用自监督预训练提升眼底血管渗漏分割精度
MAE-SAM2: Mask Autoencoder-Enhanced SAM2 for Clinical Retinal Vascular Leakage Segmentation
- 融合掩码自编码器与SAM2，利用自监督学习增强特征提取
- 在荧光造影图像上实现最高Dice和IoU，较原版SAM2提升5%
- 适合医疗影像分割研究者，尤其关注小目标精准定位
我们提出MAE-SAM2，一种用于荧光造影图像中视网膜血管渗漏分割的新基础模型。由于渗漏区域尺寸小且分布密集，加之标注临床数据有限，分割任务面临巨大挑战。本方法将自监督学习（SSL）策略与掩码自编码器（MAE）结合到SAM2中。通过探索不同损失函数，最终采用任务特定的组合损失。大量实验与消融研究证明，MAE-SAM2优于多个最先进模型，在Dice分数和交并比（IoU）上均达最高水平。相比原始SAM2，性能提升5%，凸显了具有自监督预训练的基础模型在临床影像分割中的潜力。
原文摘要 · Abstract (English)
We propose MAE-SAM2, a novel foundation model for retinal vascular leakage segmentation on fluorescein angiography images. Due to the small size and dense distribution of the leakage areas, along with the limited availability of labeled clinical data, this presents a significant challenge for segmentation tasks. Our approach integrates a Self-Supervised learning (SSL) strategy, Masked Autoencoder (MAE), with SAM2. In our implementation, we explore different loss functions and conclude a task-specific combined loss. Extensive experiments and ablation studies demonstrate that MAE-SAM2 outperforms several state-of-the-art models, achieving the highest Dice score and Intersection-over-Union (IoU). Compared to the original SAM2, our model achieves a $5\%$ performance improvement, highlighting the promise of foundation models with self-supervised pretraining in clinical imaging tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。