Robustness Analysis of Deep Learning-Based Lung Cancer Classification Using Explainable Methods
Open accessAbstract
Deep Learning (DL) based classification algorithms have been shown to achieve top results in clinical diagnosis, namely with lung cancer datasets. However, the complexity and opaqueness of the models together with the still scant training datasets call for the development of explainable modeling methods enabling the interpretation of the results. To this end, in this paper we propose a novel interpretability approach and demonstrate how it can be used on a malignancy lung cancer DL classifier to assess its stability and congruence even when fed a low amount of image samples. Additionally, by disclosing the regions of the medical images most relevant to the resulting classification the approach provides important insights to the correspondent clinical meaning apprehended by the algorithm. Explanations of the results provided by ten different models against the same test sample are compared. These attest the stability of the approach and the algorithm focus on the same image regions.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Assessing the robustness of a model's learned features to ensure the absence of spurious correlations is intricately linked to model explainability.
“Assessing the robustness of a model’s learned features to ensure the absence of spurious correlations is also intricately linked to model explainability26,27.”
From A scoping review of robustness concepts for machine learning in healthcare (2025) · cites this paper as [26]
Cites
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · see citing works
Multiscale structural similarity for image quality assessment
Wang, Z., Simoncelli, E. P., & Bovik, A. C. (2004) · The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003 · doi:10.1109/acssc.2003.1292216 · Cited by 6,253 · cited 2× · see citing works
“…more classical approaches, such as the Root Mean Squared Error (RMSE), as well as techniques that try to approximate the perceptual quality assessment of the Human Visual System (HVS), such as the Structural SIMilarity (SSIM) index and the Multi-Scale Structural SIMilarity (MS-SSIM) index [34].”
MethodDeep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370 · see citing works
On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.-R., & Samek, W. (2015) · PLOS ONE · doi:10.1371/journal.pone.0130140 · Cited by 4,524 · see citing works
Axiomatic attribution for deep networks
Sundararajan, M., Taly, A., & Yan, Q. (2017) · arXiv · doi:10.48550/arxiv.1703.01365 · Cited by 4,087 · see citing works
Armato, S. G., McLennan, G., Bidaut, L., McNitt‐Gray, M. F., Meyer, C. R., Reeves, A. P., Zhao, B., Aberle, D. R., Henschke, C. I., Hoffman, E. A., et al. (2011) · Medical Physics · doi:10.1118/1.3528204 · Cited by 2,887 · see citing works
Learning Important Features Through Propagating Activation Differences
Shrikumar, A., Greenside, P., & Kundaje, A. (2017) · arXiv · doi:10.48550/arxiv.1704.02685 · Cited by 2,761 · see citing works
Image Quality Assessment through FSIM, SSIM, MSE and PSNR—A Comparative Study
Sara, U., Akter, M., & Uddin, M. S. (2019) · Journal of Computer and Communications · doi:10.4236/jcc.2019.73002 · Cited by 1,689 · cited 2× · see citing works
“It can be computed by the squared-root of the Mean-Squared Error (MSE), being both these metrics non-normalized, which can compromise its interpretation by not providing an absolute measure of quality [36].”
