Abstract
Manual labelling of fetal ultrasound (US) standard planes is a tedious task due to variability in acquisition, imaging systems, image quality, and human annotations, especially in high volume clinical settings. However, even in conventional Artificial Intelligence (AI)-assisted workflows, cases are assigned to reviewers without considering case complexity or the level of expertise required for accurate assessment. We propose Fetal-CARE, a human-AI collaborative framework based on Evidential Deep Learning (EDL) to intelligently allocate cases to reviewers based on their expertise. Fetal-CARE leverages EDL’s ability to decompose its predictive uncertainty into vacuity, which is an epistemic uncertainty measure that quantifies the lack of evidence supporting a prediction. Vacuity is used to dynamically route cases across reviewer skill levels using calibrated vacuity thresholds, routing low, moderate, and high vacuity cases to junior, senior, and expert reviewers, respectively. Fetal-CARE was validated on 22,987 images from 1500 patients, representing 20 standard planes. By aligning reviewer expertise with case complexity, Fetal-CARE reduces total review time by 22.1% (∼4.2 hours) compared to conventional workflows without compromising the quality of reviewer verification. This demonstrates the potential of uncertaintyaware human-AI collaborative frameworks to assist reviewers by reducing workload and improving efficiency in clinical imaging tasks.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/HAIC26_023.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/forum?id=pRB0sVkSHZ
BibTex
@InProceedings{M.Lak_FetalCARE_MICCAISAT2026,
author = { M., Lakshminarayanan AND Parthasarathy, Srivibha AND Ram, Keerthi AND Ayyasamy, Shyam AND Seshadri, Suresh AND Lakshmanan, Manojkumar AND Sivaprakasam, Mohanasankar},
title = { { Fetal-CARE: Collaborative Annotation with Reviewer-Stratified Expertise for Fetal Ultrasound Standard Plane Classification } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17279},
month = {pending},
page = {pending}
}
