Abstract
Accurate fetal biometry measurements from ultrasound examinations are critical for estimating clinical indicators like gestational age (GA), monitoring fetal growth, and assessing overall fetal well-being. Clinicians annotate the required measurements by placing calipers on the standard fetal planes. However, the reliability of these measurements depends heavily on the correct placement of calipers by sonographers. Even small deviations in caliper positioning can introduce clinically significant errors in biometric measurements and clinical indicators. While expert sonographers achieve high measurement consistency, their availability is limited, and less experienced operators are prone to annotation variability and placement errors. In this work, we present \textbf{SonoAudit}, an automated caliper auditing framework for fetal ultrasound biometry that evaluates the quality of clinician-placed calipers and provides objective feedback on measurement correctness. The proposed system localizes caliper annotations in fetal ultrasound images and segments the relevant anatomical structures, enabling assessment of caliper placement against clinically established measurement guidelines to determine whether the annotations satisfy standard measurement criteria. The proposed framework further estimates biometric measurements and corresponding clinical indicators, enabling quantitative assessment of annotation quality and its impact on fetal growth evaluation. Validation on patient studies demonstrated the feasibility of automated caliper auditing and its potential as a quality-control tool for fetal ultrasound examinations. The proposed framework achieved robust caliper detection and localization, with an average Precision of 0.88, a mean localization error of 3.05 ± 1.61 pixels, and 88.1\% PCK@5, indicating accurate caliper placement within a 5-pixel tolerance of expert annotations. And attain an average MAE of 1.13 mm for biometric measurements.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/AMAI_021.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/profile?id=%7EVasanth_Ambrose1
BibTex
@InProceedings{AmbVas_SonoAudit_MICCAISAT2026,
author = { Ambrose, Vasanth AND Dhore, Manasee Dnyaneshwar AND Ayyasamy, Shyam AND Ram, Keerthi AND Lakshmanan, Manojkumar AND Sivaprakasam, Mohanasankar},
title = { { SonoAudit: A Framework for Auditing Caliper Placement in Fetal Ultrasound Biometry } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17273},
month = {pending},
page = {pending}
}