A Controlled Variation Approach for Example-Based Explainable AI in Colorectal Polyp Classification
Source abstract
Abstract
Medical imaging is vital for diagnosing and treating colorectal cancer (CRC), a leading cause of mortality. Classifying colorectal polyps and CRC precursors remains challenging due to operator variability and expertise dependence. Deep learning (DL) models show promise in polyp classification but face adoption barriers due to their ‘black box’ nature, limiting interpretability. This study presents an example-based explainable artificial intehlligence (XAI) approach using Pix2Pix to generate synthetic polyp images with controlled size variations and LIME to explain classifier predictions visually. EfficientNet and Vision Transformer (ViT) were trained on datasets of real and synthetic images, achieving strong baseline accuracies of 94% and 96%, respectively. Image quality was assessed using PSNR (18.04), SSIM (0.64), and FID (123.32), while classifier robustness was evaluated across polyp sizes. Results show that Pix2Pix effectively controls image attributes like polyp size despite limitations in visual fidelity. LIME integration revealed classifier vulnerabilities, underscoring the value of complementary XAI techniques. This enhances DL model interpretability and deepens understanding of their behaviour. The findings contribute to developing explainable AI tools for polyp classification and CRC diagnosis. Future work will improve synthetic image quality and refine XAI methodologies for broader clinical use.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Radiomics and Machine Learning in Medical Imaging
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Institute for Systems and Computer Engineering, Technology and Science, 4200-465 Porto, Portugal
School of Sciences and Technology, University of Trás-os-Montes and Alto Douro, 5000-801 Vila Real, Portugal
Applied Computing Group, UFMA—Federal University of Maranhão, São Luís 65080-805, Brazil
ALGORITMI Research Centre, University of Minho, 4800-058 Guimarães, Portugal
Funding
FCT—Fundacão para a Ciência e a Tecnologia
References (33)
Show source-provided references
1. The relationship between colorectal polyps and colon cancer with Helicobacter pylori infection10.18203/2349-2902.isj20230486 ↗
2. Gohel, P., Singh, P., and Mohanty, M. (2021). Explainable AI: Current status and future directions. arXiv.
3. Sheu, R.-K., and Pardeshi, M.S. (2022). A Survey on Medical Explainable AI (XAI): Recent Progress, Explainability Approach, Human Interaction and Scoring System. Sensors, 22.10.3390/s22208068 ↗
4. Arrieta, A.B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., and Benjamins, R. (2019). Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI. arXiv.
5. Hesse, L.S., Dinsdale, N.K., and Namburete, A.I.L. (2023). Prototype Learning for Explainable Brain Age Prediction. arXiv.10.1109/WACV57701.2024.00772 ↗
6. Celebi, M.E., Salekin, M.S., Kim, H., Albarqouni, S., Barata, C., Halpern, A., Tschandl, P., Combalia, M., Liu, Y., and Zamzmi, G. (2023, January 8–12). Global and Local Explanations for Skin Cancer Diagnosis Using Prototypes. Proceedings of the Medical Image Computing and Computer Assisted Intervention—MICCAI 2023 Workshops, Vancouver, BC, Canada.10.1007/978-3-031-47401-9 ↗
7. Hu, B., Vasu, B., and Hoogs, A. (2022, January 3–8). X-MIR: EXplainable Medical Image Retrieval. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA. Available online: https://openaccess.thecvf.com/content/WACV2022/html/Hu_X-MIR_EXplainable_Medical_Image_Retrieval_WACV_2022_paper.html.10.1109/WACV51458.2022.00161 ↗
8. Keane, M.T., Kenny, E.M., Temraz, M., Greene, D., and Smyth, B. (2021). Twin Systems for DeepCBR: A Menagerie of Deep Learning and Case-Based Reasoning Pairings for Explanation and Data Augmentation. arXiv.
9. Thiagarajan, J.J., Narayanaswamy, V., Rajan, D., Liang, J., Chaudhari, A., and Spanias, A. (2021). Designing Counterfactual Generators On-the-Fly, Springer Nature.
