SAMedOCT: Adapting Segment Anything Model (SAM) for Retinal OCT

TL;DR

This paper evaluates the adaptation of the Segment Anything Model (SAM) for retinal OCT scans, demonstrating its potential and limitations in segmenting retinal fluids across diverse datasets and conditions.

Contribution

It provides a comprehensive assessment of SAM's performance on retinal OCT data, highlighting its adaptability and identifying areas for improvement compared to existing methods.

Findings

SAM shows promising segmentation capabilities in retinal OCT images.

SAM's performance varies across different retinal diseases and devices.

It outperforms some existing methods but still lags in certain scenarios.

Abstract

The Segment Anything Model (SAM) has gained significant attention in the field of image segmentation due to its impressive capabilities and prompt-based interface. While SAM has already been extensively evaluated in various domains, its adaptation to retinal OCT scans remains unexplored. To bridge this research gap, we conduct a comprehensive evaluation of SAM and its adaptations on a large-scale public dataset of OCTs from RETOUCH challenge. Our evaluation covers diverse retinal diseases, fluid compartments, and device vendors, comparing SAM against state-of-the-art retinal fluid segmentation methods. Through our analysis, we showcase adapted SAM's efficacy as a powerful segmentation model in retinal OCT scans, although still lagging behind established methods in some circumstances. The findings highlight SAM's adaptability and robustness, showcasing its utility as a valuable tool in retinal OCT image analysis and paving the way for further advancements in this domain.