Automatic Segmentation of Pelvic Organs in 3D Transperineal Ultrasound using Deep Learning

Szentimrey Z1, Ameri G2, Hong C3, Cheung R4, Ukwatta E1, Eltahawi A2

Research Type

Pure and Applied Science / Translational

Abstract Category

Imaging

Abstract 280
Pelvic Floor Muscle Function, Dysfunction and Morphology
Scientific Podium Short Oral Session 34
Friday 29th September 2023
14:37 - 14:45
Room 104AB
Imaging Pelvic Floor Pelvic Organ Prolapse Female
1. School of Engineering, University of Guelph, Guelph, Ontario, Canada, 2. Cosm Medical, Toronto, Ontario, Canada, 3. Department of Obstetrics & Gynecology, University of Michigan, Ann Arbor, Michigan, USA, 4. Department of Obstetrics & Gynaecology, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong
Presenter
Links

Abstract

Hypothesis / aims of study
Pelvic organ prolapse (POP) is one of the most common pelvic floor disorders (PFD) in females [1],[2]. Recent advances have been able to image the female pelvic floor using three dimensional (3D) transperineal ultrasound (TPUS) [3]. Previous works on 3D TPUS, have used deep learning methods to identify 2D locations including the plane of minimal hiatal dimensions (PMHD) and the levator hiatus. However, analysis of the entire 3D TPUS image still relies on manual segmentation. Thus, segmenting structures of interest using 3D deep learning methods can reduce the time required to analyze such images to provide a better understanding of the positions and interaction of the pelvic organs. The objective of this work was to develop a fully automated and first of its kind segmentation method to segment the pelvic organs in 3D TPUS to aid in the analysis and treatment of POP.
Study design, materials and methods
Segmentation models were developed using 3D TPUS images. The available dataset consisted of 161 3D TPUS volumes from 104 patients who presented to a tertiary urogynecology clinic with symptoms of pelvic floor disorders. Of the 161 3D TPUS volumes, 89 were captured at rest and 72 were captured during a Valsalva maneuver. An expert with prior experience in pelvic floor US interpretation and three trainees, who were trained by the expert, then manually segmented the relevant pelvic anatomical structures. These structures included the pubic symphysis, urethra, bladder, rectum, rectal ampulla, and anorectal angle. We separated the images patient-wise into train/validation/test sets with amounts 97/15/49 respectively. A deep learning segmentation model was developed using a 3D U-Net model with ResNet34 encoder. For comparison, a 2D slice-based U-Net model and a vanilla 3D U-Net model were also implemented. The models were compared to ground truth using the spatial overlap metric, i.e., the Dice similarity coefficient (DSC).
Results
An example of one segmentation result from each tested model as well as the manual ground truth are shown in Figure 1. A full summary of results for each model can be seen in Table 1.
Interpretation of results
The proposed 3D U-Net with ResNet34 encoder had the greatest DSC for each of the segmented structures on the 49-image test set and could segment one TPUS image in less than five seconds. The proposed model achieved 53.9%, 32.1%, 67.1%, 53.9%, 15.9% and 34.3% DSC for pubic symphysis, urethra, bladder, rectum, rectal ampulla, and anorectal angle respectively, as shown in Table 1. The results demonstrated that a deep learning model can effectively segment pelvic organs in 3D TPUS.
Concluding message
Deep learning models can provide accurate segmentations at a fraction of the time required for manual segmentation. Allowing for easier and faster 3D analysis of the pelvic floor. While the DSC can be improved with better model selection and tuning, the current results can be used for making clinical measurements such as the bladder descent or rectal ampulla descent.
Figure 1 Table 1. The test set mean DSC in % for the segmented structures pubic symphysis, urethra, bladder, rectum, rectal ampulla, and anorectal angle for each of the three models trained. These models are the 2D U-Net, 3D U-Net and 3D U-Net+ResNet34.
Figure 2 Figure 1: Example 3D TPUS image, ground truth and segmentation results. (a) Example of a 3D TPUS image, (b) the ground truth segmentation, (c) the 2D U-Net segmentation, (d) 3D U-Net segmentation, (e) 3D U-Net+ResNet34 segmentation, and colour legend.
References
  1. I. Nygaard et al., “Prevalence of symptomatic pelvic floor disorders in US women,” Jama, vol. 300, no. 11, pp. 1311–1316, 2008.
  2. J. M. Wu et al., “Prevalence and trends of symptomatic pelvic floor disorders in us women,” Obstetrics Gynecol., vol. 123, no. 1, p. 141, 2014.
  3. H. P. Dietz, “Pelvic floor ultrasound: A review,” Clin. Obstetrics Gynecol., vol. 60, no. 1, pp. 58–81, 2017.
Disclosures
Funding Cosm Medical, Mitacs, NSERC Clinical Trial No Subjects Human Ethics Committee University of Guelph Research Ethics Board. REB # 21-08-011 Helsinki Yes Informed Consent Yes
Citation

Continence 7S1 (2023) 100997
DOI: 10.1016/j.cont.2023.100997

03/11/2024 00:09:27