Explainable AI for Image-Based Auxiliary Assessment of Radiation Pneumonitis on Post-Treatment CT Images Using GAN Grad-CAM and Ensemble Learning Techniques.
Authors
Affiliations (8)
Affiliations (8)
- Medical Physics and Informatics Laboratory of Electronic Engineering, National Kaohsiung University of Science and Technology, Kaohsiung 80778, Taiwan.
- Graduate Institute of Clinical Medicine, Kaohsiung Medical University, Kaohsiung 80708, Taiwan.
- Department of Medical Imaging and Radiological Sciences, Kaohsiung Medical University, Kaohsiung 80708, Taiwan.
- Department of Medical Imaging and Radiological Sciences, I-Shou University, Kaohsiung 82445, Taiwan.
- Department of Dermatology, Kaohsiung Yuan's General Hospital, Kaohsiung 80249, Taiwan.
- Department of Radiation Oncology, Columbia University, New York, NY 10032, USA.
- Department of Radiation Oncology, Kaohsiung Veterans General Hospital, Kaohsiung 813414, Taiwan.
- Department of Radiation Oncology, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung 833401, Taiwan.
Abstract
<b>Objective:</b> This study aims to develop a preliminary explainable image-based auxiliary assessment framework for radiation pneumonitis (RP) by integrating a generative adversarial network (GAN), Gradient-weighted Class Activation Mapping (Grad-CAM), and ensemble learning to improve image-based classification performance, interpretability, and computational efficiency. <b>Methods:</b> Chest CT images from 46 lung cancer patients who underwent VMAT were retrospectively collected, yielding 542 RP and 1857 non-RP images. Images were preprocessed using Otsu-based segmentation and standardized before being input into the RP-GAN for feature extraction. Grad-CAM was applied to qualitatively visualize attention patterns across convolutional layers and guide feature-layer selection, while PCA reduced the extracted features from 12,288 to 730 dimensions. An ensemble stacking classifier combining RF, SVM, KNN, and XGBoost with logistic regression as a meta-learner was constructed. Model performance was evaluated using AUC, accuracy, PPV, NPV, specificity, recall, and F1-score. <b>Results:</b> Grad-CAM highlighted conv2d_4 and conv2d_5 as the most informative layers. PCA reduced training time from 49 min to 49 s with minimal performance loss. In the internal hold-out test set, the ensemble model achieved the highest point estimates for AUC and accuracy among the evaluated classifiers (AUC = 0.921; accuracy = 87.1%). The model identified RP-positive CT slices and provided qualitative visual cues for suspected RP-related regions. <b>Conclusions:</b> The proposed GAN-Grad-CAM ensemble framework showed promising internal classification performance for post-treatment CT-based RP image assessment with substantially improved computational efficiency. Its qualitative visual outputs may support clinical image review, although further external validation and quantitative localization assessment are required before clinical application as an auxiliary image-review tool.