10. Training calibration-based counterfactual explainers for deep learning models in medical image analysis10.1038/s41598-021-04529-5 ↗
11. Deep learning generates synthetic cancer histology for explainability and education10.1038/s41698-023-00399-4 ↗
12. Thambawita, V., Hicks, S.A., Isaksen, J., Stensen, M.H., Haugen, T.B., Kanters, J., Parasa, S., de Lange, T., Johansen, H.D., and Johansen, D. (2021, January 19–21). DeepSynthBody: The beginning of the end for data deficiency in medicine. Proceedings of the 2021 International Conference on Applied Artificial Intelligence (ICAPAI), Halden, Norway.10.1109/ICAPAI49758.2021.9462062 ↗
13. Explainable artificial intelligence (XAI) in deep learning-based medical image analysis10.1016/j.media.2022.102470 ↗
14. Isola, P., Zhu, J.-Y., Zhou, T., and Efros, A.A. (2018). Image-to-Image Translation with Conditional Adversarial Networks. arXiv.10.1109/CVPR.2017.632 ↗
15. Ribeiro, M.T., Singh, S., and Guestrin, C. (2016). “Why Should I Trust You?”: Explaining the Predictions of Any Classifier. arXiv.10.18653/v1/N16-3020 ↗
16. WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians10.1016/j.compmedimag.2015.02.007 ↗
17. Towards automatic polyp detection with a polyp appearance model10.1016/j.patcog.2012.03.002 ↗
18. Toward embedded detection of polyps in WCE images for early diagnosis of colorectal cancer10.1007/s11548-013-0926-3 ↗
19. Jha, D., Smedsrud, P.H., Riegler, M.A., Halvorsen, P., de Lange, T., Johansen, D., and Johansen, H.D. (2019). Kvasir-SEG: A Segmented Polyp Dataset. arXiv.10.1007/978-3-030-37734-2_37 ↗
20. Bernal, J.J., Histace, A., Masana, M., Angermann, Q., Sánchez-Montes, C., Rodriguez, C., Hammami, M., Garcia-Rodriguez, A., Córdova, H., and Romain, O. (2018, January 17–20). Polyp Detection Benchmark in Colonoscopy Videos using GTCreator: A Novel Fully Configurable Tool for Easy and Fast Annotation of Image Databases. Proceedings of the 32nd CARS Conference, Berlin, Germany. Available online: https://hal.science/hal-01846141.
21. A survey on Image Data Augmentation for Deep Learning10.1186/s40537-019-0197-0 ↗
22. Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv.10.1007/978-3-319-24574-4_28 ↗
23. Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative Adversarial Networks. arXiv.
24. He, X., and Cheng, J. (2022). Revisiting L1 Loss in Super-Resolution: A Probabilistic View and Beyond. arXiv.
25. Kato, S., and Hotta, K. (2021). MSE Loss with Outlying Label for Imbalanced Classification. arXiv.
26. Johnson, J., Alahi, A., and Fei-Fei, L. (2016, January 8–16). Perceptual Losses for Real-Time Style Transfer and Super-Resolution. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherland.10.1007/978-3-319-46475-6_43 ↗
27. Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009, January 20–25). ImageNet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.10.1109/CVPR.2009.5206848 ↗
28. Kingma, D.P., and Ba, J. (2017). Adam: A Method for Stochastic Optimization. arXiv.
29. Kim, C., Kim, S., Kim, J., Lee, D., and Kim, S. (2021). Automated Learning Rate Scheduler for Large-batch Training. arXiv.
30. Orr, G.B., and Müller, K.-R. (1998). Early Stopping—But When?. Neural Networks: Tricks of the Trade, Springer.10.1007/3-540-49430-8 ↗
31. Tan, M., and Le, Q.V. (2020). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv.
32. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv.
33. Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22–29). Grad-Cam: Visual Explanations From Deep Networks via Gradient-Based Localization. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.74 ↗