BackgroundExplainable artificial intelligence (XAI) in deep learning-based medical image analysis
van der Velden, B. H. M., Kuijf, H. J., Gilhuijs, K. G. A., & Viergever, M. A. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102470 · Cited by 1,328 · see citing works
A strategy to apply machine learning to small datasets in materials science
Zhang, Y., & Ling, C. (2018) · npj Computational Materials · doi:10.1038/s41524-018-0081-z · Cited by 791 · see citing works
Yang, G., Ye, Q., & Xia, J. (2022) · Information Fusion · doi:10.1016/j.inffus.2021.07.016 · Cited by 717 · see citing works
On the Euclidean distance of images
Wang, L., Zhang, Y., & Feng, J. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.165 · Cited by 659 · see citing works
Captum: A unified and generic model interpretability library for PyTorch
Kokhlikyan, N., Miglani, V., Martin, M., Wang, E., Alsallakh, B., Reynolds, J., Melnikov, A., Kliushkina, N., Araya, C., Yan, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2009.07896 · Cited by 658 · see citing works
Multi-scale Convolutional Neural Networks for Lung Nodule Classification
Shen, W., Zhou, M., Yang, F., Yang, C., & Tian, J. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-19992-4_46 · Cited by 635 · see citing works
Generating Visual Explanations
Hendricks, L. A., Akata, Z., Rohrbach, M., Donahue, J., Schiele, B., & Darrell, T. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_1 · Cited by 534 · see citing works
Explainable Deep Learning: A Field Guide for the Uninitiated
Ras, G., Xie, N., van Gerven, M. A. J., & Doran, D. (2022) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.13200 · Cited by 486 · see citing works
On the interpretability of artificial intelligence in radiology: challenges and opportunities
Reyes, M., Meier, R., Pereira, S., Silva, C. A., Dahlweid, F.-M., Tengg-Kobligk, H. V., Summers, R. M., & Wiest, R. (2020) · Radiology: Artificial Intelligence · doi:10.1148/ryai.2020190043 · Cited by 484 · see citing works
Highly accurate model for prediction of lung nodule malignancy with CT scans
Causey, J., Zhang, J., Ma, S., Jiang, B., Qualls, J., Politte, D. G., Prior, F., Zhang, S., & Huang, X. (2018) · Scientific Reports · doi:10.1038/s41598-018-27569-w · Cited by 214 · see citing works
Armato, S. G., III, McLennan, G., Bidaut, L., McNitt-Gray, M. F., Meyer, C. R., Reeves, A. P., Zhao, B., Aberle, D. R., Henschke, C. I., Hoffman, E. A., et al. (2015) · The Cancer Imaging Archive · doi:10.7937/k9/tcia.2015.lo9ql9sx · Cited by 150 · see citing works
A Review of Explainable Deep Learning Cancer Detection Models in Medical Imaging
Gulum, M. A., Trombley, C. M., & Kantardzic, M. M. (2021) · Applied Sciences · doi:10.3390/app11104573 · Cited by 144 · see citing works
Explainable Artificial Intelligence: An Introduction to Interpretable Machine Learning
Kamath, U., & Liu, J. (2021) · doi:10.1007/978-3-030-83356-5 · Cited by 126 · see citing works
Jiang, H., Shen, F., Gao, F., & Han, W. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.107825 · Cited by 120 · see citing works
Shape and margin-aware lung nodule classification in low-dose CT images via soft activation mapping
Lei, Y., Tian, Y., Shan, H., Zhang, J., Wang, G., & Kalra, M. K. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.101628 · Cited by 91 · see citing works
Limitations of the SSIM quality metric in the context of diagnostic imaging
Pambrun, J.-F., & Noumeir, R. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351345 · Cited by 89 · see citing works
Efficient Saliency Maps for Explainable AIPreprint
Mundhenk, T. N., Chen, B. Y., & Friedland, G. H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.11293 · Cited by 87 · see citing works
Papanastasopoulos, Z., Samala, R. K., Chan, H., Hadjiiski, L. M., Paramagul, C., Helvie, M. A., & Neal, C. H. (2020) · SPIE Medical Imaging: Computer-Aided Diagnosis · doi:10.1117/12.2549298 · Cited by 78 · see citing works
Hryniewska-Guzik, W., Bombiński, P., Szatkowski, P., Tomaszewska, P., Przelaskowski, A., & Biecek, P. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.108035 · Cited by 57 · see citing works
Sharing Biomedical Data: Strengthening AI Development in Healthcare
Pereira, T., Morgado, J., Silva, F., Pelter, M. M., Dias, V. R., Barros, R., Freitas, C., Negrão, E., Flor de Lima, B., Correia da Silva, M., et al. (2021) · Healthcare · doi:10.3390/healthcare9070827 · Cited by 54 · cited 3× · see citing works
“LIDC-IDRI dataset used in this work is the most well know dataset for lung cancer-related research activities and it was extensively used for computer-aided decision systems for lung cancer detection [1].”
