Key result
Automated deep learning for CAC quantification achieves 90% sensitivity and highly correlates with expert scoring.
Why the study?
Automated deep learning-based calcium quantification on ECG gated cardiac CT scans requires validation against manual evaluation to assess accuracy and reliability.
Does fully automated deep learning-based calcium quantification accurately calculate Agatston scores compared to manual evaluation in patients undergoing ECG gated Cardiac CT?
Observational (n=110)
No
Does fully automated deep learning-based calcium quantification accurately calculate Agatston scores compared to manual evaluation in patients undergoing ECG gated Cardiac CT?
Effect estimate: Pearson correlation coefficient 0.84
p-value: p=<0.001
Fully automated deep learning-based calcium quantification on cardiac CTs provides accurate Agatston scores comparable to manual evaluation, potentially optimizing clinical workflow.
May streamline CAC scoring workflows; leaves open prospective outcome validation before routine adoption.
Purpose: To evaluate deep learning-based calcium segmentation and quantification on ECG gated Cardiac CT scans compared with manual evaluation. Methods:Automated calcium quantification was performed using a combination of deep-learning convolution neural networks based on Mask R CNN for multiorgan segmentation. Calcifications were identified automatically, after which the algorithm automatically excluded all non-coronary calcifications using 2D erosion, dilation, volume, and maximum intensity threshold and by applying cardiac, aortic, and epicardial fat segmentation. This study used 40 patients to train and test the segmentation model. Results:110 patients were tested for the validation of the algorithm. The Pearson correlation coefficient between the reference actual and the computed predictive scores on the test set show high level of correlation (0.84; p < 0.001) and high limits of agreement in Bland-Altman plot. The proposed method correctly classifies the risk group in 75.2% of the cases and classifies the subjects in the same group. 81% of the predictive scores lie in the same categories and only seven patients out of 110 were more than one category off. For the presence/absence of coronary artery calcifications, the deep learning model achieved a sensitivity of 90 % and a specificity of 94 %. Conclusion: Fully automated deep learning-based calcium quantification on cardiac-CTs shows good correlation compared to reference standards. Automating this process may reduce evaluation time and potentially optimize clinical calcium scoring without additional resources.
No takes yet. Share an insight, caveat, or question.
Gautam et al. (2022) conducted an observational in Coronary artery disease (n=110). Deep learning-based automated calcium quantification (KardioNet) vs. Manual evaluation by an expert cardiologist was evaluated on Pearson correlation coefficient between reference actual and computed predictive Agatston scores (Pearson correlation coefficient 0.84, p=<0.001). A fully automated deep learning-based algorithm for coronary artery calcium quantification demonstrated a high correlation (r=0.84) with manual expert scoring and achieved 90% sensitivity and 94% specificity for detecting calcifications.