Advanced Application of Artificial Intelligence for Pelvic Floor Ultrasound in Diagnosis and Treatment

doi:10.37015/AUDT.2023.230021

Abstract

Abstract:

Artificial intelligence-based pelvic floor ultrasound helps the diagnosis, preoperative assessment, and postoperative monitoring of female pelvic floor dysfunction (FPFD). The application of artificial intelligence in pelvic floor ultrasound mainly includes automatic segmentation and measurement, the diagnosis of muscle injury, childbirth prediction and postoperational evaluation. It can not only overcome the problem of operator experience dependence but also improve work efficiency and simplify the workflow, which has popularized the application of pelvic floor ultrasound. However, most of the current research is still limited to the automatic segmentation of three-dimensional axial plane levator hiatus (LH). The automatic reconstruction, real-time tracking of 3D/4D images and the imaging navigation of pelvic floor surgery remain major challenges for researchers.

Key words: Pelvic floor ultrasound; Artificial intelligence; Female pelvic floor dysfunction

Enze Qu, MD, Xinling Zhang, MD. Advanced Application of Artificial Intelligence for Pelvic Floor Ultrasound in Diagnosis and Treatment. Advanced Ultrasound in Diagnosis and Therapy, 2023, 7(2): 114-121.

Figures/Tables 5

Figure 1

Figure 2

Figure 3A

Figure 3B

Figure 3C

References 35

[1]	Doumouchtsis SK, de Tayrac R, Lee J, Daly O, Melendez-Munoz J, Lindo FM, et al. An International Continence Society (ICS)/ International Urogynecological Association (IUGA) joint report on the terminology for the assessment and management of obstetric pelvic floor disorders. Int Urogynecol J 2023; 34:1-42.
[2]	AIUM/IUGA practice parameter for the performance of Urogynecological ultrasound examinations: developed in collaboration with the ACR, the AUGS, the AUA, and the SRU. Int Urogynecol J 2019; 30:1389-1400. doi: 10.1007/s00192-019-03954-5
[3]	Khatri G, Bhosale PR, Robbins JB, Akin EA, Ascher SM, et al. ACR Appropriateness Criteria® pelvic floor dysfunction in females. Journal of the American College of Radiology 2022; 19:S137-S155.
[4]	Dietz HP. Pelvic floor ultrasound: a review. Clin Obstet Gynecol 2017; 60:58-81. doi: 10.1097/GRF.0000000000000264 pmid: 28005595
[5]	Handa VL, Roem J, Blomquist JL, Dietz HP, Muñoz A. Pelvic organ prolapse as a function of levator ani avulsion, hiatus size, and strength. Am J Obstet Gynecol 2019; 221:41.e1-41.e7.
[6]	Ying T, Li Q, Xu L, Liu F, Hu B. Three-dimensional ultrasound appearance of pelvic floor in nulliparous women and pelvic organ prolapse women. Int J Med Sci 2012; 9:894-900. doi: 10.7150/ijms.4829 pmid: 23155363
[7]	Majida M, Braekken I, Bø K, Benth J, Engh M. Anterior but not posterior compartment prolapse is associated with levator hiatus area: a three- and four-dimensional transperineal ultrasound study. BJOG 2010; 118:329-337. doi: 10.1111/bjo.2011.118.issue-3
[8]	Sindhwani N, Barbosa D, Alessandrini M, Heyde B, Dietz HP, D'Hooge J, et al. Semi-automatic outlining of levator hiatus. Ultrasound Obstet Gynecol 2016; 48:98-105. doi: 10.1002/uog.15777 pmid: 26434661
[9]	Tingting Y, Huifang W, Hua C, Dong N, Qiuxiang C, Xiaoshuang D, et al. Study on the practicality of the semi‐automatic measurement for the urogenital hiatus. Chin J Ultrasonogr 2019; 28:256-260.
[10]	Bonmati E, Hu Y, Sindhwani N, Dietz HP, D’hooge J, Barratt D, et al. Automatic segmentation method of pelvic floor levator hiatus in ultrasound using a self-normalizing neural network. J Med Imag 2018; 5:021206.
[11]	Li X, Hong Y, Kong D, Zhang X. Automatic segmentation of levator hiatus from ultrasound images using U-net with dense connections. Phys Med Biol 2019; 64:075015. doi: 10.1088/1361-6560/ab0ef4
[12]	Van den Noort F, Manzini C, van der Vaart CH, Slump CH, Grob ATM. Automatic identification and segmentation of slice of minimal hiatal dimensions in transperineal ultrasound volumes. Ultrasound Obstet Gynecol 2022; 60:570-576. doi: 10.1002/uog.v60.4
[13]	Huang Z, Qu E, Meng Y, Zhang M, Wei Q, Bai X, et al. Deep learning-based pelvic levator hiatus segmentation from ultrasound images. Eur J Radiol Open 2022; 9:100412. doi: 10.1016/j.ejro.2022.100412
[14]	Williams H, Cattani L, Van Schoubroeck D, Yaqub M, Sudre C, Vercauteren T, et al. Automatic extraction of hiatal dimensions in 3-D transperineal pelvic ultrasound recordings. Ultrasound Med Biol 2021; 47:3470-3479. doi: 10.1016/j.ultrasmedbio.2021.08.009 pmid: 34538535
[15]	Xia W, Ameri G, Fakim D, Akhuanzada H, Raza MZ, Shobeiri SA, et al. Automatic plane of minimal hiatal dimensions extraction from 3D female pelvic floor ultrasound. IEEE Trans Med Imaging 2022; 41:3873-3883. doi: 10.1109/TMI.2022.3199968
