Deep learning for vessel-specific coronary artery calcium scoring: validation on a multi-centre dataset

Artificial Intelligence in Cardiovascular Disease Prevention: Is it Ready for Prime Time?

PURPOSE OF REVIEW

This review evaluates how Artificial Intelligence (AI) enhances atherosclerotic cardiovascular disease (ASCVD) risk assessment, allows for opportunistic screening, and improves adherence to guidelines through the analysis of unstructured clinical data and patient-generated data. Additionally, it discusses strategies for integrating AI into clinical practice in preventive cardiology.

RECENT FINDINGS

AI models have shown superior performance in personalized ASCVD risk evaluations compared to traditional risk scores. These models now support automated detection of ASCVD risk markers, including coronary artery calcium (CAC), across various imaging modalities such as dedicated ECG-gated CT scans, chest X-rays, mammograms, coronary angiography, and non-gated chest CT scans. Moreover, large language model (LLM) pipelines are effective in identifying and addressing gaps and disparities in ASCVD preventive care, and can also enhance patient education. AI applications are proving invaluable in preventing and managing ASCVD and are primed for clinical use, provided they are implemented within well-regulated, iterative clinical pathways.

Artificial intelligence in coronary artery calcium score: rationale, different approaches, and outcomes

Almost 35 years after its introduction, coronary artery calcium score (CACS) not only survived technological advances but became one of the cornerstones of contemporary cardiovascular imaging. Its simplicity and quantitative nature established it as one of the most robust approaches for atherosclerotic cardiovascular disease risk stratification in primary prevention and a powerful tool to guide therapeutic choices. Groundbreaking advances in computational models and computer power translated into a surge of artificial intelligence (AI)-based approaches directly or indirectly linked to CACS analysis. This review aims to provide essential knowledge on the AI-based techniques currently applied to CACS, setting the stage for a holistic analysis of the use of these techniques in coronary artery calcium imaging. While the focus of the review will be detailing the evidence, strengths, and limitations of end-to-end CACS algorithms in electrocardiography-gated and non-gated scans, the current role of deep-learning image reconstructions, segmentation techniques, and combined applications such as simultaneous coronary artery calcium and pulmonary nodule segmentation, will also be discussed.

Implications of Bias in Artificial Intelligence: Considerations for Cardiovascular Imaging

PURPOSE OF REVIEW

Bias in artificial intelligence (AI) models can result in unintended consequences. In cardiovascular imaging, biased AI models used in clinical practice can negatively affect patient outcomes. Biased AI models result from decisions made when training and evaluating a model. This paper is a comprehensive guide for AI development teams to understand assumptions in datasets and chosen metrics for outcome/ground truth, and how this translates to real-world performance for cardiovascular disease (CVD).

RECENT FINDINGS

CVDs are the number one cause of mortality worldwide; however, the prevalence, burden, and outcomes of CVD vary across gender and race. Several biomarkers are also shown to vary among different populations and ethnic/racial groups. Inequalities in clinical trial inclusion, clinical presentation, diagnosis, and treatment are preserved in health data that is ultimately used to train AI algorithms, leading to potential biases in model performance. Despite the notion that AI models themselves are biased, AI can also help to mitigate bias (e.g., bias auditing tools). In this review paper, we describe in detail implicit and explicit biases in the care of cardiovascular disease that may be present in existing datasets but are not obvious to model developers. We review disparities in CVD outcomes across different genders and race groups, differences in treatment of historically marginalized groups, and disparities in clinical trials for various cardiovascular diseases and outcomes. Thereafter, we summarize some CVD AI literature that shows bias in CVD AI as well as approaches that AI is being used to mitigate CVD bias.

Automated vessel specific coronary artery calcification quantification with deep learning in a large multi-center registry

AIMS

Vessel specific coronary artery calcification (CAC) is additive to global CAC for prognostic assessment. We assessed accuracy and prognostic implications of vessel-specific automated deep learning (DL) CAC analysis on electrocardiogram gated and attenuation correction computed tomography (CT) in a large multicenter registry.

