arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.09286cs.CV

SAM-OCTA2:基于微调的Segment Anything Model 2的层序列OCTA分割

SAM-OCTA2: Layer Sequence OCTA Segmentation with Fine-tuned Segment Anything Model 2

Xiang’an Hospital of Xiamen University(厦门大学附属翔安医院)

Xinrun Chen, Chengliang Wang, Haojian Ning, Mengzhan Zhang, Mei Shen, Shiying Li

AI总结:

本研究针对现有OCTA分割方法难以捕捉3D体数据中目标变化的问题,提出SAM-OCTA2方法,通过低秩适配微调SAM 2,结合帧序列提示点生成与稀疏标注策略,在OCTA-500数据集上实现了FAZ分割的SOTA性能及层序列血管追踪。

摘要:

指定目标的分割有助于对光学相干断层扫描血管造影(OCTA)样本进行精准分析。现有分割方法通常针对2D投影目标执行,难以捕捉分割对象在3D体数据中的变化。为解决这一局限,研究采用低秩适配技术微调Segment Anything Model 2(SAM 2),使其能够在OCTA扫描层序列中追踪并分割指定对象。为推进这项工作,研究提出了帧序列中的提示点生成策略,以及用于获取视网膜血管(RV)层掩码的稀疏标注方法。该方法被命名为SAM-OCTA2,已在OCTA-500数据集上开展实验。它在常规2D en-face图像上的黄斑中心凹无血管区(FAZ)分割任务中取得了当前最优性能,并且能在扫描层序列中有效追踪局部血管。代码可在以下网址获取:https://github.com/ShellRedia/SAM-OCTA2。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