CT-Based Deep Learning Model for Invasiveness Classification and Micropapillary Pattern Prediction Within Lung Adenocarcinoma

Objective: Identification of tumor invasiveness of pulmonary adenocarcinomas before surgery is one of the most important guides to surgical planning. Additionally, preoperative diagnosis of lung adenocarcinoma with micropapillary patterns is also critical for clinical decision making. We aimed to evaluate the accuracy of deep learning models on classifying invasiveness degree and attempted to predict the micropapillary pattern in lung adenocarcinoma. Methods: The records of 291 histopathologically confirmed lung adenocarcinoma patients were retrospectively analyzed and consisted of 61 adenocarcinoma in situ, 80 minimally invasive adenocarcinoma, 117 invasive adenocarcinoma, and 33 invasive adenocarcinoma with micropapillary components (>5%). We constructed two diagnostic models, the Lung-DL model and the Dense model, based on the LeNet and the DenseNet architecture, respectively. Results: For distinguishing the nodule invasiveness degree, the area under the curve (AUC) value of the diagnosis with the Lung-DL model is 0.88 and that with the Dense model is 0.86. In the prediction of the micropapillary pattern, overall accuracies of 92 and 72.91% were obtained for the Lung-DL model and the Dense model, respectively. Conclusion: Deep learning was successfully used for the invasiveness classification of pulmonary adenocarcinomas. This is also the first time that deep learning techniques have been used to predict micropapillary patterns. Both tasks can increase efficiency and assist in the creation of precise individualized treatment plans.