Key result
U-Net 3+ outperforms U-Net and U-Net++ for coronary artery extraction with a ~0.89 Dice score.
Why the study?
Accurate extraction of coronary arteries from invasive coronary angiography is important for diagnosis and risk stratification in coronary artery disease.
Does the U-Net 3+ deep learning model improve the automatic extraction of coronary arteries from invasive coronary angiograms compared to U-Net ++ and U-net?
Does the U-Net 3+ deep learning model improve the automatic extraction of coronary arteries from invasive coronary angiograms compared to U-Net ++ and U-net?
Absolute Event Rate: 0.8942% vs 0.8814%
The U-Net 3+ deep learning model demonstrates superior performance in automatically extracting coronary arteries from invasive coronary angiograms compared to previous U-Net architectures.
Accurate extraction of coronary arteries from invasive coronary angiography (ICA) is important in clinical decision-making for the diagnosis and risk stratification of coronary artery disease (CAD). In this study, we develop a method using deep learning to automatically extract the coronary artery lumen. Methods. A deep learning model U-Net 3+, which incorporates the full-scale skip connections and deep supervisions, was proposed for automatic extraction of coronary arteries from ICAs. Transfer learning and a hybrid loss function were employed in this novel coronary artery extraction framework. Results. A data set containing 616 ICAs obtained from 210 patients was used. In the technical evaluation, the U-Net 3+ achieved a Dice score of 0.8942 and a sensitivity of 0.8735, which is higher than U-Net ++ (Dice score: 0.8814, the sensitivity of 0.8331) and U-net (Dice score: 0.8799, the sensitivity of 0.8305). Conclusion. Our study demonstrates that the U-Net 3+ is superior to other segmentation frameworks for the automatic extraction of the coronary arteries from ICAs. This result suggests great promise for clinical use.
No takes yet. Share an insight, caveat, or question.
Meng et al. (2022) studied Coronary artery disease (n=210). U-Net 3+ deep learning model vs. Other segmentation frameworks (e.g., U-Net, U-Net++) was evaluated on Dice similarity coefficient (DSC) for coronary artery extraction. The U-Net 3+ deep learning model achieved a Dice score of 0.8942 and sensitivity of 0.8735 for the automatic extraction of coronary arteries from invasive coronary angiograms, outperforming U-Net and U-Net++.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: