结构先验引导的多模态腰椎MRI图像分割算法

PDF (PC)

结构先验引导的多模态腰椎MRI图像分割算法

Multimodal lumbar MRI image segmentation algorithm guided by structure priori

结构先验引导的多模态腰椎MRI图像分割算法

Multimodal lumbar MRI image segmentation algorithm guided by structure priori

摘要/Abstract

参考文献

多维度评价

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

多维度评价

本文评价

推荐阅读 0

doi:10.6040/j.issn.1672-3961.0.2023.329

山东大学学报 (工学版) ›› 2025, Vol. 55 ›› Issue (1): 66-76.doi: 10.6040/j.issn.1672-3961.0.2023.329

• 机器学习与数据挖掘 • 上一篇

李伟豪^1,2,3,王苹苹^1,2,3,许万博^1,2,3,4,魏本征^1,2,3*

1.山东中医药大学医学人工智能研究中心, 山东青岛 266112;2.山东中医药大学青岛中医药科学院, 山东青岛 266112;3.青岛市中医人工智能技术重点实验室, 山东青岛 266112;4.山东大学齐鲁医院德州医院, 山东德州 253046

发布日期:2025-02-20
作者简介:李伟豪(1999— ),男,山东菏泽人,硕士研究生,主要研究方向为医学图像处理与分析. E-mail: 986053032@qq.com. *通信作者简介:魏本征(1976— ),男,山东临沂人,教授,博士生导师,博士,主要研究方向为医学人工智能、医学影像智能分析和医学信息工程. E-mail: wbz99@sina.com
基金资助:
国家自然科学基金资助项目(62372280,61872225);山东省自然科学基金资助项目(ZR2020KF013,ZR2019ZD04);青岛市科技惠民示范专项资助项目(23-2-8-smjk-2-nsh);齐鲁卫生与健康领军人才资助项目

LI Weihao^1,2,3, WANG Pingping^1,2,3, XU Wanbo^1,2,3,4, WEI Benzheng^1,2,3*

1. Center for Medical Artificial Intelligence, Shandong University of Traditional Chinese Medicine, Qingdao 266112, Shandong, China;
2. Qingdao Academy of Chinese Medical Science, Shandong University of Traditional Chinese Medicine, Qingdao 266112, Shandong, China;
3. Qingdao Key Laboratory of Artificial Intelligence Technology of Traditional Chinese Medicine, Qingdao 266112, Shandong, China;
4. Qilu Hospital of Shandong University Dezhou Hospital, Dezhou 253046, Shandong, China

Published:2025-02-20

摘要： 为挖掘腰椎磁共振成像(magnetic resonance image, MRI)图像中多种模态信息的相关性、腰椎结构间的相互依赖关系、腰椎结构先验知识对腰椎精准分割和疾病辅助诊断的重要价值,提出一种结构先验引导的多模态信息融合分割算法。设计的多模态图像编码模块(multi-modality encoding module, MMEM)可同时对T1和T2加权图像做语义特征提取;跨模态体素融合模块(cross-modality voxel fusion module, CMVF)可在融合过程中为各模态图像特征自适应分配融合权重。根据腰椎内部各组织结构间的先验知识构建图模型,利用图卷积神经网络分割模块(graph convolutional networks segmentation module,GCNSM)实现图模型上的语义信息传播。采用多模态图像解码模块(multi-modality decoding module, MMDM)对特征图进行解码,实现对椎体及椎间盘的精准图像分割。对山东大学齐鲁医院德州医院采集的190组患者MRI数据集进行试验验证,所设计算法的平均骰子系数D_ice、交并比I_oU、95% Hausdorff距离H_D95和平均对称表面距离A_SSD分别为90.3%、82.31%、4.40 mm和1.21 mm,结果表明了算法的有效性及先进性。

关键词: 腰椎, 磁共振成像, 多模态, 多类别分割, 图卷积神经网络

中图分类号:

TP391

李伟豪,王苹苹,许万博,魏本征. 结构先验引导的多模态腰椎MRI图像分割算法[J]. 山东大学学报 (工学版), 2025, 55(1): 66-76.

LI Weihao, WANG Pingping, XU Wanbo, WEI Benzheng. Multimodal lumbar MRI image segmentation algorithm guided by structure priori[J]. Journal of Shandong University(Engineering Science), 2025, 55(1): 66-76.

[1] JAMES S L, ABATE D, ABATE K H, et al. Global, regional, and national incidence, prevalence, and years lived with disability for 354 diseases and injuries for 195 countries and territories, 1990-2017: a systematic analysis for the Global Burden of Disease Study 2017[J]. The Lancet, 2018, 392(10159): 1789-1858.
[2] 刘方旭, 王建, 魏本征. 基于多空间注意力的小儿肺炎辅助诊断算法[J]. 山东大学学报(工学版), 2023, 53(2): 135-142. LIU Fangxu, WANG Jian, WEI Benzheng. Auxiliary diagnosis algorithm for pediatric pneumonia based on multi-spatial attention[J] Journal of Shandong University(Engineering Science), 2023, 53(2): 135-142.
[3] 张月芳, 邓红霞, 呼春香, 等. 融合残差块注意力机制和生成对抗网络的海马体分割[J]. 山东大学学报(工学版), 2020, 50(6): 76-81. ZHANG Yuefang, DENG Hongxia, HU Chunxiang, et al. Hippocampal segmentation combining residual attention mechanism and generative adversarial networks[J]. Journal of Shandong University(Engineering Science), 2020, 50(6): 76-81.
[4] SERAI S D. Basics of magnetic resonance imaging and quantitative parameters T1, T2, T2*, T1rho and diffusion-weighted imaging[J]. Pediatric Radiology, 2022, 52(2): 217-227.
[5] 王国力, 孙宇, 魏本征. 医学图像图深度学习分割算法综述[J]. 计算机工程与应用, 2022, 58(12): 37-50. WANG Guoli, SUN Yu, WEI Benzheng. Systematic review on graph deep learning in medical image segmentation[J] Computer Engineering and Applications, 2022, 58(12): 37-50.
[6] HAN Z, WEI B, LEUNG S, et al. Towards automatic report generation in spine radiology using weakly supervised framework[C] //Proceedings of Medical Image Computing and Computer Assisted Intervention-MICCAI 2018. Granada, Spain: Springer, 2018: 185-193.
[7] HAN Z, WEI B, MERCADO A, et al. Spine-GAN: semantic segmentation of multiple spinal structures[J]. Medical Image Analysis, 2018, 50: 23-35.
[8] CHEN J, QIAN L, MA L, et al. SymTC: a symbiotic Transformer-CNN net for instance segmentation of lumbar spine MRI[EB/OL].(2024-01-17)[2024-03-17]. https://arxiv.org/abs/2401.09627.
[9] LESSMANN N, VAN GINNEKEN B, DE JONG P A, et al. Iterative fully convolutional neural networks for automatic vertebra segmentation and identification[J]. Medical Image Analysis, 2019, 53: 142-155.
[10] PANG S, PANG C, SU Z, et al. DGMSNet: spine segmentation for MR image by a detection-guided mixed-supervised segmentation network[J]. Medical Image Analysis, 2022, 75: 102261.
[11] HONG Y, WEI B, HAN Z, et al. MMCL-Net: spinal disease diagnosis in global mode using progressive multi-task joint learning[J]. Neurocomputing, 2020, 399: 307-316.
[12] CHANG H, ZHAO S, ZHENG H, et al. Multi-vertebrae segmentation from arbitrary spine MR images under global view[C] //Proceedings of Medical Image Com-puting and Computer Assisted Intervention-MICCAI 2020. Lima, Peru: Springer, 2020: 702-711.
[13] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[EB/OL].(2016-09-09)[2023-11-15]. https://arxiv.org/abs/1609.02907.
[14] PANG S, PANG C, ZHAO L, et al. SpineParseNet: spine parsing for volumetric MR image by a two-stage segmentation framework with semantic image representation[J]. IEEE Transactions on Medical Imaging, 2020, 40(1): 262-273.
[15] HAN Z, WEI B, XI X, et al. Unifying neural learning and symbolic reasoning for spinal medical report generation[J]. Medical Image Analysis, 2021, 67: 101872.
[16] LI T, WEI B, CONG J, et al. S3egANet: 3D spinal structures segmentation via adversarial nets[J]. IEEE Access, 2019, 8: 1892-1901.
[17] LIM D S W, MAKMUR A, ZHU L, et al. Improved productivity using deep learning-assisted reporting for lumbar spine MRI[J]. Radiology, 2022, 305(1): 160-166.
[18] LI X, DOU Q, CHEN H, et al. 3D multi-scale FCN with random modality voxel dropout learning for intervertebral disc localization and segmentation from multi-modality MR images[J]. Medical Image Analysis, 2018, 45: 41-54.
[19] ZOU Y, SHI Y. Co-segmentation of multi-modality spinal image using channel and spatial attention[C] //Proceedings of Machine Learning in Medical Imaging: 12th International Workshop, MLMI 2021. Strasbourg, France: Springer, 2021: 287-295.
[20] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2018: 7132-7141.
[21] TSENG K L, LIN Y L, HSU W, et al. Joint sequence learning and cross-modality convolution for 3D biomedical segmentation[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE, 2017: 6393-6400.
[22] SHAKER A, MAAZ M, RASHEED H, et al. UNETR++: delving into efficient and accurate 3D medical image segmentation[EB/OL].(2022-12-08)[2023-11-15]. https://arxiv.org/abs/2212.04497.
[23] HUANG H, LIN L, TONG R, et al. UNet 3+: a full-scale connected unet for medical image segmentation[C] //Proceedings of International Conference on Acoustics, Speech and Signal Processing(ICASSP). Barcelona, Spain: IEEE, 2020: 1055-1059.
[24] PEIRIS H, HAYAT M, CHEN Z, et al. A robust volumetric transformer for accurate 3D tumor segmentation[C] //Proceedings of the International Con-ference on Medical Image Computing and Computer-Assisted Intervention. Cham, Germany: Springer, 2022: 162-172.
[25] BOZORGPOUR A, AZAD B, AZAD R, et al. HCA-Net: hierarchical context attention network for intervertebral disc semantic labeling[EB/OL].(2023-11-21)[2024-03-17]. https://arxiv.org/abs/2311.12486.

