Development of Approaches Based on Deep Neural Networks for Detection and Instance Segmentation of Retinal Lesions

• Carlos Santos IFFar
• Marilton Sanchotene de Aguiar UFPel
• Daniel Welfer UFSM

DOI: https://doi.org/10.5753/sbcas_estendido.2024.1222

Abstract

Diabetic Retinopathy (DR) is one of the leading causes of vision loss and presents fundus lesions in its initial stages, such as microaneurysms, hemorrhages, hard exudates, and soft exudates. Computational models capable of detecting these lesions can support the early diagnosis of the disease and prevent the manifestation of more severe forms of lesions, helping in the screening process and definition of the best form of treatment. However, the detection of microlesions using computational systems is a challenge due to several factors, such as the size and shape of these lesions, the presence of noise and poor contrast in the images, the small number of labeled examples in public DR datasets, and the difficulty of deep learning algorithms in detecting tiny objects due to gradient dissipation during training. Thus, to overcome these problems, this work proposes two new approaches based on image processing techniques, data augmentation, transfer learning, and deep neural networks to support the medical diagnosis of fundus lesions. We trained, adjusted, and evaluated the proposed approaches using different public Diabetic Retinopathy datasets. We partitioned the datasets into sets of training (50%), validation (20%), and test (30%) to carry out the experiments. We used a validation step to fine-tune the hyperparameters and a test step to assess the generalization capacity of the models. The approach to detecting fundus lesions achieved mAP of 0.2630 for the limit of IoU of 0.5 in the validation step using the DDR dataset and Adam optimizer. The approach for segmenting instances of fundus lesions reached mAP of 0.2903 for the limit of IoU of 0.5 in the validation stage using the DDR dataset and Adam optimizer, thus being 10.38% more accurate than the proposed detection approach. The results obtained in the experiments demonstrate that the new approaches presented promising results in detecting fundus lesions associated with DR.

References

Alyoubi, W. L., Abulkhair, M. F., and Shalash, W. M. (2021). Diabetic retinopathy fundus image classification and lesions localization system using deep learning. Sensors, 21(11).

Chakrabarti, R., Harper, C. A., and Keeffe, J. E. (2012). Diabetic retinopathy management guidelines. Expert Review of Ophthalmology, 7(5):417–439.

Dai, L., Wu, L., Li, H., and Cai, C. (2021). A deep learning system for detecting diabetic retinopathy across the disease spectrum. Nature Communications, 12(1).

Li, T., Gao, Y., Wang, K., Guo, S., Liu, H., and Kang, H. (2019). Diagnostic assessment of deep learning algorithms for diabetic retinopathy screening. Information Sciences, 501:511–522.

Mateen, M., Wen, J., Nasrullah, N., Sun, S., and Hayat, S. (2020). Exudate Detection for Diabetic Retinopathy Using Pretrained Convolutional Neural Networks. Complexity, 2020.

Nayak, J., Bhat, P. S., Acharya U, R., Lim, C. M., and Kagathi, M. (2008). Automated identification of diabetic retinopathy stages using digital fundus images. Journal of Medical Systems, 32(2):107–115.

Porwal, P., Pachade, S., Kokare, M., Deshmukh, G., Son, J., and Bae, W. (2020). IDRiD: Diabetic Retinopathy – Segmentation and Grading Challenge. Medical Image Analysis, 59.

Santos, C., De Aguiar, M. S., Welfer, D., and Belloni, B. (2021). Deep neural network model based on one-stage detector for identifying fundus lesions. In Proceedings of the International Joint Conference on Neural Networks (IJCNN), pages 1–8, Shenzhen, China, 18–22 July 2021. IEEE.

Shenavarmasouleh, F., Mohammadi, F. G., Amini, M. H., Taha, T., Rasheed, K., and Arabnia, H. R. (2021). Drdrv3: Complete lesion detection in fundus images using mask r-cnn, transfer learning, and lstm.

Ting, D. S. W., Cheung, G. C. M., and Wong, T. Y. (2016). Diabetic retinopathy: global prevalence, major risk factors, screening practices and public health challenges: a review. Clinical and Experimental Ophthalmology, 44(4):260–277.

Vocaturo, E. and Zumpano, E. (2020). The contribution of AI in the detection of the Diabetic Retinopathy. In Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020, pages 1516–1519, Seoul, Korea, 16–19 December 2020. IEEE.

Wang, H., Yuan, G., and Zhao, X. (2020). Hard exudate detection based on deep model learned information and multi-feature joint representation for diabetic retinopathy screening. Computer Methods and Programs in Biomedicine, 191:105398.

Wong, T. Y., Aiello, L. P., Ferris, F., Gupta, N., Kawasaki, R., Lansingh, V., Maia, M., Mathenge, W., Moreker, S., Mugit, M., Resnikoff, S., Ruamviboonsuk, P., Sun, J., Taylor, H., Verdaguer, J., and Zhao, P. (2017). ICO guidelines for diabetic eye care. Technical report, International Council of Ophthalmology, Brussels, Belgium.