生物医学工程研究2024，Vol.43Issue(2)：108-114,7.DOI:10.19529/j.cnki.1672-6278.2024.02.04
联合自适应核和Transformer的脊柱磁共振成像多类别分割网络
Multi category segmentation network for magnetic resonance imaging spine based on adaptive kernel and transformer
摘要
Abstract
Aiming at the problems of complex structure,redundant tissue,noise and artifacts in MRI of spine,an instance multi category segmentation network of spine MRI based on adaptive kernel and transformer was designed.The Swin Transformer was used as the backbone network.By introducing the dense connection module,the information loss of the forward channel was reduced,so as to better capture the details and local information in the image.At the same time,to further capture the multi-scale features of complex space,a self-attention kernel selection method was adopted to construct the cross-scale dense connection,so that the model could a-daptively learn the appropriate convolution kernel size in the training process,then improved the perception ability of the model for dif-ferent scale information and the segmentation performance.Experiments on 2D slices of T2 weighted MRI images of 215 subjects showed that the mean intersection over union(mIoU),mean recall rate(mRecall),and mean dice coefficient(mDice)reached 82.63%,89.37%,and 88.85%,respectively.The results show that this algorithm has excellent segmentation performance,and can realize the accurate segmentation of vertebral bodies and intervertebral discs in spinal MRI images,can provide an auxiliary diagnostic tool for cli-nicians.关键词
脊柱图像分割/磁共振成像/Swin Transformer/稠密连接/自注意力核选择Key words
Spine image segmentation/Magnetic resonance imaging/Swin Transformer/Dense connection/Self-attention kernel selection分类
医药卫生引用本文复制引用
郑州,王苹苹,张魁星..联合自适应核和Transformer的脊柱磁共振成像多类别分割网络[J].生物医学工程研究,2024,43(2):108-114,7.基金项目
山东省自然科学基金资助项目(ZR2020QF043,ZR2022QG051) （ZR2020QF043,ZR2022QG051）
山东省中医药科技项目(Q-2023045). （Q-2023045）
