Applied Explainable Artificial Intelligence (XAI) in the classification of retinal images for support in the diagnosis of Glaucoma

• Cleverson Marques Vieira UFSJ
• Marcus Vinícius De Castro Oliveira UFSJ
• Marcelo De Paiva Guimarães USP
• Leonardo Rocha UFSJ
• Diego Roberto Colombo Dias UFSJ

Resumo

Machine learning models have become ubiquitous across various domains, revolutionizing disease diagnosis and offering remarkable applications in healthcare. In particular, the use of artificial intelligence techniques has significantly transformed the field of ophthalmology, aiding in the early detection of neurodegenerative eye diseases like glaucoma through image classification. However, the lack of explainability in model decisions poses a substantial barrier to their widespread adoption in clinical practice. This research addresses this limitation by exploring and applying explainable artificial intelligence (XAI) techniques to different convolutional neural network (CNN) architectures for glaucoma classification. Our study focuses on providing ophthalmologists with robust resources for human interpretation and supporting clinical diagnosis. We propose an innovative visual interpretation approach called SCIM (SHAP-CAM Interpretable Mapping) and compare its performance against existing techniques, such as Gradient-Weighted Class Activation Mapping (Grad-CAM). Our experiments, conducted on the VGG19 architecture, demonstrate that both Grad-CAM and the novel SCIM approach offer superior resources for human interpretability, further enhancing the potential of CNNs in glaucoma diagnosis.

Palavras-chave: glaucoma, convolutional neural networks, interpretable artificial intelligence, xai

Referências

Namita Agarwal and Saikat Das. 2020. Interpretable Machine Learning Tools: A Survey. In 2020 IEEE Symposium Series on Computational Intelligence (SSCI). 1528–1534. https://doi.org/10.1109/SSCI47803.2020.9308260

Maroof Ahmad, Nikhil Kasukurthi, and Harshit Pande. 2019. Deep Learning for Weak Supervision of Diabetic Retinopathy Abnormalities. In 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). 573–577. https://doi.org/10.1109/ISBI.2019.8759417

Aziz-ur-Rehman, Imtiaz A. Taj, Muhammad Sajid, and Khasan S. Karimov. 2021. An ensemble framework based on Deep CNNs architecture for glaucoma classification using fundus photography. Mathematical Biosciences and Engineering 18, 5 (2021), 5321–5346. https://doi.org/10.3934/mbe.2021270

Muhammad Naseer Bajwa, Muhammad Imran Malik, Shoaib Ahmed Siddiqui, Andreas Dengel, Faisal Shafait, Wolfgang Neumeier, and Sheraz Ahmed. 2019. Two-stage framework for optic disc localization and glaucoma classification in retinal fundus images using deep learning. BMC Medical Informatics and Decision Making 19, 1 (17 Jul 2019), 136. https://doi.org/10.1186/s12911-019-0842-8

José Camara, Alexandre Neto, Ivan Miguel Pires, María Vanessa Villasana, Eftim Zdravevski, and António Cunha. 2022. Literature Review on Artificial Intelligence Methods for Glaucoma Screening, Segmentation, and Classification. Journal of Imaging 8, 2 (2022). https://doi.org/10.3390/jimaging8020019

François Chollet. 2016. Xception: Deep Learning with Depthwise Separable Convolutions. CoRR abs/1610.02357 (2016). arXiv:1610.02357 [link]

Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition. Ieee, 248–255

Andres Diaz-Pinto, Sandra Morales, Valery Naranjo, Thomas Köhler, Jose M. Mossi, and Amparo Navea. 2019. CNNs for automatic glaucoma assessment using fundus images: an extensive validation. BioMedical Engineering OnLine 18, 1 (20 Mar 2019), 29. https://doi.org/10.1186/s12938-019-0649-y

Juan J. Gómez-Valverde, Alfonso Antón, Gianluca Fatti, Bart Liefers, Alejandra Herranz, Andrés Santos, Clara I. Sánchez, and María J. Ledesma-Carbayo. 2019. Automatic glaucoma classification using color fundus images based on convolutional neural networks and transfer learning. Biomed. Opt. Express 10, 2 (Feb 2019), 892–913. https://doi.org/10.1364/BOE.10.000892

Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep Residual Learning for Image Recognition. CoRR abs/1512.03385 (2015). arXiv:1512.03385 [link]

Gao Huang, Zhuang Liu, Laurens van der Maaten, and Kilian Q. Weinberger. 2018. Densely Connected Convolutional Networks. arxiv:1608.06993 [cs.CV]

Yeonwoo Jang, Jaemin Son, Kyu Hyung Park, Sang Jun Park, and Kyu-Hwan Jung. 2018. Laterality Classification of Fundus Images Using Interpretable Deep Neural Network. Journal of Digital Imaging 31, 6 (01 Dec 2018), 923–928. https://doi.org/10.1007/s10278-018-0099-2

Devinder Kumar, Graham W. Taylor, and Alexander Wong. 2019. Discovery Radiomics With CLEAR-DR: Interpretable Computer Aided Diagnosis of Diabetic Retinopathy. IEEE Access 7 (2019), 25891–25896. https://doi.org/10.1109/ACCESS.2019.2893635

Scott M Lundberg and Su-In Lee. 2017. A Unified Approach to Interpreting Model Predictions. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.). Vol. 30. Curran Associates, Inc. [link].

