Beyond Segmentation: Coronary Artery Calcium Scoring with Frozen Self-Supervised CT Features

Coronary artery calcium (CAC) scoring on computed tomography (CT) acquired for other indications could provide calcium-burden information without a dedicated scoring examination. We investigate direct, segmentation-free Agatston score prediction from frozen CT patch representations using only volume-level supervision for the scoring head. A lightweight additive head maps attention-selected features to non-negative contributions, combines them within slices, and sums slice scores across each volume. In developmental evaluation, applying the nonlinear mapping before aggregation improved linearly weighted κ by 0.27–0.38 over a pooled multilayer perceptron across six encoders. Using spatially adaptive label-guided temperature (SALT) features, held-out κ was 0.930 on gated CT and 0.844 on contrast-enhanced coronary CT angiography (CCTA), with separately fitted heads. On external non-gated CT, a head fitted on 165 patients from the same cohort achieved κ=0.727 on 40 held-out patients; patient-level five-fold cross-validation over all 205 patients yielded κ=0.639, indicating preliminary local-adaptation performance. Unchanged-head external gated transfer achieved κ=0.854 (n=443). Gated intraclass correlation coefficient ICC(A,1) on log(1+score) was 0.984. Study-level CAC scores served as CCTA reference targets; non-contrast images were not model inputs. SALT uses gated calcium masks during pretraining, not downstream scoring. Its highest-attention patch overlapped calcium in 89.5% of calcium-bearing slices, but localization rankings did not directly track scoring rankings. These results support direct, spatially decomposable CAC prediction from reusable features; broader validation is needed before clinical use.

Authors

Institutions

Publication Details

Journal
Journal of Imaging
Published
2026-11-16
DOI
https://doi.org/10.3390/jimaging12110579
Primary Topic
Cardiac Imaging and Diagnostics
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Beyond Segmentation: Coronary Artery Calcium Scoring with Frozen Self-Supervised CT Features

C. Seth Parker, Vincent L. Sorrell, Caroline Leach, Steve Leung et al.
Journal of Imaging
Cardiac Imaging and Diagnostics
article

Beyond Segmentation: Coronary Artery Calcium Scoring with Frozen Self-Supervised CT Features

C. Seth Parker, Vincent L. Sorrell, Caroline Leach, Steve Leung, Stephen Hobbs, Cody Bumgardner, M. Elizabeth Oates, Mahmut Selman Gokmen, Jie Zhang, Moneera Haque, W. Brent Seales, Evan Damron
article en

Abstract

Coronary artery calcium (CAC) scoring on computed tomography (CT) acquired for other indications could provide calcium-burden information without a dedicated scoring examination. We investigate direct, segmentation-free Agatston score prediction from frozen CT patch representations using only volume-level supervision for the scoring head. A lightweight additive head maps attention-selected features to non-negative contributions, combines them within slices, and sums slice scores across each volume. In developmental evaluation, applying the nonlinear mapping before aggregation improved linearly weighted κ by 0.27–0.38 over a pooled multilayer perceptron across six encoders. Using spatially adaptive label-guided temperature (SALT) features, held-out κ was 0.930 on gated CT and 0.844 on contrast-enhanced coronary CT angiography (CCTA), with separately fitted heads. On external non-gated CT, a head fitted on 165 patients from the same cohort achieved κ=0.727 on 40 held-out patients; patient-level five-fold cross-validation over all 205 patients yielded κ=0.639, indicating preliminary local-adaptation performance. Unchanged-head external gated transfer achieved κ=0.854 (n=443). Gated intraclass correlation coefficient ICC(A,1) on log(1+score) was 0.984. Study-level CAC scores served as CCTA reference targets; non-contrast images were not model inputs. SALT uses gated calcium masks during pretraining, not downstream scoring. Its highest-attention patch overlapped calcium in 89.5% of calcium-bearing slices, but localization rankings did not directly track scoring rankings. These results support direct, spatially decomposable CAC prediction from reusable features; broader validation is needed before clinical use.

Journal of ImagingVol. 12(11)
University of Kentucky (US)
Cardiac Imaging and Diagnostics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon