The application of explainable deep-radiomics in lung cancer research: Method comparison and analysis_Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Authors：

WANG Yusen ^1,2 , GUO Chao ¹ ,  LI Shanqing ¹

1. Department of Thoracic Surgery, Peking Union Medical College Hospital, Beijing, 100730, P. R. China;
2. 4-year MD Program, Peking Union Medical College, Beijing, 100730, P. R. China;

Corresponding?author：

LI Shanqing, Email: lishanqing@pumch.cn

Keywords：

Artificial intelligence; lung neoplasms; precision medicine; radiomics; deep learning; non-fully supervised learning; model interpretability

DOI：

10.7507/1007-4848.202603088

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Nowadays, lung cancer is the most common and lethal invasive tumor type in Chinese population, challenging overall health level. However, personalized early-stage treatment is currently still not widely implemented, and the choice of treatment highly depends on experience of physician. Based on deep learning and radiomics principles, deep-radiomics is important for establishing objective and promotable precision medicine plans. Among all aspects, the explainability of a model is critical for its usage in clinical practice. This paper discusses the technical aspects of explainable deep-radiomics in lung cancer, and analyzes challenges we are facing. Non-fully supervised learning methods, as a current hotspot in deep learning technology, can construct more trustworthy and practically valuable deep learning models through the co-design method of performance-interpretability. Medical artificial intelligence faces three core challenges in transitioning from the laboratory to hospitals: high-level cognitive demands, data privacy and generalization capabilities, and regulatory compliance. However, with appropriate design, non-fully supervised learning holds the greatest potential to bridge the gap between design and application, enabling broader adoption.

1.	Vinod SK. Decision making in lung cancer—how applicable are the guidelines? Clin Oncol, 2015, 27(2): 125-131.
2.	Mokhles S, Maat APWM, Aerts JGJV, et al. Opinions of lung cancer clinicians on shared decision making in early-stage non-small-cell lung cancer. Interact Cardiovasc Thorac Surg, 2017, 25(2): 278-284.
3.	LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition. Proc IEEE, 1998, 86(11): 2278-2324.
4.	Holzinger A, Langs G, Denk H, et al. Causability and explainability of artificial intelligence in medicine. Wiley Interdiscip Rev Data Min Knowl Discov, 2019, 9(4): e1312.
5.	Anton J, Castelli L, Chan MF, et al. How well do self-supervised models transfer to medical imaging?. J Imaging, 2022, 8(12): 320.
6.	Zhu P, Ogino M. Guideline-based additive explanation for computer-aided diagnosis of lung nodules. In: Suzuki K, Reyes M, Syeda-Mahmood T, et al, Editor-in-Chief. Interpretability of Machine Intelligence in Medical Image Computing and Multimodal Learning for Clinical Decision Support: Vol. 11797. Cham: Springer International Publishing, 2019: 39-47.
7.	Kindermans PJ, Hooker S, Adebayo J, et al. The (un)reliability of saliency methods. arXiv, 2017: 1711.00867.
8.	Salimi Y, Hajianfar G, Mansouri Z, et al. Organomics: a concept reflecting the importance of PET/CT healthy organ radiomics in non-small cell lung cancer prognosis prediction using machine learning. Clin Nucl Med, 2024, 49(10): 899-908.
9.	Ferretti M, Corino VDA. Integrating radiomic and 3D autoencoder-based features for non-small cell lung cancer survival analysis. Comput Methods Programs Biomed, 2025, 258: 108496.
10.	Amini M, Hajianfar G, Salimi Y, et al. MetaPredictomics: a comprehensive approach to predict postsurgical non-small cell lung cancer recurrence using clinicopathologic, radiomics, and organomics data. Clin Nucl Med, 2025, 50(12): 1130-1143.
11.	Lu HJ, Ma HF, Chen DG, et al. Prediction of prognosis for non-small cell lung cancer after targeted therapy based on CT imaging and dense convolutional sparse coding. IEEE Sens J, 2025, 25(14): 26956-26969.
12.	Bengio Y, Courville A, Vincent P. Representation learning: a review and new perspectives. arXiv, 2014: 1206.5538.
13.	Chu SM. Audio-visual speech modeling using coupled hidden Markov models. Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2009: 1125-1128.
14.	Singh SP. Transfer of learning by composing solutions of elemental sequential tasks. Mach Learn, 1992, 8(3-4): 323-339.
15.	Xing EP, Jordan MI, Russell SJ, et al. Distance metric learning with application to clustering with side-information//Becker S, Thrun S, Obermayer K, editors. Advances in neural information processing systems 15. Cambridge: MIT Press, 2003: 505-512.
16.	Ye G, Wei Z, Han C, et al. AI-derived longitudinal and multi-dimensional CT classifier for non-small cell lung cancer to optimize neoadjuvant chemoimmunotherapy decision: a multicentre retrospective study. eClinicalMedicine, 2025, 89: 103551.
17.	Yin X, Lu Y, Cui Y, et al. CT-based radiomics-deep learning model predicts occult lymph node metastasis in early-stage lung adenocarcinoma patients: a multicenter study. Chin J Cancer Res, 2025, 37(1): 118-131.
18.	Tao J, Liang C, Yin K, et al. 3D convolutional neural network model from contrast-enhanced CT to predict spread through air spaces in non-small cell lung cancer. Diagn Interv Imaging, 2022, 103(11): 535-544.
19.	Zhao J, Wang T, Wang B, et al. Deep learning radiomics fusion model to predict visceral pleural invasion of clinical stage IA lung adenocarcinoma: a multicenter study. J Cardiothorac Surg, 2025, 20(1): 246.
20.	Jin W, Shen L, Tian Y, et al. Improving the prediction of spreading through air spaces (STAS) in primary lung cancer with a dynamic dual-delta hybrid machine learning model: a multicenter cohort study. Biomark Res, 2023, 11(1): 102.
21.	Jin W, Tian Y, Xuzhang W, et al. Non-linear modifications enhance prediction of pathological response to pre-operative PD-1 blockade in lung cancer: a longitudinal hybrid radiological model. Pharmacol Res, 2023, 198: 106992.
22.	Wang C, Ma J, Shao J, et al. Predicting EGFR and PD-L1 status in NSCLC patients using multitask AI system based on CT images. Front Immunol, 2022, 13: 813072.
23.	Wang C, Ma J, Shao J, et al. Non-invasive measurement using deep learning algorithm based on multi-source features fusion to predict PD-L1 expression and survival in NSCLC. Front Immunol, 2022, 13: 828560.
24.	Masuda T, Kawahara D, Daido W, et al. A radiomics-based machine learning model for predicting pneumonitis during durvalumab treatment in locally advanced NSCLC. AI, 2026, 7(1): 32.
25.	Zhong Y, Cai C, Chen T, et al. PET/CT based cross-modal deep learning signature to predict occult nodal metastasis in lung cancer. Nat Commun, 2023, 14(1): 7513.
26.	Zhong Y, Cai C, Chen T, et al. PET/CT-based deep learning grading signature to optimize surgical decisions for clinical stageⅠinvasive lung adenocarcinoma and biologic basis under its prediction: a multicenter study. Eur J Nucl Med Mol Imaging, 2024, 51(2): 521-534.
27.	Wang Y, Gupta A, Tushar FI, et al. Concordance-based predictive uncertainty (CPU)-index: proof-of-concept with application towards improved specificity of lung cancers on low dose screening CT. Artif Intell Med, 2025, 160: 103055.
28.	Hosny A, Parmar C, Coroller TP, et al. Deep learning for lung cancer prognostication: a retrospective multi-cohort radiomics study. PLoS Med, 2018, 15(11): e1002711.
29.	Paul R, Schabath M, Gillies R, et al. Convolutional neural network ensembles for accurate lung nodule malignancy prediction 2 years in the future. Comput Biol Med, 2020, 122: 103882.
30.	Hunter B, Chen M, Ratnakumar P, et al. A radiomics-based decision support tool improves lung cancer diagnosis in combination with the Herder score in large lung nodules. EBioMedicine, 2022, 86: 104344.
31.	Cho HH, Lee HY, Kim E, et al. Radiomics-guided deep neural networks stratify lung adenocarcinoma prognosis from CT scans. Commun Biol, 2021, 4(1): 1286.
32.	Zhang K, Qi S, Cai J, et al. Content-based image retrieval with a convolutional siamese neural network: distinguishing lung cancer and tuberculosis in CT images. Comput Biol Med, 2022, 140: 105096.
33.	Pedrycz W. Algorithms of fuzzy clustering with partial supervision. Pattern Recognit Lett, 1985, 3(1): 13-20.
34.	Zech JR, Badgeley MA, Liu M, et al. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study. PLoS Med, 2018, 15(11): e1002683.
35.	Dietterich TG, Lathrop RH, Lozano-Pérez T. Solving the multiple instance problem with axis-parallel rectangles. Artif Intell, 1997, 89(1-2): 31-71.
36.	Li R, Mai Z, Zhang Z, et al. TransCAM: transformer attention-based CAM refinement for weakly supervised semantic segmentation. J Vis Commun Image Represent, 2023, 92: 103800.
37.	MacQueen J. Some methods for classification and analysis of multivariate observations. Le Cam LM, Neyman J, editors. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability. Berkeley: University of California Press, 1967: 281-297.
38.	Shen Z, Cao P, Yang J, et al. WS-LungNet: a two-stage weakly-supervised lung cancer detection and diagnosis network. Comput Biol Med, 2023, 154: 106587.
39.	Ji Y, Ge R, Meng W, et al. Enhanced prediction of gene mutation and risk stratification in non-small-cell lung cancer through dual-pathway fusion of radiomics and pathomics. Front Oncol, 2025, 15: 1646851.
40.	Hu J, Cheng R, Quan M, et al. Hypermetabolic pulmonary lesions detection and diagnosis based on PET/CT imaging and deep learning models. Eur J Nucl Med Mol Imaging, 2025, 52(10): 3792-3806.
41.	Sun W, Zheng B, Qian W. Automatic feature learning using multichannel ROI based on deep structured algorithms for computerized lung cancer diagnosis. Comput Biol Med, 2017, 89: 530-539.
42.	Huang X, Huang X, Wang K, et al. 2.5D deep learning radiomics and clinical data for predicting occult lymph node metastasis in lung adenocarcinoma. BMC Med Imaging, 2025, 25(1): 225.
43.	Tozuka R, Kadoya N, Yasunaga A, et al. Fractal-driven self-supervised learning enhances early-stage lung cancer GTV segmentation: a novel transfer learning framework. Jpn J Radiol, 2026, 44(1): 183-195.
44.	Babic B, Gerke S, Evgeniou T, et al. Beware explanations from AI in health care. Science, 2021, 373(6552): 284-286.
45.	Liu L, Wang X, Huang S, et al. Identifying non-small cell lung cancer subtypes by a hybrid representative causal network with computed tomography images. Eng Appl Artif Intell, 2026, 174: 114540.
46.	U. S. Food and Drug Administration. Transparency for machine learning-enabled medical devices: guiding principles. Silver Spring: U. S. Food and Drug Administration, 2021. https://www.fda.gov/medical-devices/software-medical-device-samd/transparency-machine-learning-enabled-medical-devices.