José Martins, Jaime S. Cardoso, and Filipe Soares. 2020. Offline computer-aided diagnosis for Glaucoma detection using fundus images targeted at mobile devices. Computer Methods and Programs in Biomedicine 192 (2020), 105341. https://doi.org/10.1016/j.cmpb.2020.105341

Qier Meng, Yohei Hashimoto, and Shin’ichi Satoh. 2020. How to Extract More Information With Less Burden: Fundus Image Classification and Retinal Disease Localization With Ophthalmologist Intervention. IEEE Journal of Biomedical and Health Informatics 24, 12 (2020), 3351–3361. https://doi.org/10.1109/JBHI.2020.3011805

Christoph Molnar. 2022. Interpretable Machine Learning (2 ed.). [link]

Sajid Nazir, Diane M. Dickson, and Muhammad Usman Akram. 2023. Survey of explainable artificial intelligence techniques for biomedical imaging with deep neural networks. Computers in Biology and Medicine 156 (2023), 106668. https://doi.org/10.1016/j.compbiomed.2023.106668

Mohammad Norouzifard, Ali Nemati, Hamid GholamHosseini, Reinhard Klette, Kouros Nouri-Mahdavi, and Siamak Yousefi. 2018. Automated Glaucoma Diagnosis Using Deep and Transfer Learning: Proposal of a System for Clinical Testing. In 2018 International Conference on Image and Vision Computing New Zealand (IVCNZ). 1–6. https://doi.org/10.1109/IVCNZ.2018.8634671

Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. Why Should I Trust You?: Explaining the Predictions of Any Classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (San Francisco, California, USA) (KDD ’16). Association for Computing Machinery, New York, NY, USA, 1135–1144. https://doi.org/10.1145/2939672.2939778

Mhd Hasan Sarhan, M. Ali Nasseri, Daniel Zapp, Mathias Maier, Chris P. Lohmann, Nassir Navab, and Abouzar Eslami. 2020. Machine Learning Techniques for Ophthalmic Data Processing: A Review. IEEE Journal of Biomedical and Health Informatics 24, 12 (2020), 3338–3350. https://doi.org/10.1109/JBHI.2020.3012134

Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra. 2017. Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization. In Proceedings of the IEEE International Conference on Computer Vision (ICCV)

Ali Serener and Sertan Serte. 2019. Transfer Learning for Early and Advanced Glaucoma Detection with Convolutional Neural Networks. In 2019 Medical Technologies Congress (TIPTEKNO). 1–4. https://doi.org/10.1109/TIPTEKNO.2019.8894965

Thisara Shyamalee and Dulani Meedeniya. 2022. CNN Based Fundus Images Classification For Glaucoma Identification. In 2022 2nd International Conference on Advanced Research in Computing (ICARC). 200–205. https://doi.org/10.1109/ICARC54489.2022.9754171

Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. arxiv:1409.1556 [cs.CV]

Syna Sreng, Noppadol Maneerat, Kazuhiko Hamamoto, and Khin Yadanar Win. 2020. Deep Learning for Optic Disc Segmentation and Glaucoma Diagnosis on Retinal Images. Applied Sciences 10, 14 (2020). https://doi.org/10.3390/app10144916

Ana-Maria Stefan, Elena-Anca Paraschiv, Silvia Ovreiu, and Elena Ovreiu. 2020. A Review of Glaucoma Detection from Digital Fundus Images using Machine Learning Techniques., 4 pages. https://doi.org/10.1109/EHB50910.2020.9280218

Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, and Zbigniew Wojna. 2015. Rethinking the Inception Architecture for Computer Vision. arxiv:1512.00567 [cs.CV]

Luke Taylor and Geoff Nitschke. 2017. Improving Deep Learning using Generic Data Augmentation. CoRR abs/1708.06020 (2017). arXiv:1708.06020 [link]

Kaveri A. Thakoor, Xinhui Li, Emmanouil Tsamis, Paul Sajda, and Donald C. Hood. 2019. Enhancing the Accuracy of Glaucoma Detection from OCT Probability Maps using Convolutional Neural Networks. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 2036–2040. https://doi.org/10.1109/EMBC.2019.8856899

Bas H.M. van der Velden, Hugo J. Kuijf, Kenneth G.A. Gilhuijs, and Max A. Viergever. 2022. Explainable artificial intelligence (XAI) in deep learning-based medical image analysis. Medical Image Analysis 79 (2022), 102470. https://doi.org/10.1016/j.media.2022.102470

Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. 2016. Learning Deep Features for Discriminative Localization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Kang Zhou, Shenghua Gao, Jun Cheng, Zaiwang Gu, Huazhu Fu, Zhi Tu, Jianlong Yang, Yitian Zhao, and Jiang Liu. 2020. Sparse-Gan: Sparsity-Constrained Generative Adversarial Network for Anomaly Detection in Retinal OCT Image. In 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI). 1227–1231. https://doi.org/10.1109/ISBI45749.2020.9098374