Lung adenocarcinoma (ADC) with micropapillary pattern have been reported to have a poor prognosis. However, few studies have reported on the imaging-based identification of micropapillary component, which were all subjective studies dealing with qualitative CT variables. We aimed to explore imaging phenotyping using a radiomics approach for predicting micropapillary pattern within lung ADC METHODS: We enrolled 339 patients who underwent complete resection for lung ADC. Histologic subtypes and grades of the ADCs were classified. The amount of the micropapillary component was determined. Clinical features and conventional imaging variables such as tumor disappearance ratio (TDR) and maximum standardized uptake value (SUVmax) on PET were assessed. Quantitative CT analysis was performed based on histogram, size and shape, gray-level co-occurrence matrix-based, and intensity variance and size zone variance-based features.Higher tumor stage (Odds ratio[OR] 3.270; 95
作者:So Hee, Song;Hyunjin, Park;Geewon, Lee;Ho Yun, Lee;Insuk, Sohn;Hye Seung, Kim;Seung Hak, Lee;Ji Yun, Jeong;Jhingook, Kim;Kyung Soo, Lee;Young Mog, Shim
来源:Journal of thoracic oncology : official publication of the International Association for the Study of Lung Cancer 2016 年