BackgroundMethodSelf-citationTowards Machine Learning-Aided Lung Cancer Clinical Routines: Approaches and Open Challenges
Silva, F., Pereira, T., Neves, I., Morgado, J., Freitas, C., Malafaia, M., Sousa, J. V., Fonseca, J., Negrão, E., de Lima, B. F., et al. (2022) · Journal of Personalized Medicine · doi:10.3390/jpm12030480 · Cited by 46 · see citing works
Self-citationInterpretability-Guided Content-Based Medical Image Retrieval
Silva, W., Poellinger, A., Cardoso, J. S., & Reyes, M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59710-8_30 · Cited by 43 · see citing works
Fel, T., Vigouroux, D., Cadène, R., & Serre, T. (2022) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv51458.2022.00163 · Cited by 29 · see citing works
Pre-Training Autoencoder for Lung Nodule Malignancy Assessment Using CT Images
Silva, F., Pereira, T., Frade, J., Mendes, J., Freitas, C., Hespanhol, V. P., Costa, J. L., Cunha, A. M. T. D. S., & Oliveira, H. P. (2020) · Applied Sciences · doi:10.3390/app10217837 · Cited by 25 · see citing works
Self-citationExplaining Deep Neural Network using Layer-wise Relevance Propagation and Integrated Gradients
Čík, I., Rasamoelina, A. D., Mach, M., & Sinčák, P. (2021) · IEEE World Symposium on Applied Machine Intelligence and Informatics (SAMI) · doi:10.1109/sami50585.2021.9378686 · Cited by 20 · see citing works
Ramos, B., Pereira, T., Moranguinho, J., Morgado, J., Costa, J. L., & Oliveira, H. P. (2021) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc46164.2021.9630775 · Cited by 17 · see citing works
Self-citationClassify and Explain: An Interpretable Convolutional Neural Network For Lung Cancer Diagnosis
Li, Y., Gu, D., Wen, Z., Jiang, F., & Liu, S. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9054605 · Cited by 14 · see citing works
Ma, Q., Yan, J., Zhang, J., Yu, Q., Zhao, Y., Liang, C., & Di, D. (2022) · Frontiers in Medicine · doi:10.3389/fmed.2022.840319 · Cited by 2 · see citing works
Flagged first, then by citations
1 of the 37 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Deep Learning for Medical Image-Based Cancer Diagnosis
Jiang, X., Hu, Z., Wang, S., & Zhang, Y. (2023) · Cancers · doi:10.3390/cancers15143608 · Cited by 390 · see citing works
Şahin, E., Arslan, N. N., & Özdemir, D. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10437-2 · Cited by 323 · see citing works
Hasan, M. A., Haque, F. M., Sabuj, S. R., Sarker, H., Goni, M. O. F., Rahman, F. S., & Rashid, M. M. (2024) · Technologies · doi:10.3390/technologies12040056 · Cited by 83 · see citing works
A scoping review of robustness concepts for machine learning in healthcare
Balendran, A., Beji, C., Bouvier, F., Khalifa, O., Evgeniou, T., Ravaud, P., & Porcher, R. (2025) · npj Digital Medicine · doi:10.1038/s41746-024-01420-1 · Cited by 43 · see citing works
“Assessingtherobustnessofamodel ’ slearnedfeaturestoensure the absence of spurious correlations is also intricately linked to model explainability 26,27 .”
Improving lung cancer detection via MobileNetV2 and stacked-GRU with explainable AI
Tofighi, A. B., Ahmadi, A., & Mosadegh, H. (2024) · International Journal of Information Technology · doi:10.1007/s41870-024-02045-z · Cited by 25 · see citing works
Haque, F. M., Hasan, M. A., Siddique, M. A. I., Roy, T., Shaha, T. K., Islam, Y., Paul, A., & Chowdhury, M. E. H. (2025) · IEEE Access · doi:10.1109/access.2025.3572423 · Cited by 21 · see citing works
Sridevi, S., & RajivKannan, A. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106243 · Cited by 10 · see citing works
Borra, S., Dey, N., Fong, S., Sherratt, R. S., & Shi, F. (2026) · Cancers · doi:10.3390/cancers18091361 · Cited by 8 · see citing works
Lung Cancer Classification Using Deep Neural Networks
Keerthi, P., Srisai Satya Santosh, Y., & Iniyan, S. (2025) · AI-Driven Smart Healthcare for Society 5.0 · doi:10.1109/ieeeconf64992.2025.10963162 · Cited by 6 · see citing works
Finzel, B., Rieger, I., Kuhn, S., & Schmid, U. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-40837-3_3 · Cited by 6 · see citing works
Shekhar, M., & Khetavath, S. (2024) · Journal of Medical Engineering & Technology · doi:10.1080/03091902.2024.2399015 · Cited by 3 · see citing works
