Deep Learning Analysis of CT Images Reveals High-Grade Pathological Features to Predict Survival in Lung Adenocarcinoma

Simple Summary The high-grade pattern (micropapillary or solid pattern, MPSol) in lung adenocarcinoma affects the patient's poor prognosis. We aimed to develop a deep learning (DL) model for predicting any high-grade patterns in lung adenocarcinoma and to assess the prognostic performance of model in advanced lung cancer patients who underwent neoadjuvant of definitive concurrent chemoradiation therapy (CCRT). Our model considering both tumor and peri-tumoral area showed area under the curve value of 0.8. DL model worked well in independent validation set of advanced lung cancer, stratifying their survival significantly. The subgroup with a high probability of MPSol estimated by the DL model showed a 1.76-fold higher risk of death. Thus, our DL model can be useful in estimating high-grade histologic patterns in lung adenocarcinomas and predicting clinical outcomes of patients with advanced lung cancer who underwent neoadjuvant or definitive CCRT. We aimed to develop a deep learning (DL) model for predicting high-grade patterns in lung adenocarcinomas (ADC) and to assess the prognostic performance of model in advanced lung cancer patients who underwent neoadjuvant or definitive concurrent chemoradiation therapy (CCRT). We included 275 patients with 290 early lung ADCs from an ongoing prospective clinical trial in the training dataset, which we split into internal-training and internal-validation datasets. We constructed a diagnostic DL model of high-grade patterns of lung ADC considering both morphologic view of the tumor and context view of the area surrounding the tumor (MC3DN; morphologic-view context-view 3D network). Validation was performed on an independent dataset of 417 patients with advanced non-small cell lung cancer who underwent neoadjuvant or definitive CCRT. The area under the curve value of the DL model was 0.8 for the prediction of high-grade histologic patterns such as micropapillary and solid patterns (MPSol). When our model was applied to the validation set, a high probability of MPSol was associated with worse overall survival (probability of MPSol >0.5 vs. <0.5; 5-year OS rate 56.1% vs. 70.7%), indicating that our model could predict the clinical outcomes of advanced lung cancer patients. The subgroup with a high probability of MPSol estimated by the DL model showed a 1.76-fold higher risk of death (HR 1.76, 95% CI 1.16-2.68). Our DL model can be useful in estimating high-grade histologic patterns in lung ADCs and predicting clinical outcomes of patients with advanced lung cancer who underwent neoadjuvant or definitive CCRT.

Automated summary

The study developed a deep learning model for predicting high-grade patterns in lung adenocarcinomas and assessing their prognostic performance in advanced lung cancer patients who underwent neoadjuvant or definitive CCRT. The model showed an area under the curve value of 0.8 and successfully stratified survival in an independent validation set. Patients with a high probability of Micropapillary or Solid patterns (MPSol) estimated by the DL model had a significantly higher risk of death. The DL model can be useful in estimating high-grade histologic patterns in lung adenocarcinomas and predicting clinical outcomes of advanced lung cancer patients undergoing neoadjuvant or definitive CCRT.