On the Evaluation and Real-World Usage Scenarios of Deep Vessel Segmentation for Retinography
This work provides practical insights for medical imaging researchers working on retinal vessel segmentation, though it is largely incremental in methodology.
The paper addresses three research gaps in retinal vessel segmentation: demonstrating that simple rescaling techniques from lower-resolution datasets achieve state-of-the-art performance on high-resolution HRF data, showing that most SOTA methods have comparable performance when evaluated consistently, and open-sourcing their pipeline for reproducibility.
We identify and address three research gaps in the field of vessel segmentation for funduscopy. The first focuses on the task of inference on high-resolution fundus images for which only a limited set of ground-truth data is publicly available. Notably, we highlight that simple rescaling and padding or cropping of lower resolution datasets is surprisingly effective. Additionally we explore the effectiveness of semi-supervised learning for better domain adaptation. Our results show competitive performance on a set of common public retinal vessel datasets using a small and light-weight neural network. For HRF, the only very high-resolution dataset currently available, we reach new state-of-the-art performance by solely relying on training images from lower-resolution datasets. The second topic concerns evaluation metrics. We investigate the variability of the F1-score on the existing datasets and report results for recent SOTA architectures. Our evaluation show that most SOTA results are actually comparable to each other in performance. Last, we address the issue of reproducibility by open-sourcing our complete pipeline.