Automatic segmentation of levator ani muscle in MRI images based on DenseUnet model

Yongjia XIANG; Yi WU; Xiaoqin ZHANG; Xin HU; Jingjing LIU; Ling LEI; Yanzhou WANG; Yan WANG

doi:10.16016/j.1000-5404.202102089

您当前的位置：

首页 >

文章列表页 >

Automatic segmentation of levator ani muscle in MRI images based on DenseUnet model

Monographic Reports: Digital medicine and artificial intelligence | 更新时间：2026-01-09

- Automatic segmentation of levator ani muscle in MRI images based on DenseUnet model
- Journal of Third Military Medical University Vol. 43, Issue 18, Pages: 1720-1728(2021)
- 作者机构：
  
  1.401331 重庆，重庆师范大学数学科学学院，智慧金融与大数据分析重庆市重点实验室
  2.400038 重庆，陆军军医大学(第三军医大学)：生物医学工程与影像医学系数字医学教研室
  3.561000 贵州安顺，安顺人民医院妇科
  4.400038 重庆，陆军军医大学(第三军医大学)：第一附属医院妇产科
- 作者简介：
- 基金信息：
  
  the National Natural Science Foundation of China(31971113);the National Natural Science Foundation for Distinguished Young Scholars of China(11901071)
- DOI：10.16016/j.1000-5404.202102089
  CLC： R312;R322.46;R445.2
- Received：19 February 2021，
  
  Revised：2021-05-12，
  
  Published：30 September 2021
- 稿件说明：
移动端阅览
Yongjia XIANG, Yi WU, Xiaoqin ZHANG, et al. Automatic segmentation of levator ani muscle in MRI images based on DenseUnet model[J]. Journal of Third Military Medical University, 2021, 43(18): 1720-1728.
DOI：

Yongjia XIANG, Yi WU, Xiaoqin ZHANG, et al. Automatic segmentation of levator ani muscle in MRI images based on DenseUnet model[J]. Journal of Third Military Medical University, 2021, 43(18): 1720-1728. DOI： 10.16016/j.1000-5404.202102089.

摘要

目的

基于盆底的核磁共振图像(MRI)，构建深度学习自动分割模型，进行盆底MRI图像的智能分割研究，以提高肛提肌分割效率和精准度。

方法

以DenseUnet模型为主干，搭建一个主要由编码器模块、上下文提取模块和解码器模块3部分组成的网络结构；在上下文提取模块中，通过使用空洞卷积和金字塔池化模块克服Unet较少利用上下文信息及不同感受野下的全局信息的缺点，通过19例患者的MRI数据，包括14例正常女性盆底MRI影像、1例盆腔脏器脱垂1度(pelvic organ prolapse degree 1，POP1)患者和2例盆腔脏器脱垂2度(POP2)患者作为训练集，并使用1例正常女性盆底MRI影像和1例POP2女性盆底MRI影像进行验证。

结果

构建模型能够自动、有效地分割盆底MRI图像中的肛提肌，通过验证，测试集中肛提肌总的平均相似性系数值为77.1%，平均豪斯多夫距离值为16 mm，平均对称面距离值为0.9 mm。其中正常志愿者肛提肌的平均相似性系数值为81.2%，POP2肛提肌的平均相似性系数值为74.5%。

结论

构建的DenseUnet模型分割精度优于Unet、ResUnet和Unet++ 3个经典的网络模型，在MRI图像下肛提肌的自动分割任务中具有较强的实用价值。

Abstract

Objective

To construct a deep learning automatic segmentation model based on the magnetic resonance image (MRI) of the pelvic floor

and make the intelligent segmentation of the pelvic floor MR image so as to reduce the work intensity of doctors and improve the segmentation efficiency and accuracy of levator ani muscle.

