Key result
DAResUNet deep learning model achieves ~92% left atrial segmentation accuracy, strongly matching manual volume annotations.
Why the study?
Quantitative assessment of left atrial volume is important for studying atrial fibrillation pathogenesis, but automated left atrial segmentation with quantitative assessment usually faces many challenges.
Do deep learning-based segmentation models accurately segment the left atrium and quantify left atrial volume in patients with atrial fibrillation compared to manual expert annotation?
Observational (n=182)
Yes
Do deep learning-based segmentation models accurately segment the left atrium and quantify left atrial volume in patients with atrial fibrillation compared to manual expert annotation?
p-value: p=<0.01
Deep learning models, particularly DAResUNet, can accurately segment the left atrium and quantify left atrial volume from cardiac CTA in patients with atrial fibrillation, performing comparably to manual expert annotation.
BACKGROUND AND PURPOSE: Quantitative assessment of left atrial volume (LAV) is an important factor in the study of the pathogenesis of atrial fibrillation. However, automated left atrial segmentation with quantitative assessment usually faces many challenges. The main objective of this study was to find the optimal left atrial segmentation model based on cardiac computed tomography angiography (CTA) and to perform quantitative LAV measurement. METHOD: A multi-center left atrial study cohort containing 182 cardiac CTAs with atrial fibrillation was created, each case accompanied by expert image annotation by a cardiologist. Then, based on this left atrium dataset, five recent states-of-the-art (SOTA) models in the field of medical image segmentation were used to train and validate the left atrium segmentation model, including DAResUNet, nnFormer, xLSTM-UNet, UNETR, and VNet, respectively. Further, the optimal segmentation model was used to assess the consistency validation of the LAV. RESULTS: DAResUNet achieved the best performance in DSC (0.924 ± 0.023) and JI (0.859 ± 0.065) among all models, while VNet is the best performer in HD (12.457 ± 6.831) and ASD (1.034 ± 0.178). The Bland-Altman plot demonstrated the extremely strong agreement (mean bias - 5.69 mL, 95% LoA - 19-7.6 mL) between the model's automatic prediction and manual measurements. CONCLUSION: Deep learning models based on a study cohort of 182 CTA left atrial images were capable of achieving competitive results in left atrium segmentation. LAV assessment based on deep learning models may be useful for biomarkers of the onset of atrial fibrillation.
No takes yet. Share an insight, caveat, or question.
Feng et al. (2025) conducted an observational in Atrial fibrillation (n=182). DAResUNet deep learning model vs. Manual expert annotation was evaluated on Dice similarity coefficient (DSC) (p=<0.01). The DAResUNet deep learning model achieved high left atrial segmentation accuracy (Dice similarity coefficient 0.924) and automated volume measurements strongly agreed with manual annotations.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: