Deep Learning Model Predicts Pathological Complete Response of Lung Cancer Following Neoadjuvant Immunochemotherapy

Deep Learning Model, Neoadjuvant Chemoimmunotherapy, Non-small Cell Lung Cancer, Pathological Complete Response

This study presents the development and validation of an artificial intelligence (AI) prediction system that utilizes pre-neoadjuvant immunotherapy plain scans and enhanced multimodal CT scans to extract deep learning features. The aim is to predict the occurrence of pathological complete response in non-small cell lung cancer patients undergoing neoadjuvant immunochemotherapyy.

This study retrospectively obtained non-contrast enhanced and contrast enhanced CT scans of patients with NSCLC who underwent surgery after receiving neoadjuvant immunochemotherapy. at multiple centers between August 2019 and February 2023. Deep learning features were extracted from both non-contract enhanced and contract enhanced CT scans to construct the predictive models (LUNAI-nCT model and LUNAI-eCT model), respectively. After feature fusion of these two types of features, a fused model (LUNAI-fCT model) was constructed. The performance of the model was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). SHapley Additive exPlanations (SHAP) analysis was used to quantify the impact of CT imaging features on model prediction. To gain insights into how our model makes predictions, we employed Gradient-weighted Class Activation Mapping (Grad-CAM) to generate saliency heatmaps.