New technique for automatic sonographic measurement of change in head–perineum distance and angle of progression during active phase of second stage of labor

Abstract

What are the novel findings of this work? We assessed the performance of a new automatic ultrasound technique for measurement of the change in head-perineum distance and angle of progression, two sonographic parameters that are highly predictive of fetal head station and mode of delivery, during the active phase of the second stage of labor. The algorithm proved to be as accurate as an experienced operator and to quickly provide the necessary measurements. What are the clinical implications of this work? The ability to calculate automatically the dynamic change in the most commonly used sonographic indices of fetal head station and progression may provide accurate and fundamental information to the clinician who is managing an obstructed or protracted second stage of labor, avoiding a time-consuming and technically challenging examination.

Novel artificial intelligence approach for automatic differentiation of fetal occiput anterior and non‐occiput anterior positions during labor

“…A ML algorithm could be trained to assess simultaneously, in the same axial scanning plane at TPU, both the fetal position and the fetal head station. It has already been shown that automatic measurement of the head-perineum distance (HPD) using dedicated software is feasible and accurate 43,44 . We believe that the greatest clinical benefit of a diagnostic ML model for the assessment of fetal head position would be gained from its use by non-expert examiners.…”

“…One study has explored the use of AI technology for fetal head biometry using three-dimensional volumes, showing a high level of agreement between experienced operators and the AI software for the measurement of both biparietal diameter and head circumference 34 . Other studies have not used AI, focusing their attention on the automatic measurement of TPU parameters, such as angle of progression and HPD [43][44][45][46][47] .…”

Multitask Deep Neural Network for the Fully Automatic Measurement of the Angle of Progression

“…In the former category, Conversano et al [32] proposed an algorithm that manually identifies the standard plane image first and adopts a pattern tracking algorithm for subsequent sessions to calculate AoP. Youssef et al [54] reported an AoP measurement method based on commercial software; however, the technical characteristics of the software are not explained in detail [55]. In the deep learning-based category, Zhou et al [33] applied an endto-end deep learning method to measure AoP, but this approach is not fully automatic because it does not include image classification.…”

A framework for computing angle of progression from transperineal ultrasound images for evaluating fetal head descent using a novel double branch network

“…At the second stage, segmented areas were ellipse-fitted and thereby coordinates of three key points (including the endpoints of the long axis of PS and the right tangent point of FH) were calculated for the AoP measurement. In the all-existing approaches, most studies have relied heavily on manual measurement, while a few studies attempted to automatically measure AoP (Conversano et al, 2017;Angeli et al, 2020a;Angeli et al, 2020b). Conversano et al (2017) combined morphological filters with pattern recognition methods to identify PS and FH, and segmented targets were used to calculate AoP.…”