用轻量级注意力机制提升OCT图像中微小病灶的分割精度
Weakly Supervised Segmentation of Hyper-Reflective Foci with Compact Convolutional Transformers and SAM2
- 结合LRP与SAM2，通过逐层重要性传播提升定位精度
- 引入紧凑卷积变压器，使小结构分割准确率显著提高
- 适合医学影像中标注成本高、目标微小的场景
弱监督分割有望大幅降低光学相干断层扫描（OCT）中微小结构如高反射灶（HRF）的标注成本。然而，现有方法普遍存在输入图像强下采样或仅能粗粒度定位的问题，难以满足小结构需求。本文提出新框架：利用层间相关性传播（LRP）引导分割任意模型（SAM2），提升传统基于注意力的多实例学习（MIL）的空间分辨率；并通过迭代推理提升召回率。此外，将MIL替换为加入位置编码的紧凑卷积变压器（CCT），实现图像不同区域间信息交互，进一步显著提升分割准确性。
原文摘要 · Abstract (English)
Weakly supervised segmentation has the potential to greatly reduce the annotation effort for training segmentation models for small structures such as hyper-reflective foci (HRF) in optical coherence tomography (OCT). However, most weakly supervised methods either involve a strong downsampling of input images, or only achieve localization at a coarse resolution, both of which are unsatisfactory for small structures. We propose a novel framework that increases the spatial resolution of a traditional attention-based Multiple Instance Learning (MIL) approach by using Layer-wise Relevance Propagation (LRP) to prompt the Segment Anything Model (SAM~2), and increases recall with iterative inference. Moreover, we demonstrate that replacing MIL with a Compact Convolutional Transformer (CCT), which adds a positional encoding, and permits an exchange of information between different regions of the OCT image, leads to a further and substantial increase in segmentation accuracy.
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。