一个模型搞定心脏超声多视角分割，提升临床效率
EchoONE: Segmenting Multiple echocardiography Planes in One Model
- 基于SAM架构，设计可组合掩码学习模块生成语义感知提示
- 引入轻量级CNN分支融合局部特征，实现模型对多视图适配
- 首次在多个数据集上统一完成多视角分割，适合医疗影像开发
临床心脏超声检查需获取不同视角的心脏结构图像，现有AI模型需为每个视图单独训练，导致重复开发与复杂性高。本文提出EchoONE，首个统一解决超声多视角分割（MPS）问题的模型，采用基于SAM的分割架构，结合先验可组合掩码学习（PC-Mask）模块实现语义感知密集提示生成，并引入可学习的CNN分支与简单有效的局部特征融合与自适应（LFFA）模块以增强SAM适配能力。在多个内部和外部超声数据集上验证，对不同心腔视角均实现一致领先性能。代码将开源于https://github.com/a2502503/EchoONE。
原文摘要 · Abstract (English)
In clinical practice of echocardiography examinations, multiple planes containing the heart structures of different view are usually required in screening, diagnosis and treatment of cardiac disease. AI models for echocardiography have to be tailored for each specific plane due to the dramatic structure differences, thus resulting in repetition development and extra complexity. Effective solution for such a multi-plane segmentation (MPS) problem is highly demanded for medical images, yet has not been well investigated. In this paper, we propose a novel solution, EchoONE, for this problem with a SAM-based segmentation architecture, a prior-composable mask learning (PC-Mask) module for semantic-aware dense prompt generation, and a learnable CNN-branch with a simple yet effective local feature fusion and adaption (LFFA) module for SAM adapting. We extensively evaluated our method on multiple internal and external echocardiography datasets, and achieved consistently state-of-the-art performance for multi-source datasets with different heart planes. This is the first time that the MPS problem is solved in one model for echocardiography data. The code will be available at https://github.com/a2502503/EchoONE.
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。