MTCSNN: Multi-task Clinical Siamese Neural Network for Diabetic Retinopathy Severity Prediction
This work addresses diabetic retinopathy severity prediction for medical diagnosis, but it is incremental as it builds on existing methods by adding ordinal information and multi-task learning.
The paper tackles the problem of diabetic retinopathy severity prediction by proposing MTCSNN, a multi-task clinical Siamese neural network that incorporates ordinal label information and a regression task, resulting in improved AUC and accuracy compared to benchmark models like ResNet-18, 34, and 50 on the RetinaMNIST dataset.
Diabetic Retinopathy (DR) has become one of the leading causes of vision impairment in working-aged people and is a severe problem worldwide. However, most of the works ignored the ordinal information of labels. In this project, we propose a novel design MTCSNN, a Multi-task Clinical Siamese Neural Network for Diabetic Retinopathy severity prediction task. The novelty of this project is to utilize the ordinal information among labels and add a new regression task, which can help the model learn more discriminative feature embedding for fine-grained classification tasks. We perform comprehensive experiments over the RetinaMNIST, comparing MTCSNN with other models like ResNet-18, 34, 50. Our results indicate that MTCSNN outperforms the benchmark models in terms of AUC and accuracy on the test dataset.