Explainable Fuzzy Learning for Cardiac Segmentation in 3D Short-Axis MRI
Abstract
Accurate segmentation in short-axis cardiac MRI is crucial for extracting pa-rameters to diagnose cardiovascular diseases. However, deep learning models often use Max or Average pooling to reduce feature map size, risking loss of important information. In addition, most current research focuses mainly on the segmentation accuracy of machine learning models, while lacking inter-pretation of the segmentation results- a critical factor for clinical applica-tions. In this study, we propose a fuzzy deep learning model called 3DMFL-Net, which combines Explainable AI (XAI) techniques to segment cardiac structures including the Left Ventricle, Myocardium, and Right Ventricle from 3D short axis MRI images, while also providing interpretation of the segmentation results. The model adopts a 3D fuzzy pooling method to re-place traditional pooling methods. The 3D fuzzy pooling leverages fuzzy logic along with a Gaussian membership function to identify important features within the pooling window, allowing reduction of the feature map size while preserving essential information. To visualize and interpret the model’s deci-sions, we apply XAI with the 3D Grad-CAM method to generate heatmaps that highlight the important image regions involved in the segmentation process of the proposed model. The proposed model is evaluated on the M&Ms-2020 dataset, which includes multiple 3D cardiac MRI scans across various disease groups and is provided by different device vendors. The re-sults show that the Dice coefficient reaches 84.6% for the left ventricle, 76.6% for the myocardium, and 79.5% for the right ventricle. The proposed method suits intelligent healthcare deployment and helps clinicians trust segmentation outcomes.
References
2. Chen, C., Qin, C., Qiu, H., Tarroni, G., Duan, J., Bai, W., & Rueckert, D. Deep learning for cardiac image segmentation: a review. Frontiers in cardiovascular medicine, 7, 25, (2020).
3. Yuniarno, E. M., Purnama, I. K. E., Aritsugi, M., & Purnomo, M. H. . Investigating diverse loss functions for myocardium ring segmentation in Cardiac Magnetic Resonance images using fuzzy pooling. Array, 26, 100382, (2025).
4. Li, L., Zimmer, V. A., Ding, W., Wu, F., Huang, L., Schnabel, J. A., & Zhuang, X. Random style transfer based domain generalization networks integrating shape and spatial information. In Statistical Atlases and Computational Models of the Heart. M&Ms and EMIDEC Challenges: 11th International Workshop, STACOM 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 4, 2020, Revised Selected Papers 11 (pp. 208-218). Springer International Publishing, (2021).
5. Silva, I. F. S. D., Silva, A. C., Paiva, A. C. D., Gattass, M., & Cunha, A. M. A Multi Stage Automatic Method Based on a Combination of Fully Convolutional Networks for Cardiac Segmentation in Short-Axis MRI. Applied Sciences (2076-3417), 14(16), (2024).
6. DLi, J., Lv, Y., Xu, L., & Qi, L. An Unsupervised Domain Adaptation Model Based on Multi-Level Joint Alignment for Multi-Modal Cardiac Image Segmentation. Procedia Computer Science, 226, 106-112, (2023).
7. Campello, V. M., Gkontra, P., Izquierdo, C., Martin-Isla, C., Sojoudi, A., Full, P. M., & Lekadir, K. Multi-centre, multi-vendor and multi-disease cardiac segmentation: the M&Ms challenge. IEEE Transactions on Medical Imaging, 40(12), 3543-3554, (2021).
8. Flores-Alonso, S. I., Tovar-Corona, B., & Luna-García, R. Deep learning algorithm for heart valve diseases assisted diagnosis. Applied Sciences, 12(8), 3780, (2022).
9. Irshad, M., Yasmin, M., Sharif, M. I., Rashid, M., Sharif, M. I., & Kadry, S. A novel light u-net model for left ventricle segmentation using MRI. Mathematics, 11(14), 3245, (2023).
10. Gunashekar, D. D., Bielak, L., Hägele, L., Oerther, B., Benndorf, M., Grosu, A. L., & Bock, M. Explainable AI for CNN-based prostate tumor segmentation in multi parametric MRI correlated to whole mount histopathology. Radiation Oncology, 17(1), 65, (2022).
11. J. M. Wolterink, T. Leiner, M. A. Viergever and I. Isgum. Automatic Segmentation and Disease. 4, 12, (2024).
12. V. M. Rao, Z. Wan, S. Arabshahi, D. J. Ma, P.-Y. Lee, Y. Tian, X. Zhang, A. F. Laine and J. Guo. Improving Across-Dataset Brain Tissue Segmentation Using Transformer. 31 1 (2023).
13. Chang, Y., Song, B., Jung, C., & Huang, L. Automatic segmentation and cardiopathy classification in cardiac MRI images based on deep neural networks. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), (15 Apr. 2018).
14. Wolterink, J. M., Leiner, T., Viergever, M. A., & Isgum, I. Automatic Segmentation and Disease, (3 Aug. 2020).
15. Tao, L., Tian, Y., Zhao, S., Huang, X., & Qingjun, W. Residual Convolutional Neural Network for Cardiac Image Segmentation and Heart Disease Diagnosis. IEEE Access, 8, (2020).
16. Isensee, F., Jaeger, P. F., Full, P. M., Wolf, I., Engelhardt, S., & Maier-Hein, K. H. Automatic Cardiac Disease Assessment on cine-MRI via Time-Series Segmentation and Domain Specific Features, (25 Jan. 2018).
17. Wibowo, A., Triadyaksa, P., Sugiharto, A., Sarwoko, E. A., Nugroho, F. A., Arai, H., &Kawakubo,M.Cardiac Disease Classification Using Two-Dimensional. Journal of Imaging, p. 194, (2022).
18. Cepova, L., Elangovan, M., Ramesh, J. N., Chohan, M. K., Verma, A., & Mohammad, F. Improving privacy preserving multi-faceted long short term memory for accurate evaluation of encrypted time series MRI images in heart disease. Scientific Reports, 14, (30 Aug. 2024).
19. Liu, X., Thermos, S., Chartsias, A., ONeil, A., & Tsaftaris, S. A. Disentangled representations for domain-generalized cardiac segmentation. In International Workshop on Statistical Atlases and Computational Models of the Heart (pp. 187-195). Cham: Springer International Publishing, (2020).
20. Scannell, C. M., Chiribiri, A., & Veta, M. Domain-adversarial learning for multicentre, multi-vendor, and multi-disease cardiac MR image segmentation. In International Workshop on Statistical Atlases and Computational Models of the Heart (pp. 228-237). Cham: Springer International Publishing, (2020).
