Abstract
Fractional flow reserve (FFR) is the reference standard for the physiological significance of a coronary stenosis, but it requires a pressure wire and hyperemic stimulation and is not measured for ev- ery lesion. Intravascular ultrasound (IVUS) morphology can be used to estimate FFR-defined significance, but area-based morphology does not capture calcified or attenuated plaque. We add interpretable plaque characterization descriptors to an IVUS morphology baseline and evaluate FFR prediction across six classifier families. The extended feature set improves test AUROC in every classifier, and the improvement concentrates in borderline lesions near the FFR cutoff. Integrated discrimination improvement and decision curve analysis show the same concentration, and permutation importance ranks several descriptors among the most informative features. These results suggest that plaque characterization descriptors add information beyond morphology for IVUS-based FFR prediction, most clearly in borderline lesions.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/STACOM2026_009.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=~Hyungjoo_Cho1
BibTex
@InProceedings{ChoHyu_IVUS_MICCAISAT2026,
author = { Cho, Hyungjoo AND Park, Chaebin},
title = { { IVUS Plaque Characterization Descriptors Carry FFR Information Beyond Morphology in Borderline Lesions } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17267},
month = {pending},
page = {pending}
}