A token-mixer architecture for CAD-RADS classification of coronary stenosis on multiplanar reconstruction CT images

Fully automated artificial intelligence-based coronary CT angiography image processing: efficiency, diagnostic capability, and risk stratification

OBJECTIVES

To prospectively investigate whether fully automated artificial intelligence (FAAI)-based coronary CT angiography (CCTA) image processing is non-inferior to semi-automated mode in efficiency, diagnostic ability, and risk stratification of coronary artery disease (CAD).

MATERIALS AND METHODS

Adults with indications for CCTA were prospectively and consecutively enrolled at two hospitals and randomly assigned to either FAAI-based or semi-automated image processing using equipment workstations. Outcome measures were workflow efficiency, diagnostic accuracy for obstructive CAD (≥ 50% stenosis), and cardiovascular events at 2-year follow-up. The endpoints included major adverse cardiovascular events, hospitalization for unstable angina, and recurrence of cardiac symptoms. The non-inferiority margin was 3 percentage difference in diagnostic accuracy and C-index.

RESULTS

In total, 1801 subjects (62.7 ± 11.1 years) were included, of whom 893 and 908 were assigned to the FAAI-based and semi-automated modes, respectively. Image processing times were 121.0 ± 18.6 and 433.5 ± 68.4 s, respectively (p <0.001). Scan-to-report release times were 6.4 ± 2.7 and 10.5 ± 3.8 h, respectively (p < 0.001). Of all subjects, 152 and 159 in the FAAI-based and semi-automated modes, respectively, subsequently underwent invasive coronary angiography. The diagnostic accuracies for obstructive CAD were 94.7% (89.9-97.7%) and 94.3% (89.5-97.4%), respectively (difference 0.4%). Of all subjects, 779 and 784 in the FAAI-based and semi-automated modes were followed for 589 ± 182 days, respectively, and the C-statistic for cardiovascular events were 0.75 (0.67 to 0.83) and 0.74 (0.66 to 0.82) (difference 1%).

CONCLUSIONS

FAAI-based CCTA image processing significantly improves workflow efficiency than semi-automated mode, and is non-inferior in diagnosing obstructive CAD and risk stratification for cardiovascular events.

CLINICAL RELEVANCE STATEMENT

Conventional coronary CT angiography image processing is semi-automated. This observation shows that fully automated artificial intelligence-based image processing greatly improves efficiency, and maintains high diagnostic accuracy and the effectiveness in stratifying patients for cardiovascular events.

KEY POINTS

• Coronary CT angiography (CCTA) relies heavily on high-quality and fast image processing. • Full-automation CCTA image processing is clinically non-inferior to the semi-automated mode. • Full automation can facilitate the application of CCTA in early detection of coronary artery disease.

Combined-task deep network based on LassoNet feature selection for predicting the comorbidities of acute coronary syndrome

Acute coronary syndrome (ACS) is a multifaceted cardiovascular condition frequently accompanied by multiple comorbidities, which can have significant implications for patient outcomes and treatment approaches. Precisely predicting these comorbidities is crucial for providing personalized care and making well-informed clinical decisions. However, there is a shortage of research investigating the identification of risk factors associated with ACS comorbidities and accurately predicting their likelihood of occurrence beyond heart failure. In this study, an approach called Combined-task Deep Network based on LassoNet feature selection (CDNL) is presented for predicting ACS comorbidities, including hypertension, diabetes, hyperlipidemia, and heart failure. In order to identify crucial biomarkers associated with ACS comorbidities, the proposed framework first incorporates LassoNet, which extends Lasso regression to the deep network by adding a skip (residual) layer. Additionally, a correlation score calculation method across tasks is introduced based on measuring the overlap of identified biomarkers and their assigned importance. This method enables the development of an optimal combined-task prediction model for each ACS comorbidity, addressing the challenge of limited representations in traditional multi-task learning. Our evaluation, conducted through a meticulous cross-sectional study at a tertiary hospital in China, involved a dataset of 2941 samples with 42 clinical features. The results demonstrate that CDNL facilitates the identification of significant biomarkers and achieves an average improvement in AUC of 4.93% and 8.58% compared to deep learning multi-layer neural network (DNN) and SVM, respectively. Additionally, it shows an average improvement of 2.64% and 1.92% compared to two state-of-the-art multi-task models.

CAD-RADS scoring of coronary CT angiography with Multi-Axis Vision Transformer: A clinically-inspired deep learning pipeline

BACKGROUND AND OBJECTIVE

The standard non-invasive imaging technique used to assess the severity and extent of Coronary Artery Disease (CAD) is Coronary Computed Tomography Angiography (CCTA). However, manual grading of each patient's CCTA according to the CAD-Reporting and Data System (CAD-RADS) scoring is time-consuming and operator-dependent, especially in borderline cases. This work proposes a fully automated, and visually explainable, deep learning pipeline to be used as a decision support system for the CAD screening procedure. The pipeline performs two classification tasks: firstly, identifying patients who require further clinical investigations and secondly, classifying patients into subgroups based on the degree of stenosis, according to commonly used CAD-RADS thresholds.

METHODS

The pipeline pre-processes multiplanar projections of the coronary arteries, extracted from the original CCTAs, and classifies them using a fine-tuned Multi-Axis Vision Transformer architecture. With the aim of emulating the current clinical practice, the model is trained to assign a per-patient score by stacking the bi-dimensional longitudinal cross-sections of the three main coronary arteries along channel dimension. Furthermore, it generates visually interpretable maps to assess the reliability of the predictions.

RESULTS

When run on a database of 1873 three-channel images of 253 patients collected at the Monzino Cardiology Center in Milan, the pipeline obtained an AUC of 0.87 and 0.93 for the two classification tasks, respectively.

CONCLUSION

According to our knowledge, this is the first model trained to assign CAD-RADS scores learning solely from patient scores and not requiring finer imaging annotation steps that are not part of the clinical routine.