| 注册
首页|期刊导航|生命科学仪器|基于深度学习的人体腰椎MRI图像自动分割

基于深度学习的人体腰椎MRI图像自动分割

冯鹏程 曹圣伟 覃兵 伍彪 吴济文 周璐 钱志余 祝桥桥

生命科学仪器2023,Vol.21Issue(5):53-57,5.
生命科学仪器2023,Vol.21Issue(5):53-57,5.DOI:10.11967/2023211011

基于深度学习的人体腰椎MRI图像自动分割

Automatic segmentation of human lumbar spine MRI images based on deep learning

冯鹏程 1曹圣伟 1覃兵 1伍彪 1吴济文 1周璐 1钱志余 1祝桥桥1

作者信息

  • 1. 南京航空航天大学自动化学院,江苏南京 211016
  • 折叠

摘要

Abstract

Lumbar intervertebral disc pathology constitutes a major contributor to lower back pain,with lumbar spine Magnetic Resonance Imaging(MRI)images playing a pivotal role in its diagnosis.This study introduces a deep learning-based automatic segmentation method aimed at enhancing the recognition and segmentation of inter-vertebral disc morphology,thereby mitigating the inconveniences and inconsistencies associated with manual seg-mentation by healthcare professionals.We employed the renowned segmentation network,Mask-Rcnn(Mask Re-gion-based Convolutional Neural Network),recognized for its exceptional feature extraction capabilities,adept object detection performance,and precise instancesegmentation outcomes,rendering it an optimal choice.By lever-aging the neural network model library in PyTorch,we revamped the dataset interface and fine-tuned output layer parameters to better align with the task of identifying and segmenting lumbar intervertebral discs.This study uti-lized a publicly available dataset comprising 1545 lumbar spine MRI images,each annotated for structures including intervertebral discs.After dataset preprocessing to retain annotations pertaining to intervertebral discs,we ran-domly selected 450 images for testing,with the remainder utilized for training.Following 20 training epochs,we a-chieved an average precision of 97.7%and an average recall of 98.6%,a DICE coefficient of 96.9%..This research underscores the substantial potential of a deep learning-based automatic segmentation method to markedly im-prove the recognition and segmentation of intervertebral discs in lumbar spine MRI images.This methodology holds promise for clinical applications,potentially enhancing the accuracy and efficiency of disease diagnosis while alleviating the burden on healthcare professionals.

关键词

深度学习/神经网络/生物医学图像/腰椎间盘自动切割

Key words

Deep learning/neural networks/biomedical imaging/automated lumbar disc cutting

分类

医药卫生

引用本文复制引用

冯鹏程,曹圣伟,覃兵,伍彪,吴济文,周璐,钱志余,祝桥桥..基于深度学习的人体腰椎MRI图像自动分割[J].生命科学仪器,2023,21(5):53-57,5.

基金项目

国家自然科学基金重大科研仪器研制项目(81827803,81727804),国家自然科学基金(11902154),江苏省自然科学基金(BK20190387),江苏省研究生科研与实践创新计划项目(KYCX22_0349),南京航空航天大学科研与实践创新计划(xcxjh20220330) (81827803,81727804)

生命科学仪器

1671-7929

访问量0
|
下载量0
段落导航相关论文