[16]	Cyr MP, Kruger J, Wong V, Dumoulin C, Girard I, Morin M. Pelvic floor morphometry and function in women with and without puborectalis avulsion in the early postpartum period. Am J Obstet Gynecol 2017; 216:274.e1-e8.
[17]	Guzmán Rojas R, Wong V, Shek KL, Dietz HP. Impact of levator trauma on pelvic floor muscle function. Int Urogynecol J 2013; 25:375-380. doi: 10.1007/s00192-013-2226-4
[18]	Van Delft K, Sultan A, Thakar R, Schwertner-Tiepelmann N, Kluivers K. The relationship between postpartum levator ani muscle avulsion and signs and symptoms of pelvic floor dysfunction. BJOG 2014; 121:1164-1172. doi: 10.1111/bjo.2014.121.issue-9
[19]	Van den Noort F, Grob ATM, Slump CH, van der Vaart CH, van Stralen M. Automatic segmentation of puborectalis muscle on three‐dimensional transperineal ultrasound. Ultrasound Obstet Gynecol 2018; 52:97-102. doi: 10.1002/uog.18927 pmid: 29024119
[20]	Noort F, Vaart CH, Grob ATM, Waarsenburg MK, Slump CH, Stralen M. Deep learning enables automatic quantitative assessment of puborectalis muscle and urogenital hiatus in plane of minimal hiatal dimensions. Ultrasound Obstet Gynecol 2019; 54:270-275. doi: 10.1002/uog.20181 pmid: 30461079
[21]	Wu S, Ren Y, Lin X, Huang Z, Zheng Z, Zhang X. Development and validation of a composite AI model for the diagnosis of levator ani muscle avulsion. Eur Radiol 2022; 32:5898-5906. doi: 10.1007/s00330-022-08754-y pmid: 35362748
[22]	Shek KL, Zazzera VD, Atan IK, Rojas RG, Langer S, Dietz HP. The evolution of transperineal ultrasound findings of the external anal sphincter during the first years after childbirth. Int Urogynecol J 2016; 27:1899-1903. pmid: 27250832
[23]	Jangö H, Langhoff-Roos J, Rosthøj S, Sakse A. Recurrent obstetric anal sphincter injury and the risk of long-term anal incontinence. Am J Obstet Gynecol 2017; 216: 610.e1-e8. doi: 10.1016/j.ajog.2017.02.010
[24]	Sultan AH, Thakar R. Lower genital tract and anal sphincter trauma. Best Pract Res Clin Obstet Gynaecol 2002; 16:99-115. doi: 10.1053/beog.2002.0258
[25]	Zhang M, Lin X, Zheng Z, Chen Y, Ren Y, Zhang X. Artificial intelligence models derived from 2D transperineal ultrasound images in the clinical diagnosis of stress urinary incontinence. Int Urogynecol J 2021; 33:1179-1185. doi: 10.1007/s00192-021-04859-y
[26]	Youssef A, Salsi G, Montaguti E, Bellussi F, Pacella G, Azzarone C, et al. Automated measurement of the angle of progression in labor: a feasibility and reliability study. Fetal Diagn Ther 2017; 41:293-299. doi: 10.1159/000448947 pmid: 27592216
[27]	Conversano F, Peccarisi M, Pisani P, Di Paola M, De Marco T, Franchini R, et al. Automatic ultrasound technique to measure angle of progression during labor. Ultrasound Obstet Gynecol 2017; 50:766-775. doi: 10.1002/uog.17441 pmid: 28233418
[28]	Angeli L, Conversano F, Dall’Asta A, Volpe N, Simone M, Di Pasquo E, et al. New technique for automatic sonographic measurement of change in head-perineum distance and angle of progression during active phase of second stage of labor. Ultrasound Obstet Gynecol 2020; 56:597-602. doi: 10.1002/uog.21963 pmid: 31909525
[29]	Shen YT, Chen L, Yue WW, Xu HX. Artificial intelligence in ultrasound. Eur J Radiol 2021; 139:109717. doi: 10.1016/j.ejrad.2021.109717
[30]	Yin P, Wang H. Evaluation of nursing effect of pelvic floor rehabilitation training on pelvic organ prolapse in postpartum pregnant women under ultrasound imaging with artificial intelligence algorithm. Comput Math Methods Med 2022; 2022:1786994.
[31]	Zhu Y, Zhang J, Ji Z, Liu W, Li M, Xia E, et al. Ultrasound evaluation of pelvic floor function after transumbilical laparoscopic single-site total hysterectomy using deep learning algorithm. Comput Math Methods Med 2022; 2022:1116332.
[32]	Yu H, Zhao Z, Duan X, Zhou J, Su D. Ultrasound image under artificial intelligence algorithm to evaluate the intervention effect of accelerated rehabilitation surgery nursing on laparoscopic hysterectomy. Comput Intell Neurosci 2022; 2022:9042954.
[33]	Chen L, Lu C. Image enhancement algorithm-based ultrasound on pelvic floor rehabilitation training in preventing postpartum female pelvic floor dysfunction. Comput Math Methods Med 2022; 2022:8002055.
[34]	Lubner RJ, Barber SR, Knoll RM, Kempfle J, Lee DJ, Reinshagen KL, et al. Transcanal computed tomography views for transcanal endoscopic lateral skull base surgery: pilot cadaveric study. J Neurol Surg B Skull Base 2021; 82:338-344. doi: 10.1055/s-0039-3400219
[35]	Jing B, Qian R, Jiang D, Gai Y, Liu Z, Guo F, et al. Extracellular vesicles based pre-targeting strategy enables multi-modal imaging of orthotopic colon cancer and image-guided surgery. J Nanobiotechnology 2021; 19:151. doi: 10.1186/s12951-021-00888-3