1. Vinod SK. Decision making in lung cancer—how applicable are the guidelines? Clin Oncol, 2015, 27(2): 125-131.
2. Mokhles S, Maat APWM, Aerts JGJV, et al. Opinions of lung cancer clinicians on shared decision making in early-stage non-small-cell lung cancer. Interact Cardiovasc Thorac Surg, 2017, 25(2): 278-284.
3. LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition. Proc IEEE, 1998, 86(11): 2278-2324.
4. Holzinger A, Langs G, Denk H, et al. Causability and explainability of artificial intelligence in medicine. Wiley Interdiscip Rev Data Min Knowl Discov, 2019, 9(4): e1312.
5. Anton J, Castelli L, Chan MF, et al. How well do self-supervised models transfer to medical imaging?. J Imaging, 2022, 8(12): 320.
6. Zhu P, Ogino M. Guideline-based additive explanation for computer-aided diagnosis of lung nodules. In: Suzuki K, Reyes M, Syeda-Mahmood T, et al, Editor-in-Chief. Interpretability of Machine Intelligence in Medical Image Computing and Multimodal Learning for Clinical Decision Support: Vol. 11797. Cham: Springer International Publishing, 2019: 39-47.
7. Kindermans PJ, Hooker S, Adebayo J, et al. The (un)reliability of saliency methods. arXiv, 2017: 1711.00867.
8. Salimi Y, Hajianfar G, Mansouri Z, et al. Organomics: a concept reflecting the importance of PET/CT healthy organ radiomics in non-small cell lung cancer prognosis prediction using machine learning. Clin Nucl Med, 2024, 49(10): 899-908.
9. Ferretti M, Corino VDA. Integrating radiomic and 3D autoencoder-based features for non-small cell lung cancer survival analysis. Comput Methods Programs Biomed, 2025, 258: 108496.
10. Amini M, Hajianfar G, Salimi Y, et al. MetaPredictomics: a comprehensive approach to predict postsurgical non-small cell lung cancer recurrence using clinicopathologic, radiomics, and organomics data. Clin Nucl Med, 2025, 50(12): 1130-1143.
11. Lu HJ, Ma HF, Chen DG, et al. Prediction of prognosis for non-small cell lung cancer after targeted therapy based on CT imaging and dense convolutional sparse coding. IEEE Sens J, 2025, 25(14): 26956-26969.
12. Bengio Y, Courville A, Vincent P. Representation learning: a review and new perspectives. arXiv, 2014: 1206.5538.
13. Chu SM. Audio-visual speech modeling using coupled hidden Markov models. Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2009: 1125-1128.
14. Singh SP. Transfer of learning by composing solutions of elemental sequential tasks. Mach Learn, 1992, 8(3-4): 323-339.
15. Xing EP, Jordan MI, Russell SJ, et al. Distance metric learning with application to clustering with side-information//Becker S, Thrun S, Obermayer K, editors. Advances in neural information processing systems 15. Cambridge: MIT Press, 2003: 505-512.
16. Ye G, Wei Z, Han C, et al. AI-derived longitudinal and multi-dimensional CT classifier for non-small cell lung cancer to optimize neoadjuvant chemoimmunotherapy decision: a multicentre retrospective study. eClinicalMedicine, 2025, 89: 103551.
17. Yin X, Lu Y, Cui Y, et al. CT-based radiomics-deep learning model predicts occult lymph node metastasis in early-stage lung adenocarcinoma patients: a multicenter study. Chin J Cancer Res, 2025, 37(1): 118-131.
18. Tao J, Liang C, Yin K, et al. 3D convolutional neural network model from contrast-enhanced CT to predict spread through air spaces in non-small cell lung cancer. Diagn Interv Imaging, 2022, 103(11): 535-544.
19. Zhao J, Wang T, Wang B, et al. Deep learning radiomics fusion model to predict visceral pleural invasion of clinical stage IA lung adenocarcinoma: a multicenter study. J Cardiothorac Surg, 2025, 20(1): 246.
20. Jin W, Shen L, Tian Y, et al. Improving the prediction of spreading through air spaces (STAS) in primary lung cancer with a dynamic dual-delta hybrid machine learning model: a multicenter cohort study. Biomark Res, 2023, 11(1): 102.
21. Jin W, Tian Y, Xuzhang W, et al. Non-linear modifications enhance prediction of pathological response to pre-operative PD-1 blockade in lung cancer: a longitudinal hybrid radiological model. Pharmacol Res, 2023, 198: 106992.
22. Wang C, Ma J, Shao J, et al. Predicting EGFR and PD-L1 status in NSCLC patients using multitask AI system based on CT images. Front Immunol, 2022, 13: 813072.
23. Wang C, Ma J, Shao J, et al. Non-invasive measurement using deep learning algorithm based on multi-source features fusion to predict PD-L1 expression and survival in NSCLC. Front Immunol, 2022, 13: 828560.
24. Masuda T, Kawahara D, Daido W, et al. A radiomics-based machine learning model for predicting pneumonitis during durvalumab treatment in locally advanced NSCLC. AI, 2026, 7(1): 32.
25. Zhong Y, Cai C, Chen T, et al. PET/CT based cross-modal deep learning signature to predict occult nodal metastasis in lung cancer. Nat Commun, 2023, 14(1): 7513.
26. Zhong Y, Cai C, Chen T, et al. PET/CT-based deep learning grading signature to optimize surgical decisions for clinical stageⅠinvasive lung adenocarcinoma and biologic basis under its prediction: a multicenter study. Eur J Nucl Med Mol Imaging, 2024, 51(2): 521-534.
27. Wang Y, Gupta A, Tushar FI, et al. Concordance-based predictive uncertainty (CPU)-index: proof-of-concept with application towards improved specificity of lung cancers on low dose screening CT. Artif Intell Med, 2025, 160: 103055.
28. Hosny A, Parmar C, Coroller TP, et al. Deep learning for lung cancer prognostication: a retrospective multi-cohort radiomics study. PLoS Med, 2018, 15(11): e1002711.
29. Paul R, Schabath M, Gillies R, et al. Convolutional neural network ensembles for accurate lung nodule malignancy prediction 2 years in the future. Comput Biol Med, 2020, 122: 103882.
30. Hunter B, Chen M, Ratnakumar P, et al. A radiomics-based decision support tool improves lung cancer diagnosis in combination with the Herder score in large lung nodules. EBioMedicine, 2022, 86: 104344.
31. Cho HH, Lee HY, Kim E, et al. Radiomics-guided deep neural networks stratify lung adenocarcinoma prognosis from CT scans. Commun Biol, 2021, 4(1): 1286.
32. Zhang K, Qi S, Cai J, et al. Content-based image retrieval with a convolutional siamese neural network: distinguishing lung cancer and tuberculosis in CT images. Comput Biol Med, 2022, 140: 105096.
33. Pedrycz W. Algorithms of fuzzy clustering with partial supervision. Pattern Recognit Lett, 1985, 3(1): 13-20.
34. Zech JR, Badgeley MA, Liu M, et al. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study. PLoS Med, 2018, 15(11): e1002683.
35. Dietterich TG, Lathrop RH, Lozano-Pérez T. Solving the multiple instance problem with axis-parallel rectangles. Artif Intell, 1997, 89(1-2): 31-71.
36. Li R, Mai Z, Zhang Z, et al. TransCAM: transformer attention-based CAM refinement for weakly supervised semantic segmentation. J Vis Commun Image Represent, 2023, 92: 103800.
37. MacQueen J. Some methods for classification and analysis of multivariate observations. Le Cam LM, Neyman J, editors. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability. Berkeley: University of California Press, 1967: 281-297.
38. Shen Z, Cao P, Yang J, et al. WS-LungNet: a two-stage weakly-supervised lung cancer detection and diagnosis network. Comput Biol Med, 2023, 154: 106587.
39. Ji Y, Ge R, Meng W, et al. Enhanced prediction of gene mutation and risk stratification in non-small-cell lung cancer through dual-pathway fusion of radiomics and pathomics. Front Oncol, 2025, 15: 1646851.
40. Hu J, Cheng R, Quan M, et al. Hypermetabolic pulmonary lesions detection and diagnosis based on PET/CT imaging and deep learning models. Eur J Nucl Med Mol Imaging, 2025, 52(10): 3792-3806.
41. Sun W, Zheng B, Qian W. Automatic feature learning using multichannel ROI based on deep structured algorithms for computerized lung cancer diagnosis. Comput Biol Med, 2017, 89: 530-539.
42. Huang X, Huang X, Wang K, et al. 2.5D deep learning radiomics and clinical data for predicting occult lymph node metastasis in lung adenocarcinoma. BMC Med Imaging, 2025, 25(1): 225.
43. Tozuka R, Kadoya N, Yasunaga A, et al. Fractal-driven self-supervised learning enhances early-stage lung cancer GTV segmentation: a novel transfer learning framework. Jpn J Radiol, 2026, 44(1): 183-195.
44. Babic B, Gerke S, Evgeniou T, et al. Beware explanations from AI in health care. Science, 2021, 373(6552): 284-286.
45. Liu L, Wang X, Huang S, et al. Identifying non-small cell lung cancer subtypes by a hybrid representative causal network with computed tomography images. Eng Appl Artif Intell, 2026, 174: 114540.
46. U. S. Food and Drug Administration. Transparency for machine learning-enabled medical devices: guiding principles. Silver Spring: U. S. Food and Drug Administration, 2021. https://www.fda.gov/medical-devices/software-medical-device-samd/transparency-machine-learning-enabled-medical-devices.

Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Latest ArticlesThe application of explainable deep-radiomics in lung cancer research: Method comparison and analysis

Abstract Full text Figures/Tables Video References Cited by

Format

Content