The code provides an implementation of the CMAC net described in the paper: Haowei Chen, Ming Yin, Yi Guo, Toufique Ahmed Soomro, CMAC-Net: Cascade Multi-Scale Attention Convolution Network for diabetic retinopathy lesion segmentation, Biomedical Signal Processing and Control, Volume 112, Part B, 2026, 108484, ISSN 1746-8094, https://doi.org/10.1016/j.bspc.2025.108484. (https://www.sciencedirect.com/science/article/pii/S1746809425009954)

It also includes two datasets, the DDR segmentation dataset and the IDRiD. The DDR segmentation dataset was provided by and can be found at: LI2019, "Diagnostic Assessment of Deep Learning Algorithms for Diabetic Retinopathy Screening", "Tao Li and Yingqi Gao and Kai Wang and Song Guo and Hanruo Liu and Hong Kang", "Information Sciences","501","511 - 522","2019","0020-0255","https://doi.org/10.1016/j.ins.2019.06.011","http://www.sciencedirect.com/science/article/pii/S0020025519305377", Github: https://github.com/nkicsl/DDR-dataset/blob/master/README.md

The IDRiD can be found at: https://www.kaggle.com/datasets/aaryapatel98/indian-diabetic-retinopathy-image-dataset