Solid Attenuation Components Attention Deep Learning Model to Predict Micropapillary and Solid Patterns in Lung Adenocarcinomas on Computed Tomography

Chen, Li-WeiLi-WeiChenSHUN-MAO YANGChuang, Ching-ChiaChing-ChiaChuangWang, Hao-JenHao-JenWangChen, Yi-ChangYi-ChangChenMONG-WEI LINMIN-SHU HSIEHAntonoff, Mara BMara BAntonoffYEUN-CHUNG CHANGWu, Carol CCarol CWuPan, TinsuTinsuPanCHUNG-MING CHEN2022-11-082022-11-082022-111068-9265https://scholars.lib.ntu.edu.tw/handle/123456789/624509High-grade adenocarcinoma subtypes (micropapillary and solid) treated with sublobar resection have an unfavorable prognosis compared with those treated with lobectomy. We investigated the potential of incorporating solid attenuation component masks with deep learning in the prediction of high-grade components to optimize surgical strategy preoperatively.enINTERNATIONAL-ASSOCIATION; IASLC/ATS/ERS CLASSIFICATION; PROGNOSTIC IMPACT; TUMOR RECURRENCE; CT; SUBTYPE; RESECTION; SURVIVAL; SIZE[SDGs]SDG3Solid Attenuation Components Attention Deep Learning Model to Predict Micropapillary and Solid Patterns in Lung Adenocarcinomas on Computed Tomographyjournal article10.1245/s10434-022-12055-5357893012-s2.0-85133468768WOS:000822007500003https://scholars.lib.ntu.edu.tw/handle/123456789/624094