基于MSC-LSAM的多尺度交叉超声医学图像分割方法  

Multi-scale Crossed Algorithm for Ultrasound Medical Image Segmentation Based on MSC-LSAM

作　　者：王朝欣 杨汶汶[1] 戎泽 李铮昱 王行 马磊 WANG Zhaoxin;YANG Wenwen;RONG Ze;LI Zhengyu;WANG Xing;MA Lei(School of Information Science and Technology,Nantong University,Nantong 226019,China)

机构地区：[1]南通大学信息科学技术学院,南通226019

出　　处：《数据采集与处理》2025年第2期469-484,共16页Journal of Data Acquisition and Processing

基　　金：江苏省产学研合作项目(FZ20220736)。

摘　　要：脑卒中是全球范围内致死致残率最高的疾病之一,颈动脉狭窄和心脏病变是缺血性脑卒中的重要致病因素。超声(Ultrasound,US)是检查由颈动脉狭窄和心脏病变引起的缺血性脑卒中的常用影像学手段,但超声图像噪声多、边界模糊,具有较高的分割难度。本文提出MSC⁃LSAM算法,一种多尺度交叉的双编码器超声图像分割网络,旨在实现颈动脉腔体和心脏腔体的快速、准确分割,辅助医生完成疾病诊断。MSC⁃LSAM在编码器部分并行了分割一切模型(Segment anything model,SAM)的视觉编码器和UNet编码器,在解码器部分采用UNet解码器。本研究首先冻结了预训练的SAM视觉编码器,并在Transformer层中引入高效的适配器(Adapter)块,被称可学习的分割一切模型(Learnable SAM,LSAM)。LSAM在拥有较低参数量的同时,保留学习能力和高度泛化性。然后,在UNet全局网络引入多尺度交叉注意力(Multi⁃scale cross⁃axial attention,MCA),实现多尺度特征的交叉融合,有效提升边缘分割能力,抑制模型过拟合。最后,通过高效通道注意力(Efficient channel attention,ECA)实现双编码器多尺度特征的高效融合,减少模型误分割。结果表明,本研究提出的MSC⁃LSAM在心脏超声公开数据集CAMUS和颈动脉超声自建数据集CAUS上均取得了良好的效果。CAMUS的两心腔(2CH)和四心腔(4CH)数据集分割的平均Dice相似系数(Dice similarity coefficient,DSC)分别达到0.927和0.934;CAUS数据集的平均DSC达到0.917。MSC⁃LSAM在颈动脉腔体和心脏腔体超声图像分割任务上获得了良好的分割准确度,高于主流分割算法,具有良好的应用前景。Stroke is one of the leading causes of death and disability around the world.Carotid artery stenosis(CAS)and cardiac lesions are important contributing factors to ischemic stroke,and ultrasound imaging has shown great potential in diagnosing ischemic stroke caused by CAS and cardiac lesions.But ultrasound images present significant segmentation challenges due to noise and blurred boundaries.To address this issue,the MSC⁃LSAM algorithm,a multi⁃scale crossed dual encoder network for ultrasound image segmentation is proposed.It aims to achieve rapid and accurate segmentation of carotid and cardiac cavities,assisting physicians in disease diagnosis.In the MSC⁃LSAM,the encoder part parallels a segment anything model(SAM)vision encoder and an UNet encoder,while the decoder part utilizes an UNet decoder.In the SAM image encoder,we froze the pretrained SAM image encoder and introduce efficient adapter blocks in Transformer layers,referred to as learnable SAM(LSAM).LSAM maintains learning capability and high generalization ability while having a low number of parameters.In the global UNet network,we incorporate the multi⁃scale cross⁃axial attention(MCA)blocks to achieve cross⁃fusion of multi⁃scale features between different axes,effectively enhancing edge segmentation capabilities and suppressing model overfitting.Following the parallel encoders,the efficient channel attention(ECA)block is added to enable integration of multi⁃scale features from dual encoders,reducing incorrect segmentation caused by feature level mismatches.MSC⁃LSAM achieves good performance on both the publicly available cardiac ultrasound dataset of CAMUS and the self⁃constructed carotid artery ultrasound dataset of CAUS.Average dice similarity coefficients(DSCs)for the segmentation of the two⁃chamber(2CH)and four⁃chamber(4CH)datasets in CAMUS reach 0.927 and 0.934,respectively;while the average DSC for the CAUS dataset reaches 0.917.MSC⁃LSAM achieves good segmentation accuracy in tasks of carotid lumen and cardiac chamber ult

关 键 词：缺血性脑卒中 超声图像分割 分割一切模型 多尺度交叉注意力 高效通道注意力 

分 类 号：R318[医药卫生—生物医学工程] TP391.41[医药卫生—基础医学]