基于深度学习的CT-MR图像联合配准分割方法  

Joint Registration and Segmentation Method of CT-MR Images Based on Deep Learning

作　　者：洪犇 钱旭升 申明磊[1] 胡冀苏 耿辰[2] 戴亚康[2] 周志勇[2] HONG Ben;QIAN Xusheng;SHEN Minglei;HU Jisu;GENG Chen;DAI Yakang;ZHOU Zhiyong(School of Electronic Engineering and Optoelectronic Technology,Nanjing University of Science and Technology,Nanjing 210094,China;Suzhou Institute of Biomedical Engineering and Technology,Chinese Academy of Science,Suzhou 215163,Jiangsu,China)

机构地区：[1]南京理工大学电子工程与光电技术学院,南京210094 [2]中国科学院苏州生物医学工程技术研究所,江苏苏州215163

出　　处：《计算机工程》2023年第9期234-245,共12页Computer Engineering

基　　金：中国科学院青年创新促进会项目(2021324);江苏省重点研发计划项目(BE2022049-2,BE2021053,BE2020625,BE2021612);江苏省卫生健康委医学科研项目(M2020068);苏州市医疗卫生科技创新项目(SKY2021031);苏州市科技计划项目(SS202054);丽水市科技计划项目(2020ZDYF09)。

摘　　要：医学图像配准和分割是医学图像分析中的两项重要任务,将其相结合可以有效提升两者的精度,但现有的单模态图像联合配准分割框架难以适用于多模态图像。针对以上问题,提出基于模态一致性监督和多尺度邻域描述符的CT-MR图像联合配准分割框架,包含一个多模态图像配准网络和两个分割网络。联合配准分割框架利用多模态图像配准产生的形变场在两种模态的分割结果之间建立对应的形变关系,并设计模态一致性监督损失,通过两个分割网络互相监督的方式提升多模态分割的精度。在多模态图像配准网络中,构建多尺度模态独立邻域描述符以增强跨模态信息表征能力,并将该描述符作为结构性损失项加入配准网络,更加准确地约束多模态图像的局部结构对应关系。在118例肝脏CT-MR多模态图像数据集上的实验结果表明,在仅提供30%分割标签的情况下,该方法的肝脏配准Dice相似系数(DSC)达到94.66(±0.84)%,目标配准误差达到5.191(±1.342)mm,CT和MR图像的肝脏分割DSC达到94.68(±0.82)%和94.12(±1.06)%,优于对比的配准方法和分割方法。Medical image registration and segmentation are important tasks in medical image analysis.The accuracy of the tasks can be improved effectively by their combination.However,the existing joint registration and segmentation framework of single-modal images is difficult to apply to multi-modal images.To address these problems,a Computed Tomography-Magnetic Resonance(CT-MR)image-based joint registration and segmentation framework based on modality-consistent supervision and a multi-scale modality-independent neighborhood descriptor is proposed.It consists of a multimodal image registration network and two segmentation networks.The deformation field generated by the multi-modal registration is used to establish the corresponding deformation relationship between the segmentation network results of the two modalities.Modality consistency supervision loss is constructed,which improves the accuracy of multi-modal segmentation because the two segmentation networks supervise each other.In the multimodal image registration network,a multi-scale modality-independent neighborhood descriptor is constructed to enhance the representation ability of cross-modal information.The descriptor is added to the registration network as a structural loss term to constrain the local structure correspondence of multimodal images more accurately.Experiments were performed on a dataset of 118 CT-MR multimodal liver images.When 30%segmentation labels are provided,the Dice Similarity Coefficient(DSC)of liver registration of this method reaches 94.66(±0.84)%,and the Target Registration Error(TRE)reaches 5.191(±1.342)mm.The DSC of liver segmentation of this method reaches 94.68(±0.82)%and 94.12%(±1.06)%in CT and MR images.These results are superior to those of the comparable registration and segmentation method.

关 键 词：多模态图像 配准 分割 模态一致性监督 多尺度邻域描述符 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]