Automatic C-Plane Detection in Pelvic Floor Transperineal Volumetric Ultrasound

Abstract

Transperineal volumetric ultrasound (US) imaging has become routine practice for diagnosing pelvic floor disease (PFD). Hereto, clinical guidelines stipulate to make measurements in an anatomically defined 2D plane within a 3D volume, the so-called C-plane. This task is currently performed manually in clinical practice, which is labourintensive and requires expert knowledge of pelvic floor anatomy, as no computer-aided C-plane method exists. To automate this process, we propose a novel, guideline-driven approach for automatic detection of the C-plane. The method uses a convolutional neural network (CNN) to identify extreme coordinates of the symphysis pubis and levator ani muscle (which define the C-plane) directly via landmark regression. The C-plane is identified in a postprocessing step. When evaluated on 100 US volumes, our best performing method (multi-task regression with UNet) achieved a mean error of 6.05 mm and 4.81 degrees and took 20 seconds. Two experts blindly evaluated the quality of the automatically detected planes and manually defined the (gold standard) C-plane in terms of their clinical diagnostic quality. We show that the proposed method performs comparably to the manual definition. The automatic method reduces the average time to detect the C-plane by 100 seconds and reduces the need for high-level expertise in PFD US assessment.

Reply

“…There are indeed other options to detect the SMHD automatically. When documenting our study, we failed to cite the recently published work by Williams et al 2 , which focused on the automatic identification of the SMHD based on the detection of the center of the pubic symphysis and the anorectal angle. Their method follows the official guideline for manual selection of the SMHD.…”

Automatic Tomographic Ultrasound Imaging Sequence Extraction of the Anal Sphincter

“…Automatic assessment of the levator hiatus [1,5] utilised CNNs and active shape models [9], and performed within inter-observer variability. In other work, an automatic clinical solution was presented for the extraction of a plane of interest used in PFD assessment [12]. The paper utilised CNN landmark regression, and performed within inter-observer variability, while reducing the time required for assessment by 100 seconds.…”