{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T10:59:43Z","timestamp":1785495583789,"version":"3.56.0"},"reference-count":27,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:00:00Z","timestamp":1785456000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Science and Technology Council (NSTC) of the Executive Yuan of the Republic of China","award":["113-2221-E-992-011-MY2"],"award-info":[{"award-number":["113-2221-E-992-011-MY2"]}]},{"name":"National Science and Technology Council (NSTC) of the Executive Yuan of the Republic of China","award":["114-2637-8-992-002"],"award-info":[{"award-number":["114-2637-8-992-002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Life"],"abstract":"<jats:p>Objective: 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. Methods: 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. Results: 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. Conclusions: The proposed GAN\u2013Grad-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.<\/jats:p>","DOI":"10.3390\/life16081269","type":"journal-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T10:11:38Z","timestamp":1785492698000},"page":"1269","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable AI for Image-Based Auxiliary Assessment of Radiation Pneumonitis on Post-Treatment CT Images Using GAN Grad-CAM and Ensemble Learning Techniques"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3112-3594","authenticated-orcid":false,"given":"Tsair-Fwu","family":"Lee","sequence":"first","affiliation":[{"name":"Medical Physics and Informatics Laboratory of Electronic Engineering, National Kaohsiung University of Science and Technology, Kaohsiung 80778, Taiwan"},{"name":"Graduate Institute of Clinical Medicine, Kaohsiung Medical University, Kaohsiung 80708, Taiwan"},{"name":"Department of Medical Imaging and Radiological Sciences, Kaohsiung Medical University, Kaohsiung 80708, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guang-Zhi","family":"Lin","sequence":"additional","affiliation":[{"name":"Medical Physics and Informatics Laboratory of Electronic Engineering, National Kaohsiung University of Science and Technology, Kaohsiung 80778, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen-Ping","family":"Yun","sequence":"additional","affiliation":[{"name":"Medical Physics and Informatics Laboratory of Electronic Engineering, National Kaohsiung University of Science and Technology, Kaohsiung 80778, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Lun","family":"Liao","sequence":"additional","affiliation":[{"name":"Medical Physics and Informatics Laboratory of Electronic Engineering, National Kaohsiung University of Science and Technology, Kaohsiung 80778, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6712-2350","authenticated-orcid":false,"given":"Liyun","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging and Radiological Sciences, I-Shou University, Kaohsiung 82445, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0887-8558","authenticated-orcid":false,"given":"Chao-Hong","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Dermatology, Kaohsiung Yuan\u2019s General Hospital, Kaohsiung 80249, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng-Shie","family":"Wuu","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Columbia University, New York, NY 10032, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Chang","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Kaohsiung Veterans General Hospital, Kaohsiung 813414, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1768-8994","authenticated-orcid":false,"given":"Yu-Wei","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Kaohsiung Veterans General Hospital, Kaohsiung 813414, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pei-Ju","family":"Chao","sequence":"additional","affiliation":[{"name":"Medical Physics and Informatics Laboratory of Electronic Engineering, National Kaohsiung University of Science and Technology, Kaohsiung 80778, Taiwan"},{"name":"Department of Radiation Oncology, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung 833401, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1374-0775","authenticated-orcid":false,"given":"Yang-Wei","family":"Hsieh","sequence":"additional","affiliation":[{"name":"Medical Physics and Informatics Laboratory of Electronic Engineering, National Kaohsiung University of Science and Technology, Kaohsiung 80778, Taiwan"},{"name":"Department of Radiation Oncology, Kaohsiung Veterans General Hospital, Kaohsiung 813414, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Chen, Z., Yi, G., Li, X., Yi, B., Bao, X., Zhang, Y., Zhang, X., Yang, Z., and Guo, Z. (2024). Predicting radiation pneumonitis in lung cancer using machine learning and multimodal features: A systematic review and meta-analysis of diagnostic accuracy. BMC Cancer, 24.","DOI":"10.1186\/s12885-024-13098-5"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: Visual explanations from deep networks via gradient-based localization","volume":"128","author":"Selvaraju","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"101805","DOI":"10.1016\/j.inffus.2023.101805","article-title":"Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence","volume":"99","author":"Ali","year":"2023","journal-title":"Inf. Fusion"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"102233","DOI":"10.1016\/j.displa.2022.102233","article-title":"Vibration analysis process based on spectrogram using gradient class activation map with selection process of CNN model and feature layer","volume":"73","author":"Yoo","year":"2022","journal-title":"Displays"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e670","DOI":"10.1016\/j.ijrobp.2024.07.1472","article-title":"Optimizing Deep Learning Models: CNN-RNN Augmentation with Grad-CAM Analysis for Predicting Pneumonitis from Pre-Treatment CT Images","volume":"120","author":"Zou","year":"2024","journal-title":"Int. J. Radiat. Oncol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"15330338211016386","DOI":"10.1177\/15330338211016386","article-title":"The Application and Development of Deep Learning in Radiotherapy: A Systematic Review","volume":"20","author":"Huang","year":"2021","journal-title":"Technol. Cancer Res. Treat."