SAM-OCTA2: Layer Sequence OCTA Segmentation with Fine-tuned Segment Anything Model 2
This work addresses the problem of precise 3D segmentation in OCTA imaging for medical analysis, representing an incremental improvement by adapting an existing model to a specific domain.
The paper tackled the challenge of segmenting objects in 3D optical coherence tomography angiography (OCTA) volumes by fine-tuning the Segment Anything Model 2 with low-rank adaptation, achieving state-of-the-art performance in segmenting the foveal avascular zone on 2D en-face images and effectively tracking local vessels across scanning layers.
Segmentation of indicated targets aids in the precise analysis of optical coherence tomography angiography (OCTA) samples. Existing segmentation methods typically perform on 2D projection targets, making it challenging to capture the variance of segmented objects through the 3D volume. To address this limitation, the low-rank adaptation technique is adopted to fine-tune the Segment Anything Model (SAM) version 2, enabling the tracking and segmentation of specified objects across the OCTA scanning layer sequence. To further this work, a prompt point generation strategy in frame sequence and a sparse annotation method to acquire retinal vessel (RV) layer masks are proposed. This method is named SAM-OCTA2 and has been experimented on the OCTA-500 dataset. It achieves state-of-the-art performance in segmenting the foveal avascular zone (FAZ) on regular 2D en-face and effectively tracks local vessels across scanning layer sequences. The code is available at: https://github.com/ShellRedia/SAM-OCTA2.