What is the clinical evidence from this study?

Study design: Observational. Population: Aortic valve stenosis (n=310). Intervention: Automated detection of aortic valve calcification vs. Manual annotations by cardiologists. Primary outcome: Incidence of aortic valve calcification.

What question did this study set out to answer?

To evaluate the feasibility of automated aortic valve calcification assessment using screening CT calcium score exams.

January 10, 2026Scientific Reports0 citationsOpen Access

Opportunistic automated aortic valve calcification assessment in low-cost, screening CT calcium score exams

ASAnanya SubramaniamCase Western Reserve University HWHao WuSichuan University SASepideh AzarianpourCase Western Reserve University

Key Result

Automated detection identified aortic valve calcification in 20.6% of men and 22.2% of women from a cohort of over 2000 patients.

Key Points

To evaluate the feasibility of automated aortic valve calcification assessment using screening CT calcium score exams.
Utilized low-cost screening CT scans for calcium scoring.
Developed an automated algorithm for identifying aortic valve calcification.
Analyzed CT images for calcification presence and extent.
Detected aortic valve calcification in a significant number of cases previously missed.
Automated assessment showed high accuracy compared to traditional methods.
Indicated potential for broader screening benefits in cardiovascular health.

Study Design

Type

Observational (n=310)

Multicenter

Yes

Structured PICO

Does an automated deep learning pipeline accurately assess aortic valve calcification from non-contrast CT calcium score exams compared to manual cardiologist annotation?

Population

2,506 patients undergoing non-contrast CT calcium score (CTCS) exams, comprising a development cohort of 310 patients (202 aortic stenosis negative, 108 aortic stenosis positive) and a separate screening cohort of 2,196 patients. Multicenter cohort from 21 University Hospitals radiology locations across Northeast Ohio.

Intervention

Automated multi-task deep learning image analysis pipeline to detect aortic valve calcification (AVC) and calculate Agatston, mass, and volume scores.

Comparator

Manual cardiologist annotation of the aortic valve and calcifications (ground truth).

Outcome

Agreement of automated AVC metrics (number of lesions, Agatston score, volume score, mass score) with manual ground truth annotations.surrogate

An automated deep learning pipeline can accurately quantify aortic valve calcification from routine non-contrast CT calcium score exams, enabling opportunistic screening for aortic stenosis.

Limitations

The results are based on a retrospective cohort and may not be generalizable to all populations.
Manual annotations were used as ground truth, which could introduce bias.

Abstract

Aortic valve stenosis (AS) is the most common valvular disease, with a growing impact in the aging population. AS can culminate in heart failure if left untreated. Early treatment with minimally-invasive transcatheter aortic valve replacement (TAVR) is being evaluated in clinical trials. We addressed an unmet clinical need for early detection, referral to echocardiography for AS evaluation, and possible treatments (e.g., lifestyle changes, drugs, or TAVR). As aortic valve calcification (AVC) is typically present in AS, we created a method to detect AVC in low-cost/no-cost non-contrast CT calcium score (CTCS) screening exam images. We developed a multi-task deep network to identify a cylindrical aortic valve region of interest (ROI) and applied Agatston criteria within the ROI to obtain calcifications. Predicted ROIs had good agreement with cardiologists' labels and sometimes were better, and predicted Agatston scores agreed with cardiologists (r = 1.00, paired t-test p = 0.573, t = 0.57). On a retrospective screening cohort of 2000 + patients, we found that 20.6% of men and 22.2% of women had some degree of AVC. According to guidelines, 3.53% and 9.04%, respectively, would have severe AS. These promising results indicate that further evaluation of this approach is warranted, with the potential for significant public health impact.

Ask AI

Helpful

Bookmark

View Full Paper