An Interpretable Deep Learning Framework for Preoperative Classification of Lung Adenocarcinoma on CT Scans: Advancing Surgical Decision Support.

Abstract

Aim: Lung adenocarcinoma remains a leading cause of cancer-related mortality, and the diagnostic performance of computed tomography (CT) is limited when dependent solely on human interpretation. This study aimed to develop and evaluate an interpretable deep learning framework using an attention-enhanced Squeeze-and-Excitation Residual Network (SE-ResNet) to improve automated classification of lung adenocarcinoma from thoracic CT images. Furthermore, Gradient-weighted Class Activation Mapping (Grad-CAM) was applied to enhance model interpretability and assist in the visual localization of tumor regions.

Methods: A total of 3800 chest CT axial slices were collected from 380 subjects (190 patients with lung adenocarcinoma and 190 controls, with 10 slices extracted from each case). This dataset was used to train and evaluate the baseline ResNet50 model as well as the proposed SE-ResNet50 model. Performance was compared using accuracy, Area Under the Curve (AUC), precision, recall, and F1-score. Grad-CAM visualizations were generated to assess the alignment between the model's attention and radiologically confirmed tumor locations.

Results: The SE-ResNet model achieved a classification accuracy of 94% and an AUC of 0.941, significantly outperforming the baseline ResNet50, which had an 85% accuracy and an AUC of 0.854. Grad-CAM heatmaps produced from the SE-ResNet demonstrated superior localization of tumor-relevant regions, confirming the enhanced focus provided by the attention mechanism.

Conclusions: The proposed SE-ResNet framework delivers high accuracy and interpretability in classifying lung adenocarcinoma from CT images. It shows considerable potential as a decision-support tool to assist radiologists in diagnosis and may serve as a valuable clinical tool with further validation.