基于磁共振成像的女性盆底器官三维数字模型重建的研究进展

doi:10.3969/j.issn.1674-8115.2022.03.018

摘要/Abstract

摘要：

女性盆底器官、肌肉及周围结缔组织的结构和功能的改变是造成女性盆底功能障碍性疾病（pelvic floor disorders，PFD）的主要原因，细致了解盆底病理生理状态下的空间解剖结构能够帮助临床医师做出精确诊断以优化治疗策略。磁共振成像（magnetic resonance imaging，MRI）技术的广泛应用提高了临床医师对于盆底构造的认识，但其对于盆底结构的展示仍停留于二维平面影像，无法直观展示三维空间结构。而基于MRI的三维重建技术能够将女性盆底器官结构转化为数字模型用以观察、测量甚至用于三维打印后进行逆向分析，极大地推动了临床对于PFD发病到治疗的认识并为个体化诊疗提供依据。尽管如此，现有MRI三维重建技术尚未成熟，如不同商业软件使用方式各有优劣、不同图形识别技术算法各异、三维重建模型尚无统一评价标准、建模效率与质量难以平衡等问题，均限制其成为有效的PFD的医学研究手段。为此，该文归纳基于MRI的女性盆底组织器官三维数字模型重建的研究进展，旨在为PFD的临床诊治及科学研究提供参考。

关键词: 盆底, 磁共振成像, 三维成像, 图形识别, 深度学习

Abstract:

Changes in the structure and function of female pelvic floor organs, muscles and surrounding connective tissue are the main causes of pelvic floor disorders (PFD), and a detailed understanding of the spatial anatomy of the pelvic floor under physiological and pathological conditions can help clinicians make accurate diagnoses and optimize treatment strategies. The widespread use of magnetic resonance imaging (MRI) technology has improved clinicians' understanding of the pelvic floor structure, but presentation of the pelvic floor structure is still limited to two-dimensional planar images and the three-dimensional (3D) spatial structure cannot be visualized. The 3D reconstruction technology based on MRI can transform the structure of the female pelvic floor organs into digital models for observation, measurement and even 3D printing for inverse analysis, which greatly promotes the clinical understanding of the pathogenesis and treatment of PFD and provides basis for individualized treatment. However, the existing MRI-based 3D reconstruction technology is not yet mature, for example different advantages and disadvantages of different commercial softwares, different algorithms of different image recognition techniques, lack of uniform evaluation criteria for 3D reconstruction models, and difficulty of balancing modeling efficiency and quality, which limit it as an effective medical research tool for PFD. This paper reviews the research of 3D digital model reconstruction of female pelvic floor tissue and organs based on MRI, aiming to provide reference for clinical diagnosis, treatment and scientific research of PFD.

Key words: pelvic floor, magnetic resonance imaging (MRI), three-dimensional imaging, pattern recognition, deep learning

中图分类号:

R711.2

陈立奇, 薛卓维, 吴氢凯. 基于磁共振成像的女性盆底器官三维数字模型重建的研究进展[J]. 上海交通大学学报（医学版）, 2022, 42(3): 381-386.

CHEN Liqi, XUE Zhuowei, WU Qingkai. Review of MRI-based three-dimensional digital model reconstruction of female pelvic floor organs[J]. Journal of Shanghai Jiao Tong University (Medical Science), 2022, 42(3): 381-386.