METHODS AND RESULTS

Vessel-specific CAC was assessed in the left main/left anterior descending (LM/LAD), left circumflex (LCX) and right coronary artery (RCA) using a DL model trained on 3000 gated CT and tested on 2094 gated CT and 5969 non-gated attenuation correction CT. Vessel-specific agreement was assessed with linear weighted Cohen's Kappa for CAC zero, 1-100, 101-400 and >400 Agatston units (AU). Risk of major adverse cardiovascular events (MACE) was assessed during 2.4±1.4 years follow-up, with hazard ratios (HR) and 95% confidence intervals (CI). There was strong to excellent agreement between DL and expert ground truth for CAC in LM/LAD, LCX and RCA on gated CT [0.90 (95% CI 0.89 to 0.92); 0.70 (0.68 to 0.73); 0.79 (0.77 to 0.81)] and attenuation correction CT [(0.78 (0.77 to 0.80); 0.60 (0.58 to 0.62); 0.70 (0.68 to 0.71)]. MACE occurred in 242 (12%) undergoing gated CT and 841(14%) of undergoing attenuation correction CT. LM/LAD CAC >400 AU was associated with the highest risk of MACE on gated (HR 12.0, 95% CI 7.96, 18.0, p<0.001) and attenuation correction CT (HR 4.21, 95% CI 3.48, 5.08, p<0.001).

CONCLUSION

Vessel-specific CAC assessment with DL can be performed accurately and rapidly on gated CT and attenuation correction CT and provides important prognostic information.

Artificial Intelligence in Coronary Artery Calcium Scoring Detection and Quantification

Coronary artery calcium (CAC) is a marker of coronary atherosclerosis, and the presence and severity of CAC have been shown to be powerful predictors of future cardiovascular events. Due to its value in risk discrimination and reclassification beyond traditional risk factors, CAC has been supported by recent guidelines, particularly for the purposes of informing shared decision-making regarding the use of preventive therapies. In addition to dedicated ECG-gated CAC scans, the presence and severity of CAC can also be accurately estimated on non-contrast chest computed tomography scans performed for other clinical indications. However, the presence of such "incidental" CAC is rarely reported. Advances in artificial intelligence have now enabled automatic CAC scoring for both cardiac and non-cardiac CT scans. Various AI approaches, from rule-based models to machine learning algorithms and deep learning, have been applied to automate CAC scoring. Convolutional neural networks, a deep learning technique, have had the most successful approach, with high agreement with manual scoring demonstrated in multiple studies. Such automated CAC measurements may enable wider and more accurate detection of CAC from non-gated CT studies, thus improving the efficiency of healthcare systems to identify and treat previously undiagnosed coronary artery disease.

Fusion Modeling: Combining Clinical and Imaging Data to Advance Cardiac Care

In addition to the traditional clinical risk factors, an increasing amount of imaging biomarkers have shown value for cardiovascular risk prediction. Clinical and imaging data are captured from a variety of data sources during multiple patient encounters and are often analyzed independently. Initial studies showed that fusion of both clinical and imaging features results in superior prognostic performance compared with traditional scores. There are different approaches to fusion modeling, combining multiple data resources to optimize predictions, each with its own advantages and disadvantages. However, manual extraction of clinical and imaging data is time and labor intensive and often not feasible in clinical practice. An automated approach for clinical and imaging data extraction is highly desirable. Convolutional neural networks and natural language processing can be utilized for the extraction of electronic medical record data, imaging studies, and free-text data. This review outlines the current status of cardiovascular risk prediction and fusion modeling; and in addition gives an overview of different artificial intelligence approaches to automatically extract data from images and electronic medical records for this purpose.

Imaging Early Life Cardiovascular Phenotype

The growing epidemics of obesity, hypertension, and diabetes, in addition to worsening environmental factors such as air pollution, water scarcity, and climate change, have fueled the continuously increasing prevalence of cardiovascular diseases (CVDs). This has caused a markedly increasing burden of CVDs that includes mortality and morbidity worldwide. Identification of subclinical CVD before overt symptoms can lead to earlier deployment of preventative pharmacological and nonpharmacologic strategies. In this regard, noninvasive imaging techniques play a significant role in identifying early CVD phenotypes. An armamentarium of imaging techniques including vascular ultrasound, echocardiography, magnetic resonance imaging, computed tomography, noninvasive computed tomography angiography, positron emission tomography, and nuclear imaging, with intrinsic strengths and limitations can be utilized to delineate incipient CVD for both clinical and research purposes. In this article, we review the various imaging modalities used for the evaluation, characterization, and quantification of early subclinical cardiovascular diseases.

Artificial Intelligence for Cardiothoracic Imaging: Overview of Current and Emerging Applications

Artificial intelligence algorithms can learn by assimilating information from large datasets in order to decipher complex associations, identify previously undiscovered pathophysiological states, and construct prediction models. There has been tremendous interest and increased incorporation of artificial intelligence into various industries, including healthcare. As a result, there has been an exponential rise in the number of research articles and industry participants producing models intended for a variety of applications in medical imaging, which can be challenging to navigate for radiologists. In thoracic imaging, multiple applications are being evaluated for chest radiography and computed tomography and include applications for lung nodule evaluation and cancer imaging, quantifying diffuse lung disorders, and cardiac imaging, to name a few. This review aims to provide an overview of current clinical AI models, focusing on the most common clinical applications of AI in cardiothoracic imaging.

Diagnostic performance of deep learning-based vessel extraction and stenosis detection on coronary computed tomography angiography for coronary artery disease: a multi-reader multi-case study

BACKGROUND

Post-processing and interpretation of coronary CT angiography (CCTA) imaging are time-consuming and dependent on the reader's experience. An automated deep learning (DL)-based imaging reconstruction and diagnosis system was developed to improve diagnostic accuracy and efficiency.

METHODS

Our study including 374 cases from five sites, inviting 12 radiologists, assessed the DL-based system in diagnosing obstructive coronary disease with regard to diagnostic performance, imaging post-processing and reporting time of radiologists, with invasive coronary angiography as a standard reference. The diagnostic performance of DL system and DL-assisted human readers was compared with the traditional method of human readers without DL system.

RESULTS

Comparing the diagnostic performance of human readers without DL system versus with DL system, the AUC was improved from 0.81 to 0.82 (p < 0.05) at patient level and from 0.79 to 0.81 (p < 0.05) at vessel level. An increase in AUC was observed in inexperienced radiologists (p < 0.05), but was absent in experienced radiologists. Regarding diagnostic efficiency, comparing the DL system versus human reader, the average post-processing and reporting time was decreased from 798.60 s to 189.12 s (p < 0.05). The sensitivity and specificity of using DL system alone were 93.55% and 59.57% at patient level and 83.23% and 79.97% at vessel level, respectively.

CONCLUSIONS

With the DL system serving as a concurrent reader, the overall post-processing and reading time was substantially reduced. The diagnostic accuracy of human readers, especially for inexperienced readers, was improved. DL-assisted human reader had the potential of being the reading mode of choice in clinical routine.

Performance of visual, manual, and automatic coronary calcium scoring of cardiac 13N-ammonia PET/low dose CT

BACKGROUND

Coronary artery calcium is a well-known predictor of major adverse cardiac events and is usually scored manually from dedicated, ECG-triggered calcium scoring CT (CSCT) scans. In clinical practice, a myocardial perfusion PET scan is accompanied by a non-ECG triggered low dose CT (LDCT) scan. In this study, we investigated the accuracy of patients' cardiovascular risk categorisation based on manual, visual, and automatic AI calcium scoring using the LDCT scan.

METHODS

We retrospectively enrolled 213 patients. Each patient received a 13N-ammonia PET scan, an LDCT scan, and a CSCT scan as the gold standard. All LDCT and CSCT scans were scored manually, visually, and automatically. For the manual scoring, we used vendor recommended software (Syngo.via, Siemens). For visual scoring a 6-points risk scale was used (0; 1-10; 11-100; 101-400; 401-100; > 1 000 Agatston score). The automatic scoring was performed with deep learning software (Syngo.via, Siemens). All manual and automatic Agatston scores were converted to the 6-point risk scale. Manual CSCT scoring was used as a reference.

RESULTS

The agreement of manual and automatic LDCT scoring with the reference was low [weighted kappa 0.59 (95% CI 0.53-0.65); 0.50 (95% CI 0.44-0.56), respectively], but the agreement of visual LDCT scoring was strong [0.82 (95% CI 0.77-0.86)].

CONCLUSIONS

Compared with the gold standard manual CSCT scoring, visual LDCT scoring outperformed manual LDCT and automatic LDCT scoring.

Fully automated deep learning powered calcium scoring in patients undergoing myocardial perfusion imaging

BACKGROUND

To assess the accuracy of fully automated deep learning (DL) based coronary artery calcium scoring (CACS) from non-contrast computed tomography (CT) as acquired for attenuation correction (AC) of cardiac single-photon-emission computed tomography myocardial perfusion imaging (SPECT-MPI).

METHODS AND RESULTS

Patients were enrolled in this study as part of a larger prospective study (NCT03637231). In this study, 56 Patients who underwent cardiac SPECT-MPI due to suspected coronary artery disease (CAD) were prospectively enrolled. All patients underwent non-contrast CT for AC of SPECT-MPI twice. CACS was manually assessed (serving as standard of reference) on both CT datasets (n = 112) and by a cloud-based DL tool. The agreement in CAC scores and CAC score risk categories was quantified. For the 112 scans included in the analysis, interscore agreement between the CAC scores of the standard of reference and the DL tool was 0.986. The agreement in risk categories was 0.977 with a reclassification rate of 3.6%. Heart rate, image noise, body mass index (BMI), and scan did not significantly impact (p=0.09 - p=0.76) absolute percentage difference in CAC scores.

CONCLUSION

A DL tool enables a fully automated and accurate estimation of CAC scores in patients undergoing non-contrast CT for AC of SPECT-MPI.

Opportunistic deep learning powered calcium scoring in oncologic patients with very high coronary artery calcium (≥ 1000) undergoing 18F-FDG PET/CT

Our aim was to identify and quantify high coronary artery calcium (CAC) with deep learning (DL)-powered CAC scoring (CACS) in oncological patients with known very high CAC (≥ 1000) undergoing 18F-FDG-PET/CT for re-/staging. 100 patients were enrolled: 50 patients with Agatston scores ≥ 1000 (high CACS group), 50 patients with Agatston scores < 1000 (negative control group). All patients underwent oncological 18F-FDG-PET/CT and cardiac SPECT myocardial perfusion imaging (MPI) by 99mTc-tetrofosmin within 6 months. CACS was manually performed on dedicated non-contrast ECG-gated CT scans obtained from SPECT-MPI (reference standard). Additionally, CACS was performed fully automatically with a user-independent DL-CACS tool on non-contrast, free-breathing, non-gated CT scans from 18F-FDG-PET/CT examinations. Image quality and noise of CT scans was assessed. Agatston scores obtained by manual CACS and DL tool were compared. The high CACS group had Agatston scores of 2200 ± 1620 (reference standard) and 1300 ± 1011 (DL tool, average underestimation of 38.6 ± 26%) with an intraclass correlation of 0.714 (95% CI 0.546, 0.827). Sufficient image quality significantly improved the DL tool's capability of correctly assigning Agatston scores ≥ 1000 (p = 0.01). In the control group, the DL tool correctly assigned Agatston scores < 1000 in all cases. In conclusion, DL-based CACS performed on non-contrast free-breathing, non-gated CT scans from 18F-FDG-PET/CT examinations of patients with known very high (≥ 1000) CAC underestimates CAC load, but correctly assigns an Agatston scores ≥ 1000 in over 70% of cases, provided sufficient CT image quality. Subgroup analyses of the control group showed that the DL tool does not generate false-positives.

Automated total and vessel-specific coronary artery calcium (CAC) quantification on chest CT: direct comparison with CAC scoring on non-contrast cardiac CT

BACKGROUND

This study aimed to evaluate the artificial intelligence (AI)-based coronary artery calcium (CAC) quantification and regional distribution of CAC on non-gated chest CT, using standard electrocardiograph (ECG)-gated CAC scoring as the reference.

METHODS

In this retrospective study, a total of 405 patients underwent non-gated chest CT and standard ECG-gated cardiac CT. An AI-based algorithm was used for automated CAC scoring on chest CT, and Agatston score on cardiac CT was manually quantified. Bland-Altman plots were used to evaluate the agreement of absolute Agatston score between the two scans at the patient and vessel levels. Linearly weighted kappa (κ) was calculated to assess the reliability of AI-based CAC risk categorization and the number of involved vessels on chest CT.

RESULTS

The AI-based algorithm showed moderate reliability for the number of involved vessels in comparison to measures on cardiac CT (κ = 0.75, 95% CI 0.70-0.79, P < 0.001) and an assignment agreement of 76%. Considerable coronary arteries with CAC were not identified with a per-vessel false-negative rate of 59.3%, 17.8%, 34.9%, and 34.7% for LM, LAD, CX, and RCA on chest CT. The leading causes for false negatives of LM were motion artifact (56.3%, 18/32) and segmentation error (43.8%, 14/32). The motion artifact was almost the only cause for false negatives of LAD (96.6%, 28/29), CX (96.7%, 29/30), and RCA (100%, 34/34). Absolute Agatston scores on chest CT were underestimated either for the patient and individual vessels except for LAD (median difference: - 12.5, - 11.3, - 5.6, - 18.6 for total, LM, CX, and RCA, all P < 0.01; - 2.5 for LAD, P = 0.18). AI-based total Agatston score yielded good reliability for risk categorization (weighted κ 0.86, P < 0.001) and an assignment agreement of 86.7% on chest CT, with a per-patient false-negative rate of 15.2% (28/184) and false-positive rate of 0.5% (1/221) respectively.

CONCLUSIONS

AI-based per-patient CAC quantification on non-gated chest CT achieved a good agreement with dedicated ECG-gated CAC scoring overall and highly reliable CVD risk categorization, despite a slight but significant underestimation. However, it is challenging to evaluate the regional distribution of CAC without ECG-synchronization.

Deep Learning of Coronary Calcium Scores From PET/CT Attenuation Maps Accurately Predicts Adverse Cardiovascular Events

BACKGROUND

Assessment of coronary artery calcium (CAC) by computed tomographic (CT) imaging provides an accurate measure of atherosclerotic burden. CAC is also visible in computed tomographic attenuation correction (CTAC) scans, always acquired with cardiac positron emission tomographic (PET) imaging.

OBJECTIVES

The aim of this study was to develop a deep-learning (DL) model capable of fully automated CAC definition from PET CTAC scans.

METHODS

The novel DL model, originally developed for video applications, was adapted to rapidly quantify CAC. The model was trained using 9,543 expert-annotated CT scans and was tested in 4,331 patients from an external cohort undergoing PET/CT imaging with major adverse cardiac events (MACEs) (follow-up 4.3 years), including same-day paired electrocardiographically gated CAC scans available in 2,737 patients. MACE risk stratification in 4 CAC score categories (0, 1-100, 101-400, and >400) was analyzed and CAC scores derived from electrocardiographically gated CT scans (standard scores) by expert observers were compared with automatic DL scores from CTAC scans.

RESULTS

Automatic DL scoring required <6 seconds per scan. DL CTAC scores provided stepwise increase in the risk for MACE across the CAC score categories (HR up to 3.2; P < 0.001). Net reclassification improvement of standard CAC scores over DL CTAC scores was nonsignificant (-0.02; 95% CI: -0.11 to 0.07). The negative predictive values for MACE of zero CAC with standard (85%) and DL CTAC (83%) CAC scores were similar (P = 0.19).

CONCLUSIONS

DL CTAC scores predict cardiovascular risk similarly to standard CAC scores quantified manually by experienced operators from dedicated electrocardiographically gated CAC scans and can be obtained almost instantly, with no changes to PET/CT scanning protocol.

Diagnostic Value of Fully Automated Artificial Intelligence Powered Coronary Artery Calcium Scoring from 18F-FDG PET/CT

Objectives: The objective of this study was to assess the feasibility and accuracy of a fully automated artificial intelligence (AI) powered coronary artery calcium scoring (CACS) method on ungated CT in oncologic patients undergoing 18F-FDG PET/CT. Methods: A total of 100 oncologic patients examined between 2007 and 2015 were retrospectively included. All patients underwent 18F-FDG PET/CT and cardiac SPECT myocardial perfusion imaging (MPI) by 99mTc-tetrofosmin within 6 months. CACS was manually performed on non-contrast ECG-gated CT scans obtained from SPECT-MPI (i.e., reference standard). Additionally, CACS was performed using a cloud-based, user-independent tool (AI-CACS) on ungated CT scans from 18F-FDG-PET/CT examinations. Agatston scores from the manual CACS and AI-CACS were compared. Results: On a per-patient basis, the AI-CACS tool achieved a sensitivity and specificity of 85% and 90% for the detection of CAC. Interscore agreement of CACS between manual CACS and AI-CACS was 0.88 (95% CI: 0.827, 0.918). Interclass agreement of risk categories was 0.8 in weighted Kappa analysis, with a reclassification rate of 44% and an underestimation of one risk category by AI-CACS in 39% of cases. On a per-vessel basis, interscore agreement of CAC scores ranged from 0.716 for the circumflex artery to 0.863 for the left anterior descending artery. Conclusions: Fully automated AI-CACS as performed on non-contrast free-breathing, ungated CT scans from 18F-FDG-PET/CT examinations is feasible and provides an acceptable to good estimation of CAC burden. CAC load on ungated CT is, however, generally underestimated by AI-CACS, which should be taken into account when interpreting imaging findings.

Artificial Intelligence Advancements in the Cardiovascular Imaging of Coronary Atherosclerosis

Coronary artery disease is a leading cause of death worldwide. There has been a myriad of advancements in the field of cardiovascular imaging to aid in diagnosis, treatment, and prevention of coronary artery disease. The application of artificial intelligence in medicine, particularly in cardiovascular medicine has erupted in the past decade. This article serves to highlight the highest yield articles within cardiovascular imaging with an emphasis on coronary CT angiography methods for % stenosis evaluation and atherosclerosis quantification for the general cardiologist. The paper finally discusses the evolving paradigm of implementation of artificial intelligence in real world practice.