Key result
nnU-Net 3D outperforms 2D models in CT segmentation of Type B aortic dissection.
Why the study?
Assessing the aortic lumen, intimal flap, and false-lumen thrombosis on CT images is important for risk analysis and treatment planning in Type B aortic dissection, prompting the evaluation of U-Net-based deep neural networks for automatic segmentation of these structures.
Do 3D U-Net-based deep learning models improve the segmentation accuracy of the aortic lumen, intimal flap, and thrombus from CT scans in patients with Type B aortic dissection compared to 2D counterparts?
Do 3D U-Net-based deep learning models improve the segmentation accuracy of the aortic lumen, intimal flap, and thrombus from CT scans in patients with Type B aortic dissection compared to 2D counterparts?
3D U-Net-based deep learning models, particularly nnU-Net 3D, substantially outperform 2D models in automatically segmenting the aortic lumen, intimal flap, and false-lumen thrombus in Type B aortic dissection CT scans, establishing a baseline for automated morphological risk assessment.
Answers are grounded in this paper and cite their sources.
May support automated CT segmentation for Type B aortic dissection morphology; leaves open prospective clinical validation before risk-stratification use.
Type B aortic dissection (TBAD) is a life-threatening condition in which a tear in the intimal layer separates the aortic wall into a true and a false lumen. Assessment of the lumen, the intimal flap, and false-lumen thrombosis from CT images is important for risk analysis and treatment planning. This work applied U-Net-based deep neural networks to the automatic segmentation of these structures in TBAD. We collected 46 CT scans from 20 patients, with voxel-wise annotations of three structures: the aortic lumen, the intimal flap, and the thrombus. We explored four models: two convolutional networks, nnU-Net 2D and 3D, and two transformer-based architectures, TransUNet 2D and 3D. We observed that (1) for both nnU-Net and TransUNet, the 3D models outperformed their 2D counterparts on all three structures. The difference was small for the aortic lumen but large for the thin flap and the thrombus. The best model, nnU-Net 3D, reached a DSC of 93.05% for the lumen, 50.22% for the flap, and 69.94% for the thrombus. (2) The intimal flap was the most difficult structure for all models. Even the best 3D models showed large thrombus boundary errors in a few scans. These results provide a baseline for developing more advanced models for accurate segmentation of these structures in TBAD.
No takes yet. Share an insight, caveat, or question.
Gong et al. (2026) studied Type B aortic dissection (TBAD) (n=20). 3D U-Net-based deep learning segmentation models (nnU-Net 3D and TransUNet 3D) vs. 2D U-Net-based deep learning segmentation models (nnU-Net 2D and TransUNet 2D) was evaluated on Dice Similarity Coefficient (DSC) for multi-structure segmentation (aortic lumen, intimal flap, thrombus, and whole aorta). nnU-Net 3D outperformed 2D models in CT segmentation of Type B aortic dissection, achieving a mean DSC of 93.05% for the lumen, 50.22% for the intimal flap, and 69.94% for the thrombus.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: