A deep learning-based approach for rectus abdominis segmentation and distance measurement in ultrasonography.

Abstract

Introduction: Diastasis recti abdominis (DRA) is a common condition in postpartum women. Measuring the distance between separated rectus abdominis (RA) in ultrasound images is a reliable method for the diagnosis of this disease. In clinical practice, the RA distance in multiple ultrasound images of a patient is measured by experienced sonographers, which is time-consuming, labor-intensive, and highly dependent on experience of operators. Therefore, an objective and fully automatic technique is highly desired to improve the DRA diagnostic efficiency. This study aimed to demonstrate the deep learning-based methods on the performance of RA segmentation and distance measurement in ultrasound images. Methods: A total of 675 RA ultrasound images were collected from 94 postpartum women, and were split into training (448 images), validation (86 images), and test (141 images) datasets. Three segmentation models including U-Net, UNet++ and Res-UNet were evaluated on their performance of RA segmentation and distance measurement. Results: Res-UNet model outperformed the other two models with the highest Dice score (85.93% ± 0.26%), the highest MIoU score (76.00% ± 0.39%) and the lowest Hausdorff distance (21.80 ± 0.76mm). The average physical distance between RAs measured from the segmentation masks generated by Res-UNet and that measured by experienced sonographers was only 3.44 ± 0.16mm. In addition, these two measurements were highly correlated with each other (r = 0.944), with no systematic difference. Conclusion: Deep learning model Res-UNet has good reliability in RA segmentation and distance measurement in ultrasound images, with great potential in the clinical diagnosis of DRA.