Skip to main content
SMFM 2026 Pregnancy Meeting Main banner
Icon Legend
This session is not in your schedule.
This session is in your schedule. Click again to remove it.
Presentation Icons
Additional registration fee required
Additional registration fee required
Faculty have requested this content not be shared outside of the session
Faculty have requested this content not be shared outside of the session
CME Credit Offered
CME Credit Offered
Abstract Award
Abstract Award
Recording available 2/16-5/2
Recording available 2/16-5/2
AIUM Credit
AIUM Credit
Foundation Awardee
Foundation Awardee
Poster Icons
Abstract Award
Abstract Award
Foundation Awardee
Foundation Awardee

Poster Session 3

Category: Labor

Poster Session 3

(873) Automated AI-Based Assessment of Fetal Head Station Through Intrapartum Ultrasound: A Proof of Concept

Thursday, February 12, 2026
10:30 AM - 12:00 PM  
Objective:
This study aimed to develop and evaluate an AI-based algorithm for automatically assessed fetal head station from intrapartum transperineal ultrasound videos, focusing on the angle of progression (AOP) and head-perineum distance (HPD), which have not yet been analyzed together by a single automated system.

Study Design:
A deep learning algorithm was trained on 9,314 expert-classified ultrasound frames extracted from 314 ultrasound videos recorded during all stages of labor. Frames were manually categorized into four quality groups: “Good”, “So-so”, “Bad”, or “Uninteresting”. Frames classified as good or so-so were further annotated for either AOP or HPD. The model was trained to detect optimal frames and automatically measure AOP, and a second module was developed to perform the same task for HPD. All data were randomly divided into training (80%) and validation (20%) sets using expert annotations as references.

Results:
The model achieved a mean absolute error of 1.1° (SD 1.5°) for AOP measurement across 4,025 good or so-so frames (Figures 1 and 2). For HPD, analysis of 546 annotated images demonstrated a mean absolute error of 1.7 mm (SD 3.5 mm) compared to expert measurements (Figure 1).

Conclusion:
This proof-of-concept AI algorithm facilitates objective and automated evaluation of fetal head descent via intrapartum ultrasound. The approach demonstrates considerable potential for minimizing operator variability and supporting real-time clinical decision-making during labor. Current efforts include expanding validation cohorts, increasing and diversifying the training dataset, adding fetal head position analysis, and preparing for clinical implementation.