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"108391","DOI":"10.1016\/j.asoc.2021.108391","article-title":"Interpretability in the medical field: A systematic mapping and review study","volume":"117","author":"Hakkoum","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"13875","DOI":"10.1002\/acm2.13875","article-title":"3D deep convolution neural network for radiation pneumonitis prediction following stereotactic body radiotherapy","volume":"24","author":"Kapoor","year":"2023","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"109581","DOI":"10.1016\/j.radonc.2023.109581","article-title":"Computed tomography and radiation dose images-based deep-learning model for predicting radiation pneumonitis in lung cancer patients after radiation therapy","volume":"182","author":"Zhang","year":"2023","journal-title":"Radiother. Oncol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"15330338241254060","DOI":"10.1177\/15330338241254060","article-title":"Deep-Learning Model Prediction of Radiation Pneumonitis Using Pretreatment Chest Computed Tomography and Clinical Factors","volume":"23","author":"Lee","year":"2024","journal-title":"Technol. Cancer Res. Treat."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"191","DOI":"10.3390\/automation4030012","article-title":"Automation Radiomics in Predicting Radiation Pneumonitis (RP)","volume":"4","author":"Raptis","year":"2023","journal-title":"Automation"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ninomiya, K., Arimura, H., Yoshitake, T., Hirose, T.-A., and Shioyama, Y. (2022). Synergistic combination of a topologically invariant imaging signature and a biomarker for the accurate prediction of symptomatic radiation pneumonitis before stereotactic ablative radiotherapy for lung cancer: A retrospective analysis. PLoS ONE, 17.","DOI":"10.1371\/journal.pone.0263292"},{"key":"ref_13","first-page":"20","article-title":"A review of principal component analysis algorithm for dimensionality reduction","volume":"2","author":"Hasan","year":"2021","journal-title":"J. Soft Comput. Data Min."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Cai, J., Zhu, H., Liu, S., Qi, Y., and Chen, R. (2024). Lung image segmentation via generative adversarial networks. Front. Physiol., 15.","DOI":"10.3389\/fphys.2024.1408832"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2774","DOI":"10.1109\/TEM.2021.3103334","article-title":"Lung-GANs: Unsupervised representation learning for lung disease classification using chest CT and X-ray images","volume":"70","author":"Yadav","year":"2021","journal-title":"IEEE Trans. Eng. Manag."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"Volume 45","author":"Breiman","year":"2001","journal-title":"Machine Learning"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-Vector Networks","volume":"Volume 20","author":"Cortes","year":"1995","journal-title":"Machine Learning"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","article-title":"Nearest neighbor pattern classification","volume":"13","author":"Cover","year":"1967","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). Xgboost: A scalable tree boosting system. Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"82719","DOI":"10.1007\/s11042-024-18780-1","article-title":"Advancing brain tumor classification accuracy through deep learning: Harnessing radimagenet pre-trained convolutional neural networks, ensemble learning, and machine learning classifiers on MRI brain images","volume":"83","author":"Remzan","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Liu, J., Dong, X., Zhao, H., and Tian, Y. (2022). Predictive classifier for cardiovascular disease based on stacking model fusion. Processes, 10.","DOI":"10.3390\/pr10040749"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"21311","DOI":"10.1007\/s11042-022-13844-6","article-title":"Pediatric pneumonia diagnosis using stacked ensemble learning on multi-model deep CNN architectures","volume":"82","author":"Prakash","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Rojas-L\u00f3pez, A.G., Rodr\u00edguez-Molina, A., Uriarte-Arcia, A.V., and Villarreal-Cervantes, M.G. (2024). Vertebral Column Pathology Diagnosis Using Ensemble Strategies Based on Supervised Machine Learning Techniques. Healthcare, 12.","DOI":"10.3390\/healthcare12131324"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"105539","DOI":"10.1016\/j.compbiomed.2022.105539","article-title":"A classification of MRI brain tumor based on two stage feature level ensemble of deep CNN models","volume":"146","author":"Aurna","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on Image Data Augmentation for Deep Learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"109347","DOI":"10.1016\/j.patcog.2023.109347","article-title":"A Comprehensive survey of image augmentation techniques for deep learning","volume":"137","author":"Xu","year":"2023","journal-title":"Pattern Recognit."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"22839","DOI":"10.1007\/s00521-021-06719-8","article-title":"Enhanced lung image segmentation using deep learning","volume":"35","author":"Gite","year":"2023","journal-title":"Neural Comput. Appl."}],"container-title":["Life"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-1729\/16\/8\/1269\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T10:19:11Z","timestamp":1785493151000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-1729\/16\/8\/1269"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,31]]},"references-count":27,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["life16081269"],"URL":"https:\/\/doi.org\/10.3390\/life16081269","relation":{},"ISSN":["2075-1729"],"issn-type":[{"value":"2075-1729","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,31]]}}}