Pulmonary Nodule Classification with Fine-Tuned Deep Learning Models
Sakshiwala, & Singh, M. P. (2023) · IEEE Conference on Information and Communication Technology (CICT) · doi:10.1109/cict59886.2023.10455628 · Cited by 3 · see citing works
Design and Build Blockchain-Based Privacy Preservation and Disease Prediction Using CNN Model
Dubey, B., Patil, V., Mandal, S., Mishra, K., Singh, S., & Pandey, V. (2024) · IEEE International Conference on Advances in Computing Research on Science Engineering and Technology (ACROSET) · doi:10.1109/acroset62108.2024.10743634 · Cited by 5 · see citing works
Performance Comparison of Deep Learning Methods for Lung Nodule Benign and Malignancy Classification
Bhagwat, K., & Thirupurasundari, D. R. (2024) · International Conference on Computing for Sustainable Global Development · doi:10.23919/indiacom61295.2024.10499183 · Cited by 2 · see citing works
Tumor Detection Using Deep Learning and Explainable Artificial Intelligence
Mehra, S. D., Aswani, S., & Shetty, S. D. (2024) · International Conference on Computational Intelligence and Network Systems (CINS) · doi:10.1109/cins63881.2024.10864458 · Cited by 2 · see citing works
Lung Guard: A Hybrid Ensemble Model for Early Lung Disease Classification
Goyal, D., Dinodia, A., Iniyan, S., Senthil Raja, M., Srinivasan, A., & Desai, U. (2025) · International Conference on Data Intelligence and Cognitive Informatics (ICDICI) · doi:10.1109/icdici66477.2025.11134931 · Cited by 1 · see citing works
Hadi, F., Bilal, O., & Asif, S. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.114698 · Cited by 1 · see citing works
Yousuf, M., Yasin, A., Mohammad, M., Israq, F., Bhuiyan, S. T., Rahman, R., Alam, S. B., & Islam, A. (2026) · IEEE International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN) · doi:10.1109/qpain69676.2026.11545645 · Cited by 1 · see citing works
Fernandes, L., Pereira, T., & Oliveira, H. P. (2024) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms61543.2024.00075
Self-citationNagaraju, D., & Kumar, B. P. S. (2025) · Biomedical Materials & Devices · doi:10.1007/s44174-025-00549-1
Hema, A., & Karpagam, G. R. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-8694-0_17
MYCN-Amplified Neuroblastoma Detection Radiomics Vs. Trainable Features
Malafaia, M., Silva, F., Carvalho, D. C., Martins, R., Dias, S. C., Torrão, H., Oliveira, H. P., & Pereira, T. (2025) · IEEE International Conference on Bioinformatics and Bioengineering (BIBE) · doi:10.1109/bibe66822.2025.00034
Self-citationEfficacious Lung Cancer Detection Utilising Hybrid Deep Learning and Sophisticated Image Processing
Simgamsetti, P. M., & Tirupal, T. (2025) · International Conference on IoT Based Control Networks and Intelligent Systems (ICICNIS) · doi:10.1109/icicnis66685.2025.11315770
Uddin, M. M., Tasnim, F., Sultana, J., & Arefin, M. S. (2025) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit68739.2025.11490331
Explainable and Trustworthy AI in Oncology: A Systematic Review Across Major Organ Systems
Hassan, M., Zubair, M., Ibrahim, R., Mahmood, T., Hussain, M., & Umair, M. (2026) · IEEE Access · doi:10.1109/access.2026.3717851 · Cited by 1 · see citing works
- Authors
- Malafaia, M., Silva, F., Neves, I., Pereira, T., & Oliveira, H. P.
- Affiliations
- INESC TEC (PT)
- INESC TEC–Institute for Systems and Computer Engineering, Technology and Science, Porto, Portugal
- Venue
- IEEE Access
- Published
- 2022
- Volume
- 10
- Pages
- 112731-112741
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W4312570936
- Cited by
- 25
- References
- 37
- Citations by year
- 2026: 4 · 2025: 9 · 2024: 9 · 2023: 3
- FWCI
- 1.73
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Funds through the Portuguese Funding Agency, FCT–Foundation for Science and Technology Portugal (LA/P/0063/2020)
- Ph.D. Grant (2021.05767.BD)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Keywords
- lung cancer classification, explainable deep learning, model interpretability, robustness analysis, saliency maps, medical image classification, malignancy detection
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
