arXiv 2606.004892026-06-02cs.CV

基于视觉Mamba的3D分割一切模型用于诊断胎盘植入谱

3D Segment Anything Model with Visual Mamba for Diagnosing Placenta Accreta Spectrum

Department of Obstetrics and Gynecology, The Third Affiliated Hospital, Guangzhou Medical University（妇产科系，广州医科大学第三附属医院）；Department of Obstetrics, Guangzhou Women and Children’s Medical Center, Guangzhou Medical University（妇产科，广州妇女儿童医疗中心，广州医科大学）；Department of Radiology, The Third Affiliated Hospital, Guangzhou Medical University（放射科，广州医科大学第三附属医院）；School of Future Technology, Dalian University of Technology（未来技术学院，大连理工大学）

Yuliang Zhang, Fang He, Lulu Peng, Tianyu Yan, Pingping Zhang, Ting Song, Lili Du, Dunjin Chen

备注：: Accepted by IEEE Transactions on Image Processing (TIP2026). More modifications may be performed

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出3DSAMba框架，结合3D SAM、适配器、多级聚合Mamba和融合状态空间模型，通过MRI图像分割病灶区域实现胎盘植入谱的自动诊断。

摘要：

胎盘植入谱（PAS）是一种罕见但高度危险的产科疾病。早期准确的PAS诊断对孕产妇健康至关重要。传统的PAS诊断依赖于经验丰富的医生分析剖宫产史和磁共振成像（MRI）数据。然而，地市级医院往往缺乏准确诊断PAS的专业知识和资源。为应对这些挑战，我们建立了首个基于MRI的PAS数据集，包含细粒度分割和分类标注。同时，通过从子宫MRI图像中分割病灶区域，可以显著增强PAS诊断。为了实现自动PAS诊断，我们提出了3DSAMba，一种新颖的特征学习框架，用于有效的病灶分割。具体来说，我们首先设计了3D分割一切模型（SAM），并通过高效的适配器机制将医学领域信息融入模型。此外，我们引入了多级聚合Mamba（MLAM）来聚合不同层次的特征图，以及融合状态空间模型（FSSM）来融合来自编码器和解码器的多尺度特征。最后，我们通过逐元素乘法将分割掩码应用于原始MRI图像，有效隔离病灶区域，以实现更准确的PAS诊断。大量实验验证了我们的框架显著提升了PAS诊断性能。为促进PAS诊断的进一步研究，我们在https://github.com/Drchip61/PASD上发布了数据集和源代码。

英文摘要：

Placenta Accreta Spectrum (PAS) is a rare but highly dangerous obstetric disease. Early and accurate PAS diagnosis is critical for maternal health. Traditional PAS diagnosis relies on experienced doctors by analyzing the cesarean history and Magnetic Resonance Imaging (MRI) data. However, district-level hospitals often lack the expertise and resources for accurate PAS diagnosis. To address these challenges, we establish the first MRI-based PAS dataset, which includes both fine-grained segmentation and classification annotations. Meanwhile, diagnosing PAS can be significantly enhanced by segmenting lesion areas from MRI images of the uterus. To achieve automatic PAS diagnosis, we propose 3DSAMba, a novel feature learning framework for effective lesion segmentation. More specifically, we first design a 3D Segment Anything Model (SAM) and incorporate medical domain information into the model through an efficient adapter mechanism. In addition, we introduce a Multi-Level Aggregation Mamba (MLAM) to aggregate feature maps across different levels and a Fusion State Space Model (FSSM) to fuse multi-scale features from both the encoder and decoder. Finally, we apply segmentation masks to the original MRI images through element-wise multiplication, effectively isolating lesion areas for more accurate PAS diagnosis. Extensive experiments validate that our framework significantly improves the PAS diagnostic performance. To facilitate further research in PAS diagnosis, we have released the dataset and source code at https://github.com/Drchip61/PASD.

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。