Computer Aided Diagnosis and Out-of-Distribution Detection in Glaucoma Screening Using Color Fundus Photography
This work addresses the challenge of making glaucoma screening more reliable in real-world scenarios, though it appears incremental as it builds on existing AI methods for medical imaging.
The authors tackled the problem of robust glaucoma screening from color fundus photography by developing a method that classifies images as referable glaucoma or no referable glaucoma using convolutional neural networks, and introduced an inference-time out-of-distribution detection method to identify ungradable images.
Artificial Intelligence for RObust Glaucoma Screening (AIROGS) Challenge is held for developing solutions for glaucoma screening from color fundus photography that are robust to real-world scenarios. This report describes our method submitted to the AIROGS challenge. Our method employs convolutional neural networks to classify input images to "referable glaucoma" or "no referable glaucoma". In addition, we introduce an inference-time out-of-distribution (OOD) detection method to identify ungradable images. Our OOD detection is based on an energy-based method combined with activation rectification.