Methods

Based on DenseUnet model

a network structure composed of encoder module

context extraction module and decoder module was established; In the context extraction module

we used dilated convolution and pyramid pooling module to overcome the disadvantages that Unet uses less context information and global information under different receptive fields. We employed the MRI data of 19 patients

including 14 normal cases

1 case of grade 1 pelvic organ prolapse (POP1) and 2 cases of grade 2 pelvic organ prolapse (POP2) as training sets. One normal pelvic floor MRI image and 1 POP2 pelvic floor MR image were used for verification.

Results

The model can segment levator ani muscle in pelvic floor MR image automatically and effectively. Through verification

the average similarity coefficient of levator ani muscle in the test set is 77.1%

the average Hausdorff distance is 16 mm

and the average symmetry plane distance is 0.9 mm. The average similarity coefficient of levator ani muscle in normal volunteers was 81.2%

and that of POP2 female pelvic floor levator ani muscle was 74.5%.

Conclusion

The segmentation accuracy of DenseUnet model is better than that of Unet

ResUnet and Unet++. It has a strong practical value in the automatic segmentation task of levator ani muscle in MRI images. Through the automatic segmentation of levator ani muscle

the repetitive work of doctors is reduced

and the work efficiency is improved. At the same time

it also provides an alternative for the intelligent auxiliary diagnosis and treatment of pelvic organ prolapse.

关键词

Keywords

references

中华医学会妇产科学分会绝经学组. 中国绝经管理与绝经激素治疗指南(2018)[J]. 协和医学杂志, 2018, 9: 512-525. DOI: 10.3969./j.issn.1674-9081.2018.06.007.

Chinese Menopause Group, Obstetrics and Gynecology Branch of Chinese Medical Association. 2018 Chinese guideline on menopause management and menopause hormone therapy[J]. Med J PUMCH, 2018, 9: 512-525. DOI: 10.3969./j.issn.1674-9081.2018.06.007.

ROSTAMINIA G, WHITE D, HEGDE A, et al . Levator ani deficiency and pelvic organ prolapse severity[J ] . Obstet Gynecol, 2013, 121(5): 1017-1024. DOI: 10.1097/AOG.0b013e31828ce97d.

崔璨, 程悦, 沈文, 等. 女性盆腔器官脱垂病人肛提肌的MRI评价[J]. 国际医学放射学杂志, 2015, 38(2): 148-151. DOI: 10.3874/j.issn.1674-1897.2015.02.Z0210.

CUI C, CHENG Y, SHEN W, et al . Research progress of magnetic resonance imaging in evaluation of levator ani muscle for female patients with pelvic organ prolapse[J ] . Int J Med Radiol, 2015, 38(2): 148-151. DOI: 10.3874/j.issn.1674-1897.2015.02.Z0210.

GUO Y, GAO Y, SHEN D. Deformable MR prostate segmentation via deep feature learning and sparse patch matching[J]. IEEE Trans Med Imaging, 2016, 35(4): 1077-1089. DOI: 10.1109/tmi.2015.2508280.

LAVDAS I, GLOCKER B, KAMNITSAS K, et al . Fully automatic, multiorgan segmentation in normal whole body magnetic resonance imaging (MRI), using classification forests (CFs), convolutional neural networks (CNNs), and a multi-atlas (MA) approach[J ] . Med Phys, 2017, 44(10): 5210-5220. DOI: 10.1002/mp.12492.

BELLO G A, DAWES T J W, DUAN J, et al . Deep learning cardiac motion analysis for human survival prediction[J ] . Nat Mach Intell, 2019, 1: 95-104. DOI: 10.1038/s42256-019-0019-2.

YING T, LI Q, XU L, et al . Three-dimensional ultrasound appearance of pelvic floor in nulliparous women and pelvic organ prolapse women[J ] . Int J Med Sci, 2012, 9(10): 894-900. DOI: 10.7150/ijms.4829.

LI X, HONG Y, KONG D, et al . Automatic segmentation of levator hiatus from ultrasound images using U-net with dense connections[J ] . Phys Med Biol, 2019, 64(7): 075015. DOI: 10.1088/1361-6560/ab0ef4.

