Parth K. Shah, Kevin T. Martin,Emanuele Rezoagli, Davide Ippolito, Jennia Rajaei,Ryan Baron, Paolo Delvecchio, Shiraz Humayun,Rahim R. Rizi,Giacomo Bellani,Maurizio Cereda

Methods（2022）

引用 1|浏览27

暂无评分

摘要

•We trained a modified CycleGAN to segment pulmonary lesions on COVID-19 CT scans.•Our unsupervised model performed similarly to weakly supervised models. Our model preserved normal physiology in generated images.

查看译文

关键词

CycleGAN,COVID-19,CT,Lesion segmentation

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要