Exploring Explainable Artificial Intelligence Techniques for Diabetic Retinopathy Detection using Grad-CAM and VGG16 Framework
Keywords:
Deep learning, Diabetic retinopathy, Grad- CAM, VGG16 architecture, Visualize attention, XAIAbstract
Since diabetic retinopathy (DR) is one of the main causes of blindness in the world, avoiding vision loss requires early detection. Although deep learning models have demonstrated significant promise in the diagnosis of DR using retinal pictures, they frequently operate as “black boxes,” which means that it is difficult to understand how they make decisions. Particularly when it comes to making important healthcare decisions, this lack of openness may erode confidence in AI-based medical solutions. Our research uses Explainable Artificial Intelligence (XAI) techniques to improve the interpretability of a deep learning model for DR detection in order to overcome this difficulty. We classify retinal images using a pre-trained convolutional neural network called VGG16.To enhance transparency, we incorporate Gradient-weighted Class Activation Mapping (GradCAM), a technique that generates visual heatmaps, highlighting the regions of the image that influenced the model’s decision. By overlaying these heatmaps onto the original retinal images, we provide a clear, visual representation of what the model “sees” when making a classification. Our approach not only improves accuracy but also enhances trust in AI-based DR diagnosis. The accuracy of the VGG16 model was 72%, and Grad CAM successfully identified the crucial regions linked to DR. Deep learning models are simpler to incorporate into clinical practice thanks to these visual explanations that assist medical personnel in validating AI-generated predictions. Our research helps to improve patient outcomes by bridging the gap between interpretability and AI, which increases confidence among healthcare practitioners and makes AI-assisted medical diagnosis more transparent and trustworthy..
Downloads
Metrics
References
J. Zhou and B. Chen, “Retinal cell damage in diabetic retinopathy,” Cells, vol. 12, no. 9, p. 1342, 2023.
B. P. Makala, M. Kumar, and B. Sirisha, “Survey on automatic detection of diabetic retinopathy screening,” in 2022 11th International Conference on System Modeling & Advancement in Research Trends (SMART). IEEE, 2022, pp. 1214–1220.
R. S. Gound, B. M. Sundaram, S. K. BV, P. A. Azmat, M. N. U. Habib, and A. Garg, “Drs-unet: A deep learning approach for dia- betic retinopathy detection and segmentation from fundus images,” in 2023 4th International Conference for Emerging Technology (INCET). IEEE, 2023, pp. 1–5.
A. Bianchi, A. Di Marco, F. Marzi, G. Stilo, C. Pellegrini, S. Masi, Mengozzi, A. Virdis, M. S. Nobile, and M. Simeoni, “Trustworthy machine learning predictions to support clinical research and deci- sions,” in 2023 IEEE 36th International Symposium on Computer- Based Medical Systems (CBMS). IEEE, 2023, pp. 231–234.
R. Gargeya and T. Leng, “Automated identification of diabetic retinopathy using deep learning,” Ophthalmology, vol. 124, no. 7, pp. 962–969, 2017.
N. K. Baskaran and T. Mahesh, “Performance analysis of deep learning based segmentation of retinal lesions in fundus images,” in 2023 Second International Conference on Electronics and Renewable Systems (ICEARS). IEEE, 2023, pp. 1306–1313.
M. Garouani and M. Bouneffa, “Unlocking the black box: Towards interactive explainable automated machine learning,” in International Conference on Intelligent Data Engineering and Automated Learning. Springer, 2023, pp. 458–469.
Z. Chen and Q. Sun, “Extracting class activation maps from non- discriminative features as well,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 3135–3144.
Y. Liao, Y. Gao, and W. Zhang, “Feature activation map: Visual explanation of deep learning models for image classification,” arXiv preprint arXiv:2307.05017, 2023.
A. M. Barhoom, M. R. J. Al-Hiealy, and S. S. Abu-Naser, “Bone abnormalities detection and classification using deep learning-vgg16 algorithm,” Journal of Theoretical and Applied Information Technol- ogy, vol. 100, no. 20, pp. 6173–6184, 2022.
P. Gayathri, A. Dhavileswarapu, S. Ibrahim, R. Paul, and R. Gupta, “Exploring the potential of vgg-16 architecture for accurate brain tu- mor detection using deep learning,” Journal of Computers, Mechanical and Management, vol. 2, no. 2, pp. 23 056–23 056, 2023.
F. A. Torghabeh, Y. Modaresnia, and M. M. Khalilzadeh, “Effective- ness of learning rate in dementia severity prediction using vgg16,” Biomedical Engineering: Applications, Basis and Communications, vol. 35, no. 03, p. 2350006, 2023.
S. Goel, S. Gupta, A. Panwar, S. Kumar, M. Verma, S. Bourouis, and M. A. Ullah, “Deep learning approach for stages of severity clas- sification in diabetic retinopathy using color fundus retinal images,” Mathematical Problems in Engineering, vol. 2021, pp. 1–8, 2021.
T. Qamar and N. Z. Bawany, “Understanding the black-box: towards interpretable and reliable deep learning models,” PeerJ Computer Science, vol. 9, p. e1629, 2023.
V. Hassija, V. Chamola, A. Mahapatra, A. Singal, D. Goel, K. Huang, S. Scardapane, I. Spinelli, M. Mahmud, and A. Hussain, “Interpreting black-box models: a review on explainable artificial intelligence,” Cognitive Computation, vol. 16, no. 1, pp. 45–74, 2024.
