MediSight FusionNet: A General Medical Deep Learning Model for Myopic Maculopathy Classification

Myopic maculopathy is a highly myopic retinal disease that often occurs in patients with high myopia, serving as a major cause of visual impairment and blindness in numerous countries. Currently, fundus images serve as a prevalent diagnostic tool for myopic maculopathy. However, its efficacy relies on the expertise of clinicians, making the process labor-intensive. Thus, we propose a model specifically designed for the image classification of myopic maculopathy, named MediSight Fusion- Net, which achieves outstanding performance on the test dataset. To achieve a finer-grained classification of myopic maculopathy in fundus images, we have innovatively and for the first time proposed the use of ArcFace loss and Ranking loss in medical image classification. Then, we introduce a weak label strategy that effectively mitigates overfitting. Our MediSight FusionNet model achieves significantly improved results on the test dataset and can be easily used for various datasets and medical image tasks. We conduct a series of experiments in the MMAC2023 challenge and its datasets. In the validation dataset, our average performance metric reaches 91.36%. In the test dataset, the performance of our MediSight FusionNet model improves to 88.23%. The codes allowing replication of this study have been made publicly available at https://github.com/qingtian5/rnrnac_t1.