Computed Tomography-based Prognostication in Lung Adenocarcinomas through Histopathological Feature Learning: A Retrospective Multicenter Study.

Modeling imaging surrogates for well-validated histopathological risk factors would enable prognostication in early-stage lung adenocarcinomas. We aimed to develop and validate computed tomography (CT)-based deep learning (DL) models for the prognostication of early-stage lung adenocarcinomas through learning histopathological features and to investigate the models' reproducibility using retrospective, multicenter datasets. Two DL models were trained to predict visceral pleural invasion and lymphovascular invasion, respectively, using preoperative chest CT scans from 1,426 patients with stage I-IV lung adenocarcinomas. The averaged model output was defined as the composite score and evaluated for the prognostic discrimination and its added value to clinicopathological factors in temporal ( = 610) and external test sets ( = 681) of stage I lung adenocarcinomas. The study outcomes were freedom from recurrence (FFR) and overall survival (OS). Interscan and interreader reproducibility were analyzed in 31 patients with lung cancer who underwent same-day repeated CT scans. For the temporal test set, the time-dependent area under the receiver operating characteristic curve was 0.76 (95% confidence interval [CI], 0.71-0.81) for 5-year FFR and 0.67 (95% CI, 0.59-0.75) for 5-year OS. For the external test set, the area under the curve was 0.69 (95% CI, 0.63-0.75) for 5-year OS. The discrimination performance remained stable in 10-year follow-up for both outcomes. The prognostic value of the composite score was independent of and complementary to the clinical factors (adjusted per-percent hazard ratio for FFR [temporal test], 1.04 [95% CI, 1.03-1.05;  < 0.001]; OS [temporal test], 1.03 [95% CI, 1.02-1.04;  < 0.001]; OS [external test], 1.03 [95% CI, 1.02-1.04;  < 0.001]). The likelihood ratio tests indicated added value of the composite score (all  < 0.05). The interscan and interreader reproducibility were excellent (Pearson's correlation coefficient, 0.98 for both). The CT-based composite score obtained from DL of histopathological features predicted survival in early-stage lung adenocarcinomas with high reproducibility.