Automatic Evaluation of Progression Angle and Fetal Head Station through Intrapartum Echographic Monitoring

Abstract

Labor progression is routinely assessed through transvaginal digital inspections, meaning that the clinical decisions taken during the most delicate phase of pregnancy are subjective and scarcely supported by technological devices. In response to such inadequacies, we combined intrapartum echographic acquisitions with advanced tracking algorithms in a new method for noninvasive, quantitative, and automatic monitoring of labor. Aim of this work is the preliminary clinical validation and accuracy evaluation of our automatic algorithm in assessing progression angle (PA) and fetal head station (FHS). A cohort of 10 parturients underwent conventional labor management, with additional translabial echographic examinations after each uterine contraction. PA and FHS were evaluated by our automatic algorithm on the acquired images. Additionally, an experienced clinical sonographer, blinded regarding the algorithm results, quantified on the same acquisitions of the two parameters through manual contouring, which were considered as the standard reference in the evaluation of automatic algorithm and routine method accuracies. The automatic algorithm (mean error ± 2SD) provided a global accuracy of 0.9 ± 4.0 mm for FHS and 4° ± 9° for PA, which is far above the diagnostic ability shown by the routine method, and therefore it resulted in a reliable method for earlier identification of abnormal labor patterns in support of clinical decisions.

Transperineal ultrasonography for labor management: accuracy and reliability

“…Poor reproducibility of head position analysis by digital examination is well known, with correct diagnosis rates ranging from 35 to 39% . We detected an even lower correct diagnosis rate (24%) even though head position was assessed by a senior obstetrician.…”

Validation of an automatic segmentation method to detect vertebral interfaces in ultrasound images

“…where p and r are respectively the precision and recall calculated as 3 Results and discussion Tables 1-3 report the results of the automatic segmentation validation performed by expert operator #1, #2, and #3 respectively. Table 4 shows the values of ALE and RLE calculated according to (7) and 8, respectively. Table 5 summarises the accuracy of the segmentation algorithm as expressed by the F 1 -score.…”

“…A possible alternative is represented by the employment of dedicated ultrasound (US) techniques, which are radiation-free, portable, less expensive than DXA and available in primary care settings. In fact, bone health assessment is just one out of the several biomedical applications of US systems that have been introduced in the last years because of their mentioned intrinsic advantages over competing technologies [6][7][8][9][10][11][12][13][14][15][16]. In this context, the effectiveness of several quantitative US (QUS) methods for bone health assessment and osteoporosis diagnosis has been recently investigated [17][18][19][20].…”

Automatic ultrasound technique to measure angle of progression during labor

“…In this context, a real‐time tracking algorithm for non‐invasive and automatic monitoring of AoP during the second stage of labor was developed by our research group and tested preliminarily on both a birth simulator and a small number of parturients. The aim of the present study was to introduce an improved version of our algorithm and to evaluate its accuracy in a routine clinical context.…”