Key result
An automated deep convolutional neural network detected left ventricle ischemic scar on routine computed tomography angiography with 88.3% accuracy (AUC 0.901), outperforming manual reading.
Why the study?
LGE MRI is the gold standard for cardiac scar imaging but has common contraindications, while CTA is faster with fewer contraindications but cannot reliably image scar.
Does an automated deep convolutional neural network improve the detection of left ventricle ischemic scar in routine CTA compared to manual clinical reading?
Observational (n=225)
Yes
Does an automated deep convolutional neural network improve the detection of left ventricle ischemic scar in routine CTA compared to manual clinical reading?
Effect estimate: AUC 0.901 (95% CI 0.867-0.934)
A deep learning algorithm can accurately detect left ventricular ischemic scar from routine non-contrast cardiac CTA using only anatomical information, outperforming manual expert reading.
Supports AI scar detection on routine CTA; hypothesis-generating and requires prospective validation before clinical use.
Objectives: The aim of this study is to develop a scar detection method for routine computed tomography angiography (CTA) imaging using deep convolutional neural networks (CNN), which relies solely on anatomical information as input and is compatible with existing clinical workflows. Background: Identifying cardiac patients with scar tissue is important for assisting diagnosis and guiding interventions. Late gadolinium enhancement (LGE) magnetic resonance imaging (MRI) is the gold standard for scar imaging; however, there are common instances where it is contraindicated. CTA is an alternative imaging modality that has fewer contraindications and is faster than Cardiovascular magnetic resonance imaging but is unable to reliably image scar. Methods: A dataset of LGE MRI (200 patients, 83 with scar) was used to train and validate a CNN to detect ischemic scar slices using segmentation masks as input to the network. MRIs were segmented to produce 3D left ventricle meshes, which were sampled at points along the short axis to extract anatomical masks, with scar labels from LGE as ground truth. The trained CNN was tested with an independent CTA dataset (25 patients, with ground truth established with paired LGE MRI). Automated segmentation was performed to provide the same input format of anatomical masks for the network. The CNN was compared against manual reading of the CTA dataset by 3 experts. Results: Note that 84.7% cross-validated accuracy (AUC: 0.896) for detecting scar slices in the left ventricle on the MRI data was achieved. The trained network was tested against the CTA-derived data, with no further training, where it achieved an 88.3% accuracy (AUC: 0.901). The automated pipeline outperformed the manual reading by clinicians. Conclusion: Automatic ischemic scar detection can be performed from a routine cardiac CTA, without any scar-specific imaging or contrast agents. This requires only a single acquisition in the cardiac cycle. In a clinical setting, with near zero additional cost, scar presence could be detected to triage images, reduce reading times, and guide clinical decision-making.
No takes yet. Share an insight, caveat, or question.
O’Brien et al. (2021) conducted an observational in Left Ventricle Ischemic Scar (n=225). Deep convolutional neural network (CNN) vs. Manual reading by expert clinicians was evaluated on Accuracy of detecting ischemic scar slices in CTA (AUC 0.901, 95% CI 0.867-0.934). An automated deep convolutional neural network detected left ventricle ischemic scar on routine computed tomography angiography with 88.3% accuracy (AUC 0.901), outperforming manual reading.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: