Related Experiment Video
Updated: Jan 3, 2026

Author Spotlight: Advancing Cardiovascular Imaging - Introducing the Spatially Weighted Calcium Score for Early Disease Detection
Published on: September 22, 2023
Evaluation of an AI-based, automatic coronary artery calcium scoring software
Mårten Sandstedt1,2, Lilian Henriksson3,4, Magnus Janzon5
1Center for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden. martensandstedt@gmail.com.
An artificial intelligence (AI) software for coronary artery calcium (CAC) scoring shows excellent accuracy and agreement compared to traditional methods. This AI tool is also significantly faster, making it a promising advancement in clinical settings.
Area of Science:
- Cardiology
- Radiology
- Artificial Intelligence in Medicine
Background:
- Coronary artery calcium (CAC) scoring is crucial for cardiovascular risk assessment.
- Current semi-automatic methods require significant user time and expertise.
- The development of automated CAC scoring tools is essential for clinical efficiency.
Purpose of the Study:
- To evaluate the performance of an artificial intelligence (AI)-based automatic coronary artery calcium (CAC) scoring software.
- To compare the AI software's results against a semi-automatic software as a reference standard.
- To assess the time efficiency of the automated CAC scoring method.
Main Methods:
- An observational study analyzed 315 non-contrast-enhanced calcium scoring computed tomography (CSCT) scans.
- Agatston score (AS), volume score (VS), mass score (MS), and lesion count were calculated using both semi-automatic and automatic software.
- Statistical analyses included correlation (Spearman's ⍴), agreement (ICC, Bland Altman plots), and time analysis.
Main Results:
- Excellent correlation (⍴ > 0.93) and agreement (ICC > 0.99) were observed for AS, VS, and MS between the two methods.
- High correlation (⍴ = 0.903) and agreement (ICC = 0.977) were found for the number of calcified lesions.
- The automatic method was significantly faster (36s vs 59s, p < 0.001) and demonstrated good agreement in risk category assignment (κ = 0.919).
Conclusions:
- AI-based automatic CAC scoring software demonstrates excellent correlation and agreement with semi-automatic methods.
- The automated software is a time-efficient alternative for CAC scoring in clinical practice.
- While accurate, the AI software showed a tendency for overestimation in risk category assignment.
Related Concept Videos
Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
Imaging Studies for Cardiovascular System V: CT
Acute Coronary Syndrome III: Diagnostic Studies
Coronary Artery Disease V: Interprofessional Care
Imaging Studies for Cardiovascular System III: X-Ray
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...