参考文献 33

1	李志毅, 朱兰, 徐涛, 等. 中国城市地区女性盆腔器官脱垂临床流行病学调查[J]. 中华医学杂志, 2019, 99(11): 857-861.
2	VERBEEK M, HAYWARD L. Pelvic floor dysfunction and its effect on quality of sexual life[J]. Sex Med Rev, 2019, 7(4): 559-564.
3	CHEN L Y, LENZ F, ALT C D, et al. MRI visible Fe₃O₄ polypropylene mesh: 3D reconstruction of spatial relation to bony pelvis and neurovascular structures[J]. Int Urogynecol J, 2017, 28(8): 1131-1138.
4	FITZGERALD J, RICHTER L A. The role of MRI in the diagnosis of pelvic floor disorders[J]. Curr Urol Rep, 2020, 21(7): 26.
5	刘萍, 唐连, 陈春林, 等. 盆腔器官脱垂盆腔器官静动态磁共振成像三维变化特点研究[J]. 中国实用妇科与产科杂志, 2018, 34(3): 275-281.
6	ARIF-TIWARI H, TWISS C O, LIN F C, et al. Improved detection of pelvic organ prolapse: comparative utility of defecography phase sequence to nondefecography Valsalva maneuvers in dynamic pelvic floor magnetic resonance imaging[J]. Curr Probl Diagn Radiol, 2019, 48(4): 342-347.
7	RAMAGE L, SIMILLIS C, YEN C, et al. Magnetic resonance defecography versus clinical examination and fluoroscopy: a systematic review and meta-analysis[J]. Tech Coloproctol, 2017, 21(12): 915-927.
8	HUEBNER M, DELANCEY J O L. Levels of pelvic floor support: what do they look like on magnetic resonance imaging?[J]. Int Urogynecol J, 2019, 30(9): 1593-1595.
9	崔国策, 周娇娇, 李华山. 基于MRI检查二维、三维重建图像的直肠脱垂女性患者盆底肛提肌形态解剖学观察[J]. 山东医药, 2019, 59(12): 22-26.
10	JEANDITGAUTIER E, MAYEUR O, BRIEU M, et al. Mobility and stress analysis of different surgical simulations during a sacral colpopexy, using a finite element model of the pelvic system[J]. Int Urogynecol J, 2016, 27(6): 951-957.
11	雷玲, 赵骏, 吴毅, 等. 基于磁共振成像子宫脱垂患者盆底结构三维重建与分析[J]. 实用妇产科杂志, 2016, 32(4): 289-294.
12	BROCKER K A, MOKRY T, ALT C D, et al. 3D reconstruction of MR-visible Fe₃O₄-mesh implants: pelvic mesh measurement techniques and preliminary findings[J]. Neurourol Urodyn, 2019, 38(1): 369-378.
13	LUO J J, BETSCHART C, CHEN L Y, et al. Using stress MRI to analyze the 3D changes in apical ligament geometry from rest to maximal Valsalva: a pilot study[J]. Int Urogynecol J, 2014, 25(2): 197-203.
14	贾翔. MRI三维可视化技术结合逆向分析法在女性盆底疾病中的应用[D]. 苏州: 苏州大学, 2016.
15	PIPITONE F, SWENSON C W, DELANCEY J O L, et al. Novel 3D MRI technique to measure perineal membrane structural changes with pregnancy and childbirth: technique development and measurement feasibility[J]. Int Urogynecol J, 2021, 32(9): 2413-2420.
16	刘萍, 唐连. 磁共振成像盆底三维重建的方法及意义[J]. 中国实用妇科与产科杂志, 2017, 33(10): 1014-1018.
17	郭建生, 陈柯蓉, 刘嘉, 等. 个体化经肛提肌外腹会阴联合切除术治疗低位直肠后壁肿瘤对盆底影响的有限元分析[J]. 中国肿瘤临床, 2017, 44(24): 1268-1271.
18	刘潇, 张彬, 任力娟, 等. 女性盆底功能障碍性疾病中肛提肌的有限元应力分析[J]. 中华临床医师杂志(电子版), 2017, 11(9): 1609-1612.
19	LI Y G, CHEN C L, LIAO K D, et al. Study on the cephalopelvic relationship with cephalic presentation in nulliparous full-term Chinese pregnant women by MRI with three-dimensional reconstruction[J]. Arch Gynecol Obstet, 2018, 298(2): 433-441.
20	LI J R, LEI L, LUO N, et al. Architecture of female urethral supporting structures based on undeformed high-resolution sectional anatomical images[J]. Anat Sci Int, 2021, 96(1): 30-41.
21	杨晓红, 徐惠成, 陈伟, 等. 子宫脱垂患者骶主韧带MR三维重建模型的研究[J]. 第三军医大学学报, 2012, 34(6): 546-550.
22	LERCH T D, DEGONDA C, SCHMARANZER F, et al. Patient-specific 3-D magnetic resonance imaging-based dynamic simulation of hip impingement and range of motion can replace 3-D computed tomography-based simulation for patients with femoroacetabular impingement: implications for planning open hip preservation surgery and hip arthroscopy[J]. Am J Sports Med, 2019, 47(12): 2966-2977.
23	张冀, 郑传哲. 基于多尺度CNN-RNN的单图三维重建网络[J]. 计算机应用研究, 2020, 37(11): 3487-3491.
24	周洁洁, 张洋, 苏敏莹, 等. 基于动态增强磁共振成像的影像组学和不同CNN的深度学习对乳腺良恶性病变的诊断价值[J]. 温州医科大学学报, 2020, 50(6): 475-479.
25	马昊, 李淑琴, 丁濛. 基于深度学习的人体动作草图到三维骨骼模型重建方法的研究[J]. 计算机应用研究, 2020, 37(6): 1867-1870.
26	丁明为. 基于深度神经网络的回波平面成像无参考扫描奈奎斯特伪影校正[D]. 厦门: 厦门大学, 2019.
27	SARI H S, REAUNGAMORNRAT J, CATALANO O A, et al. Evaluation of deep learning-based approaches to segment bowel air pockets and generate pelvic attenuation maps from CAIPIRINHA-accelerated Dixon MR images[J]. J Nucl Med, 2022, 63(3): 468-475.
28	ZABIHOLLAHY F, VISWANATHAN A N, SCHMIDT E J, et al. Fully automated multiorgan segmentation of female pelvic magnetic resonance images with coarse-to-fine convolutional neural network[J]. Med Phys, 2021, 48(11): 7028-7042.
29	LIU X, HAN C, WANG H, et al. Fully automated pelvic bone segmentation in multiparameteric MRI using a 3D convolutional neural network[J]. Insights Imaging, 2021, 12(1): 93.
30	CASTELVECCHI D. Can we open the black box of AI? [J]. Nature, 2016, 538(7623): 20-23.
31	叶建平, 王大平, 张吉帅, 等. 基于磁共振图像的骨骼分割的方法及其系统: CN103871057A[P]. 2017-07-28.
32	陈冰红. 基于灰度边缘融合的相似性多色谱图像降噪技术[J]. 电子测量技术, 2019, 42(11): 92-96.
33	FENG F, ASHTON-MILLER J A, DELANCEY J O L, et al. Feasibility of a deep learning-based method for automated localization of pelvic floor landmarks using stress MR images[J]. Int Urogynecol J, 2021, 32(11): 3069-3075.

[1]	林嘉希, 汪盛嘉, 赵鑫, 高欣, 殷民月, 朱锦舟. 基于深度卷积神经网络的Barrett食管内镜图片分类模型的建立[J]. 上海交通大学学报（医学版）, 2022, 42(5): 653-659.
[2]	王亦欢, 李若坤, 种欢欢, 严福华. 钆塞酸二钠增强磁共振成像在肝细胞癌生物学行为评估中的应用进展[J]. 上海交通大学学报(医学版), 2022, 42(1): 130-134.
[3]	陈翠, 金叶, 王琳, 李红丽, 万财凤, 姜立新. 30例乳腺化生性癌的多种影像学对比分析[J]. 上海交通大学学报(医学版), 2022, 42(1): 70-76.
[4]	刘子豪, 唐文芳, 王辉. 儿童脑肿瘤氨基酸PET显像的研究进展[J]. 上海交通大学学报(医学版), 2021, 41(7): 949-952.
[5]	李小敏, 曲扬, 张少霆, 赵亮, 刘畅, 谢帅宁, 戴尅戎, 艾松涛. 人工智能技术在骨肌系统影像学方面的应用[J]. 上海交通大学学报(医学版), 2021, 41(2): 262-266.
[6]	季莹莹，薛彬，黄悦，张剑蔚. 小儿磁共振成像检查中咪达唑仑口服复合右美托咪定滴鼻镇静的安全性和有效性[J]. 上海交通大学学报(医学版), 2020, 40(8): 1098-1102.
[7]	夏志鹏1，袁瑛2，杨希2，顾豪2，林晓曦2#，陶晓峰1#. 动态增强磁共振成像对静脉畸形硬化治疗中硬化剂选择的参考价值[J]. 上海交通大学学报(医学版), 2020, 40(7): 873-880.
[8]	葛晓乾1，李晓2，赵辉林2，孙贝贝2，许建荣2，刘晓晟2. 术前颈动脉斑块动态增强磁共振成像对支架置入后再狭窄发生的预测价值[J]. 上海交通大学学报(医学版), 2020, 40(7): 901-907.
[9]	周悦玲，丁巍，艾红兰，卢建新，丁峰，胡春. 维持性血液透析的终末期肾病患者脑结构性异常及认知功能分析[J]. 上海交通大学学报(医学版), 2020, 40(7): 962-967.
[10]	邱雨，吴氢凯，黄程胜. 触觉成像技术在盆底功能障碍性疾病中的应用进展[J]. 上海交通大学学报(医学版), 2020, 40(5): 671-673.
[11]	陆言巧，沈兰，何奔. 人工智能在心血管疾病的辅助诊疗中的应用[J]. 上海交通大学学报（医学版）, 2020, 40(2): 259-.
[12]	杨涛，陈俊，方贻儒. 双相障碍Ⅰ型患者磁共振成像的研究进展[J]. 上海交通大学学报(医学版), 2020, 40(12): 1660-1664.
[13]	岳秀慧，孔维丹，任继亮，袁瑛#，陶晓峰#. 3.0-T磁共振扩散加权成像联合动态增强成像对甲状腺良恶性结节的鉴别价值[J]. 上海交通大学学报(医学版), 2020, 40(10): 1393-1397.
[14]	李小敏1，曲扬1，武文2，赵亮3，张少霆3，郝永强2，戴尅戎2，艾松涛1. 3D打印切片盒在骨盆肿瘤边界三维定位中的应用初探[J]. 上海交通大学学报(医学版), 2020, 40(10): 1408-1413.
[15]	王滔1，张陈诚1，李殿友1，孙伯民1，傅萌2. 帕金森病脑深部电刺激电极术后位置规律分析[J]. 上海交通大学学报（医学版）, 2020, 40(1): 64-.