胡鹏辉, 王娜, 王毅, 等. 基于全卷积神经网络的肛提肌裂孔智能识别[J]. 深圳大学学报(理工版), 2018, 35(3): 316-323. DOI: 10.3724/SP.J.1249.2018.03316.

HU P H, WANG N, WANG Y, et al . Automatic recognition of levator hiatus based on fully convolutional neural networks[J ] . J Shenzhen Univ Sci Eng, 2018, 35(3): 316-323. DOI: 10.3724/SP.J.1249.2018.03316.

WU Y, DABHOIWALA N F, HAGOORT J, et al . Architecture of structures in the urogenital triangle of young adult males; comparison with females[J ] . J Anat, 2018, 233(4): 447-459. DOI: 10.1111/joa.12864.

WU Y, DABHOIWALA N F, HAGOORT J, et al . Architectural differences in the anterior and middle compartments of the pelvic floor of young-adult and postmenopausal females[J ] . J Anat, 2017, 230(5): 651-663. DOI: 10.1111/joa.12598.

WU Y, DABHOIWALA N F, HAGOORT J, et al . 3D topography of the young adult anal sphincter complex reconstruc ted from undeformed serial anatomical sections[J ] . PLoS ONE, 2015, 10(8): e0132226. DOI: 10.1371/journal.pone.0132226.

OTSU N. A threshold selection method from gray-level histograms[J]. IEEE Trans Syst Man Cybern, 1979, 9(1): 62-66. DOI: 10.1109/tsmc.1979.4310076.

GU Z W, CHENG J, FU H Z, et al . CE-net: context encoder network for 2D medical image segmentation[J ] . IEEE Trans Med Imaging, 2019, 38(10): 2281-2292. DOI: 10.1109/TMI.2019.2903562.

SZEGEDY C, LIU W, JIA Y Q, et al . Going deeper with convolutions[C ] //2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). June 7-12, 2015. Boston, MA, USA. IEEE, 2015. DOI: 10.1109/cvpr.2015.7298594.

YU F, KOLTUN V. Multi-scale context aggregation by dilated convolutions[EB/OL]. 2015: arXiv: 1511.07122[cs. CV]. https://arxiv.org/abs/1511.07122

HUANG G, LIU Z, VAN DER MAATEN L, et al . Densely connected convolutional networks[C ] //2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). July 21-26, 2017. Honolulu, HI. IEEE, 2017. DOI: 10.1109/cvpr.2017.243.

ZHAO H S, SHI J P, QI X J, et al . Pyramid scene parsing network[C ] //2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). July 21-26, 2017. Honolulu, HI. IEEE, 2017. DOI: 10.1109/cvpr.2017.660.

HE K M, ZHANG X Y, REN S Q, et al . Delving deep into rectifiers: surpassing human-level performance on ImageNet classification[C ] //2015 IEEE International Conference on Computer Vision (ICCV). December 7-13, 2015. Santiago, Chile. IEEE, 2015. DOI: 10.1109/iccv.2015.123.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Automatic segmentation of female urine control anatomical elements and related structures in MRI images based on deep learning

Multi-dimensional segmentation model and system development for recognizing small lesions after acute ischemic stroke

Application of artificial intelligence technology based on convolutional neural network in early gastric cancer recognition

Establishment of segmentational data set of larynx based on Chinese visible human

Automatic drawing on target therapy area in HIFU treatment based on MRI and CT imagings

Related Author

WU Yi

ZHANG Xiaoqin

XU Zhou

LEI Ling

WANG Yanzhou

WANG Yan

ZHANG Ziqin

伍亚舟

Related Institution

School of Mathematical Sciences， Chongqing Normal University

Department of Digital Medicine， Faculty of Biomedical Engineering and Imaging Medicine， Army Medical University （Third Military Medical University）

Department of Gynecology， Anshun People’s Hospital

Department of Obstetrics and Gynecology， First Affiliated Hospital， Army Medical University （Third Military Medical University）

Department of Gastroenterology, First Affiliated Hospital, Army Medical University (Third Military Medical University)

⁰