Deep learning enables automatic quantitative assessment of puborectalis muscle and urogenital hiatus in plane of minimal hiatal dimensions

Abstract

Objectives To measure the length, width and area of the urogenital hiatus (UH), and the length and mean echogenicity (MEP) of the puborectalis muscle (PRM), automatically and observer‐independently, in the plane of minimal hiatal dimensions on transperineal ultrasound (TPUS) images, by automatic segmentation of the UH and the PRM using deep learning. Methods In 1318 three‐ and four‐dimensional (3D/4D) TPUS volume datasets from 253 nulliparae at 12 and 36 weeks' gestation, two‐dimensional (2D) images in the plane of minimal hiatal dimensions with the PRM at rest, on maximum contraction and on maximum Valsalva maneuver, were obtained manually and the UH and PRM were segmented manually. In total, 713 of the images were used to train a convolutional neural network (CNN) to segment automatically the UH and PRM in the plane of minimal hiatal dimensions. In the remainder of the dataset (test set 1 (TS1); 601 images, four having been excluded), the performance of the CNN was evaluated by comparing automatic and manual segmentations. The performance of the CNN was also tested on 117 images from an independent dataset (test set 2 (TS2); two images having been excluded) from 40 nulliparae at 12 weeks' gestation, which were acquired and segmented manually by a different observer. The success of automatic segmentation was assessed visually. Based on the CNN segmentations, the following clinically relevant parameters were measured: the length, width and area of the UH, the length of the PRM and MEP. The overlap (Dice similarity index (DSI)) and surface distance (mean absolute distance (MAD) and Hausdorff distance (HDD)) between manual and CNN segmentations were measured to investigate their similarity. For the measured clinically relevant parameters, the intraclass correlation coefficients (ICCs) between manual and CNN results were determined. Results Fully automatic CNN segmentation was successful in 99.0% and 93.2% of images in TS1 and TS2, respectively. DSI, MAD and HDD showed good overlap and distance between manual and CNN segmentations in both test sets. This was reflected in the respective ICC values in TS1 and TS2 for the length (0.96 and 0.95), width (0.77 and 0.87) and area (0.96 and 0.91) of the UH, the length of the PRM (0.87 and 0.73) and MEP (0.95 and 0.97), which showed good to very good agreement. Conclusion Deep learning can be used to segment automatically and reliably the PRM and UH on 2D ultrasound images of the nulliparous pelvic floor in the plane of minimal hiatal dimensions. These segmentations can be used to measure reliably UH dimensions as well as PRM length and MEP. © 2018 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of the International Society of Ultrasound in Obstetrics and Gynecology.

Appearance of the levator ani muscle subdivisions on 3D transperineal ultrasound

“…However, the DSI is influenced by the shape and size of the segmented structure: small and/or elongated structures are more likely to have a lower DSI, because a mismatch of a few pixels has relatively more influence. The DSI values of the PRM, PAM, ICM and ES show good segmentation reproducibility (comparable to previous results on the PRM [ 34 ]). The smallest structures (i.e., the PVM and PPM) are most of the time less than 5 mm thick.…”

Type of levator ani muscle avulsion as predictor for the disappearance of avulsion

“…Three 4D ultrasound volumes of the pelvic floor were obtained during each exploration: at rest, at maximum contraction (objective and reliable method 28,29 ), and on Valsalva (for at least 6 seconds) 30 . Levator hiatus measurements (anteroposterior diameter, transverse diameter, and area 31 ) were performed in the plane of minimal dimensions (PMD), 16 as described in previous papers 32 . Complete LAM avulsion was defined based on maximum contraction in the multislice mode described above 33,34 and was diagnosed when abnormal insertion of the LAM was observed in three central slices.…”

Echogenicity of puborectalis muscle, cervix and vastus lateralis muscle in pregnancy in relation to mode of delivery

“…After storage on hard disk, offline analysis was performed using 4D View software 7.0 (GE Medical Systems) for MEP and puborectalis muscle area (PMA) and Matlab® R2010a software (The MathWorks Inc., Natick, MA, USA) for MEP, PMA, and mean echogenicity of the cervix and vastus lateralis muscle. The plane of minimal hiatal dimensions of the puborectalis muscle in axial position was selected and exported for automatic analysis of the MEP, PMA and hiatal dimensions of the puborectalis muscle. Echogenicity is based on the grayscale image in which the value for each pixel can vary between 0 (black) and 255 (white).…”