Improve Robustness of Eye Disease Detection by including Learnable Probabilistic Discrete Latent Variables into Machine Learning Models

Prabhakaran, Anirudh, Xiao, YeKun, Cheng, Ching-Yu, Liu, Dianbo

arXiv.org Artificial Intelligence 

Ocular diseases, ranging from diabetic retinopathy to glaucoma, present a significant public health challenge due to their prevalence and potential for causing vision impairment. Early and accurate diagnosis is crucial for effective treatment and management.In recent years, deep learning models have emerged as powerful tools for analysing medical images, including ocular imaging . However, challenges persist in model interpretability and uncertainty estimation, which are critical for clinical decision-making. This study introduces a novel application of GFlowOut, leveraging the probabilistic framework of Generative Flow Networks (GFlowNets) to learn the posterior distribution over dropout masks, for the classification and analysis of ocular diseases using eye fundus images. We develop a robust and generalizable method that utilizes GFlowOut integrated with ResNet18 and ViT models as backbone in identifying various ocular conditions. This study employs a unique set of dropout masks - none, random, bottomup, and topdown - to enhance model performance in analyzing ocular images. Our results demonstrate that the bottomup GFlowOut mask significantly improves accuracy, outperforming the traditional dropout approach.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found