M. K. Singh and B. Kumar, “Fine tuning the pre-trained convolutional neural network models for hyperspectral image classification using transfer learning,” in Computer Vision and Robotics: Proceedings of CVR 2022. Springer, 2023, pp. 271–283.
A. Abhishek, S. D. Deb, R. K. Jha, R. Sinha, and K. Jha, “Classi- fication of leukemia using fine tuned vgg16,” in 2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT). IEEE, 2023, pp. 1–5.
P. Borugadda, R. Lakshmi, and S. Sahoo, “Transfer learning vgg16 model for classification of tomato plant leaf diseases: A novel approach for multi-level dimensional reduction.” Pertanika Journal of Science & Technology, vol. 31, no. 2, 2023.
J. Stodt, M. Madan, C. Reich, L. Filipovic, and T. Ilijas, “A study on the reliability of visual xai methods for x-ray images,” Healthcare Transformation with Informatics and Artificial Intelligence, vol. 305, p. 32, 2023.
S. K. Mandala, “Xai renaissance: Redefining interpretability in medical diagnostic models,” arXiv preprint arXiv:2306.01668, 2023.
R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and Batra, “Grad-cam: visual explanations from deep networks via gradient-based localization,” International journal of computer vision, vol. 128, pp. 336–359, 2020.
K. Kumar and K. Jyoti, “Recent advancements in grad-cam and variants: Enhancing brain tumor detection, segmentation, and classifi- cation,” 2024.
A. Bhatnagar, “Attention-driven convolutional neural network for accurate covid-19 diagnosis in medical imaging with gradcam-based interpretability,” in 2024 International Conference on Decision Aid Sciences and Applications (DASA). IEEE, 2024, pp. 1–7.
J. D. Bodapati, A. Vijay, and N. Veeranjaneyulu, “Brain tumor detec- tion using deep features in the latent space.” Inge´nierie des Syste`mes d’Information, vol. 25, no. 2, 2020.
Q. H. Nguyen, R. Muthuraman, L. Singh, G. Sen, A. C. Tran, B. P. Nguyen, and M. Chua, “Diabetic retinopathy detection using deep learning,” in Proceedings of the 4th international conference on machine learning and soft computing, 2020, pp. 103–107.
D. Pruthviraja, B. Anil, and C. Sowmyarani, “Efficient local cloud- based solution for diabetic retinopathy detection,” International Jour- nal of Web-Based Learning and Teaching Technologies (IJWLTT), vol. 16, no. 3, pp. 39–46, 2021.
Q. Zhang, L. Rao, and Y. Yang, “A novel visual interpretability for deep neural networks by optimizing activation maps with perturba- tion,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 4, 2021, pp. 3377–3384.
M. M. Islam, “The impact of transfer learning on ai performance across domains,” Journal of Artificial Intelligence General science (JAIGS) ISSN: 3006-4023, vol. 1, no. 1, 2024.
M. Zoric´, M. Sˇtula, I. Markic´, and M. Braovic´, “Transfer learning in building neural network model case study,” in 2024 International Conference on Software, Telecommunications and Computer Networks (SoftCOM). IEEE, 2024, pp. 1–6.
L. Alzubaidi, M. Al-Amidie, A. Al-Asadi, A. J. Humaidi, O. Al- Shamma, M. A. Fadhel, J. Zhang, J. Santamar´ıa, and Y. Duan, “Novel transfer learning approach for medical imaging with limited labeled data,” Cancers, vol. 13, no. 7, p. 1590, 2021.
M. Angriawan, “Transfer learning strategies for fine-tuning pretrained convolutional neural networks in medical imaging,” Research Journal of Computer Systems and Engineering, vol. 4, no. 2, pp. 73–88, 2023.
P. Banerjee and S. Kashyap, “Unlocking transfer learning’s potential in natural language processing: An extensive investigation and evalu- ation,” in 2024 International Conference on Advances in Computing Research on Science Engineering and Technology (ACROSET). IEEE, 2024, pp. 1–7.
N. Jaquier et al., “Transfer learning in robotics: an upcoming break- through,” A review of promises and challenges, 2023.
A. Nadali, B. Zhong, A. Trivedi, and M. Zamani, “Transfer learning for control systems via neural simulation relations,” arXiv preprint arXiv:2412.01783, 2024.
W. Li, Y. P. Park, and K. D. Duc, “Transport-based transfer learning on electronic health records: Application to detection of treatment disparities,” medRxiv, pp. 2024–03, 2024.
A. Alshardan, N. Alruwais, H. Alqahtani, A. Alshuhail, W. S. Al- mukadi, and A. Sayed, “Leveraging transfer learning-driven convolu- tional neural network-based semantic segmentation model for medical image analysis using mri images,” Scientific Reports, vol. 14, no. 1, p. 30549, 2024.
Y. Zhao, H. Zhou, S. Lu, Y. Liu, X. An, and Q. Liu, “Human activity recognition based on non-contact radar data and improved pca method,” Applied Sciences, vol. 12, no. 14, p. 7124, 2022.
H. Kafri, M. Olivieri, F. Antonacci, M. Moradi, A. Sarti, and S. Gan- not, “Grad-cam-inspired interpretation of nearfield acoustic holography using physics-informed explainable neural network,” in ICASSP 2023- 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023, pp. 1–5.
Y. Yang, R. Guo, S. Wu, Y. Wang, J. Zhang, X. Gong, and B. Zhang, “Decom–cam: Tell me what you see, in details! feature-level in- terpretation via decomposition class activation map,” arXiv preprint arXiv:2306.04644, 2023.
.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
