Abstract
Visual explanations have the potential to improve our understanding of deep learning models and their decision-making process, which is critical for building transparent, reliable, and trustworthy AI systems. However, existing visualization methods have limitations, including their reliance on categorical labels to identify regions of interest, which may be inaccessible during model deployment and lead to incorrect diagnoses if an incorrect label is provided. To address this issue, we propose a novel category-independent visual explanation method called Hessian-CIAM. Our algorithm uses the Hessian matrix, which is the second-order derivative of the activation function, to weigh the activation weight in the last convolutional layer and generate a region of interest heatmap at inference time. We then apply an SVD-based post-process to create a smoothed version of the heatmap. By doing so, our algorithm eliminates the need for categorical labels and modifications to the deep learning model. To evaluate the effectiveness of our proposed method, we compared it to seven state-of-the-art algorithms using the Chestx-ray8 dataset. Our approach achieved a 55% higher IoU measurement than classical GradCAM and a 17% higher IoU measurement than EigenCAM. Moreover, our algorithm obtained a Judd AUC score of 0.70 on the glaucoma retinal image database, demonstrating its potential applicability in various medical applications. In summary, our category-independent visual explanation method, Hessian-CIAM, generates high-quality region of interest heatmaps that are not dependent on categorical labels, making it a promising tool for improving our understanding of deep learning models and their decision-making process, particularly in medical applications.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
the dataset is obtained from https://github.com/smilell/AG-CNN.
References
Bylinskii, Z., Judd, T., Oliva, A., Torralba, A., Durand, F.: What do different evaluation metrics tell us about saliency models? arXiv preprint arXiv:1604.03605 (2016)
Cao, C., et al.: Look and think twice: capturing top-down visual attention with feedback convolutional neural networks. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 2956–2964 (2015)
Chattopadhay, A., Sarkar, A., Howlader, P., Balasubramanian, V.N.: Grad-CAM++: generalized gradient-based visual explanations for deep convolutional networks. In: IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 839–847 (2018)
COMMISSION, E.: Proposal for a regulation of the European parliament and of the council (2021). https://artificialintelligenceact.eu/the-act/
Draelos, R.L., Carin, L.: HiResCAM: faithful location representation in visual attention for explainable 3D medical image classification. arXiv preprint arXiv:2011.08891 (2020)
Draelos, R.L., Carin, L.: Explainable multiple abnormality classification of chest CT volumes. Artif. Intell. Med. 132(C), 102372 (2022)
Guo, Y., Liu, Y., Oerlemans, A., Lao, S., Wu, S., Lew, M.S.: Deep learning for visual understanding: A review. Neurocomputing 187, 27–48 (2016). recent Developments on Deep Big Vision
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Hohman, F., Kahng, M., Pienta, R., Chau, D.H.: Visual analytics in deep learning: an interrogative survey for the next frontiers. IEEE Trans. Visual Comput. Graphics 25(8), 2674–2693 (2019). https://doi.org/10.1109/TVCG.2018.2843369
Irvin, J., et al.: Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 590–597 (2019)
Ishikawa, G., Xu, R., Ohya, J., Iwata, H.: Detecting a fetus in ultrasound images using Grad-CAM and locating the fetus in the uterus. In: ICPRAM, pp. 181–189 (2019)
Jiang, P.T., Zhang, C.B., Hou, Q., Cheng, M.M., Wei, Y.: Layercam: exploring hierarchical class activation maps for localization. IEEE Trans. Image Process. 30, 5875–5888 (2021)
Li, L., Wang, B., Verma, M., Nakashima, Y., Kawasaki, R., Nagahara, H.: SCOUTER: slot attention-based classifier for explainable image recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 1046–1055 (2021)
Li, L., Xu, M., Wang, X., Jiang, L., Liu, H.: Attention based glaucoma detection: a large-scale database and CNN model. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Locatello, F., et al..: Object-centric learning with slot attention. In: Advances in Neural Information Processing Systems (NIPS), vol. 33, pp. 11525–11538 (2020)
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems (NIPS), pp. 4765–4774. Curran Associates, Inc. (2017)
Muhammad, M.B., Yeasin, M.: Eigen-CAM: class activation map using principal components. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1–7. IEEE (2020)
Oquab, M., Bottou, L., Laptev, I., Sivic, J.: Is object localization for free? weakly-supervised learning with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 685–694 (2015)
Pearlmutter, B.A.: Fast exact multiplication by the hessian. Neural Comput. 6(1), 147–160 (1994)
Petsiuk, V., Das, A., Saenko, K.: RISE: randomized input sampling for explanation of black-box models. arXiv preprint arXiv:1806.07421 (2018)
Poplin, R., et al.: Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nature Biomed. Eng. 2(3), 158–164 (2018)
Ramaswamy, H.G., et al.: Ablation-CAM: visual explanations for deep convolutional network via gradient-free localization. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 983–991 (2020)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 618–626 (2017)
Wang, H., et al.: Score-CAM: score-weighted visual explanations for convolutional neural networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 24–25 (2020)
Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., Summers, R.M.: Chestx-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2097–2106 (2017)
Yang, C., Rangarajan, A., Ranka, S.: Visual explanations from deep 3D convolutional neural networks for Alzheimer’s disease classification. In: AMIA Annual Symposium Proceedings, vol. 2018, p. 1571. American Medical Informatics Association (2018)
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2921–2929 (2016)
Acknowledgements
This work is supported by the Agency for Science, Technology and Research (A*STAR) under its RIE2020 Health and Biomedical Sciences (HBMS) Industry Alignment Fund Pre-Positioning (IAF-PP) Grant No. H20c6a0031, the National Research Foundation, Singapore under its AI Singapore Programme (AISG Award No: AISG2-TC-2021-003), the Agency for Science, Technology and Research (A*STAR) through its AME Programmatic Funding Scheme Under Project A20H4b0141, A*STAR Central Research Fund “A Secure and Privacy Preserving AI Platform for Digital Health”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Qian, Y. et al. (2023). Category-Independent Visual Explanation for Medical Deep Network Understanding. In: Greenspan, H., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. MICCAI 2023. Lecture Notes in Computer Science, vol 14221. Springer, Cham. https://doi.org/10.1007/978-3-031-43895-0_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-43895-0_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43894-3
Online ISBN: 978-3-031-43895-0
eBook Packages: Computer ScienceComputer Science (R0)