SAM-OCTA: A Fine-Tuning Strategy for Applying Foundation Model to OCTA Image Segmentation Tasks
This work addresses segmentation challenges in medical imaging for OCTA analysis, offering an incremental improvement by adapting existing foundation models to a specific domain.
The paper tackles the problem of overfitting in optical coherence tomography angiography (OCTA) image segmentation due to limited supervised datasets by fine-tuning a foundation model with low-rank adaptation and prompt point generation, achieving state-of-the-art performance on the OCTA-500 dataset, including effective artery-vein segmentation not well-solved previously.
In the analysis of optical coherence tomography angiography (OCTA) images, the operation of segmenting specific targets is necessary. Existing methods typically train on supervised datasets with limited samples (approximately a few hundred), which can lead to overfitting. To address this, the low-rank adaptation technique is adopted for foundation model fine-tuning and proposed corresponding prompt point generation strategies to process various segmentation tasks on OCTA datasets. This method is named SAM-OCTA and has been experimented on the publicly available OCTA-500 dataset. While achieving state-of-the-art performance metrics, this method accomplishes local vessel segmentation as well as effective artery-vein segmentation, which was not well-solved in previous works. The code is available at: https://github.com/ShellRedia/SAM-OCTA.