Multi-modality hierarchical fusion network for lumbar spine segmentation with magnetic resonance images

作     者：Han Yan Guangtao Zhang Wei Cui Zhuliang Yu Han Yan;Guangtao Zhang;Wei Cui;Zhuliang Yu

作者机构：School of Automation Science and EngineeringSouth China University of TechnologyGuangzhou510641GuangdongChina Guangzhou First People’s HospitalGuangzhou510180GuangdongChina Shien-Ming Wu School of Intelligent EngineeringSouth China University of TechnologyGuangzhou511442GuangdongChina Institute for Super Robotics(Huangpu)Guangzhou510000GuangdongChina 

出 版 物：《Control Theory and Technology》 (控制理论与技术（英文版）)

年 卷 期：2024年第22卷第4期

页      面：612-622页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：supported in part by the Technology Innovation 2030 under Grant 2022ZD0211700 

主　　题：Lumbar spine segmentation Deep learning Multi-modality fusion Feature fusion 

摘      要：For the analysis of spinal and disc diseases,automated tissue segmentation of the lumbar spine is *** to the continuous and concentrated location of the target,the abundance of edge features,and individual differences,conventional automatic segmentation methods perform *** the success of deep learning in the segmentation of medical images has been shown in the past few years,it has been applied to this task in a number of *** multi-scale and multi-modal features of lumbar tissues,however,are rarely explored by methodologies of deep *** of the inadequacies in medical images availability,it is crucial to effectively fuse various modes of data collection for model training to alleviate the problem of insufficient *** this paper,we propose a novel multi-modality hierarchical fusion network(MHFN)for improving lumbar spine segmentation by learning robust feature representations from multi-modality magnetic resonance *** adaptive group fusion module(AGFM)is introduced in this paper to fuse features from various modes to extract cross-modality features that could be ***,to combine features from low to high levels of cross-modality,we design a hierarchical fusion structure based on *** to the other feature fusion methods,AGFM is more effective based on experimental results on multi-modality MR images of the lumbar *** further enhance segmentation accuracy,we compare our network with baseline fusion *** to the baseline fusion structures(input-level:76.27%,layer-level:78.10%,decision-level:79.14%),our network was able to segment fractured vertebrae more accurately(85.05%).