Viewed

Full text

	From	local

	Times	34
	Rate	100%

Abstract

Just accepted	Online first	Issue

0	0	74

	From	Others

	Times	74
	Rate	100%

Cited

Web of Science	Crossref	ScienceDirect	Search for Citations in Google Scholar >>


This page requires you have already subscribed to WoS.

Shared

Discussed

Just accepted

Online first

Just accepted

Online first

[1]	谭智方,董飞,卢鹏宇,潘嘉男,聂秀山,尹义龙. 基于跨模态注意力哈希学习的视频片段定位方法[J]. 山东大学学报 (工学版), 2025, 55(1): 58-65.
[2]	聂秀山,巩蕊,董飞,郭杰,马玉玲. 短视频场景分类方法综述[J]. 山东大学学报 (工学版), 2024, 54(3): 1-11.
[3]	于艺旋,杨耕,耿华. 连续复合运动的多模态层次化关键帧提取方法[J]. 山东大学学报 (工学版), 2023, 53(2): 42-50.
[4]	沈鑫杰,黄嘉爽,丁卫平,孙颖,王海鹏,鞠恒荣. 基于双通路卷积融合网络的脑龄分布预测[J]. 山东大学学报 (工学版), 2022, 52(6): 131-138.
[5]	杨霄,袭肖明,李维翠,杨璐. 基于层次化双重注意力网络的乳腺多模态图像分类[J]. 山东大学学报 (工学版), 2022, 52(3): 34-41.
[6]	霍兵强,周涛,陆惠玲,董雅丽,刘珊. 基于NRC和多模态残差神经网络的肺部肿瘤良恶性分类[J]. 山东大学学报 (工学版), 2020, 50(6): 59-67.
[7]	田枫, 李欣, 刘芳, 李闯, 孙小强, 杜睿山. 基于多模态子空间学习的语义标签生成方法[J]. 山东大学学报 (工学版), 2020, 50(3): 31-37.
[8]	常致富,周风余,王玉刚,沈冬冬,赵阳. 基于深度学习的图像自动标注方法综述[J]. 山东大学学报 (工学版), 2019, 49(6): 25-35.
[9]	包书哲1,2,朱月澴1,王春立1*. 基于fMRI的图像底层特征关注研究[J]. 山东大学学报(工学版), 2014, 44(1): 24-28.
[10]	翟海亭,吴晓娟,彭彰 . 一种改进的基于互信息的三维医学图像配准算法[J]. 山东大学学报(工学版), 2006, 36(4): 33-39 .