Prediction of solid and micropapillary components in lung invasive adenocarcinoma: radiomics analysis from high-spatial-resolution CT data with 1024 matrix

• DOI: 10.1007/s11604-024-01534-2
• Publication Date: 2024-02-28T03:02:27Z
• Authors: Keisuke Ninomiya; Masahiro Yanagawa; Mitsuko Tsubamoto; Yukihisa Sato; Yuki Suzuki; Akinori Hata; Noriko Kikuchi; Yuriko Yoshida; Kazuki Yamagata; Shuhei Doi; Ryo Ogawa; Yukiko Tokuda; Shoji Kido; Noriyuki Tomiyama
• Keywords: 03 medical and health sciences; 0302 clinical medicine; Original Article

Abstract Purpose To predict solid and micropapillary components in lung invasive adenocarcinoma using radiomic analyses based on high-spatial-resolution CT (HSR-CT). Materials methods For this retrospective study, 64 patients with were enrolled. All scanned by HSR-CT 1024 matrix. A pathologist evaluated subtypes (lepidic, acinar, solid, micropapillary, or others). Total 61 features the images calculated our modified texture analysis software, then filtered minimized least absolute shrinkage selection operator (LASSO) regression to select optimal for predicting adenocarcinoma. Final data obtained repeating tenfold cross-validation 10 times. Two independent radiologists visually predicted each image of nodules without radiomics results. The quantitative values analyzed logistic models. receiver operating characteristic curves generated components. P < 0.05 considered significant. Results (Coefficient Variation Entropy) indicators associated (odds ratio, 30.5 11.4; 95% confidence interval, 5.1–180.5 1.9–66.6; = 0.0002 0.0071, respectively). area under curve was 0.902 (95% 0.802 0.962). results significantly improved accuracy specificity prediction two radiologists. Conclusion significant