ABSTRACT
Accurate segmentation of Type B Aortic Dissection (TBAD) is crucial for clinical diagnosis and treatment planning. In this study, we trained nnU-Net on the ImageTBAD dataset for TBAD segmentation, achieving Dice scores of 0.94, 0.90, and 0.42 for true lumen (TL), false lumen (FL), and false lumen thrombus (FLT), respectively, surpassing the baseline methods by 0.08, 0.12, and 0.13. We identified challenges in segmenting small-volume FLT and proposed potential improvements using residual skip connections. The generalization capability of nnU-Net was validated on the external AVT dataset, where the Dice scores for TL and FL exceeded 0.9, and FLT achieved a Dice score above 0.86. nnU-Net demonstrated its efficacy in TBAD segmentation and holds promise for advancing segmentation techniques in this field.
- Krissian K, Carreira J M, Esclarin J, Semi-automatic segmentation and detection of aorta dissection wall in MDCT angiography[J]. Medical image analysis, 2014, 18(1): 83-102.Google Scholar
- Pepe A, Li J, Rolf-Pissarczyk M, Detection, segmentation, simulation and visualization of aortic dissections: A review[J]. Medical image analysis, 2020, 65: 101773.Google ScholarCross Ref
- Thubrikar M J, Agali P, Robicsek F. Wall stress as a possible mechanism for the development of transverse intimal tears in aortic dissections[J]. Journal of medical engineering & technology, 1999, 23(4): 127-134.Google Scholar
- Tsai T T, Evangelista A, Nienaber C A, Partial thrombosis of the false lumen in patients with acute type B aortic dissection[J]. New England Journal of Medicine, 2007, 357(4): 349-359.Google ScholarCross Ref
- Xiang D, Qi J, Wen Y, ADSeg: A flap-attention-based deep learning approach for aortic dissection segmentation[J]. Patterns, 2023, 4(5).Google Scholar
- LeMaire S A, Russell L. Epidemiology of thoracic aortic dissection[J]. Nature reviews cardiology, 2011, 8(2): 103-113.Google Scholar
- Kamman A V, van Herwaarden J A, Orrico M, Standardized protocol to analyze computed tomography imaging of type B aortic dissections[J]. Journal of Endovascular Therapy, 2016, 23(3): 472-482.Google ScholarCross Ref
- Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer International Publishing, 2015: 234-241.Google Scholar
- Feiger B, Lorenzana-Saldivar E, Cooke C, Evaluation of U-Net based architectures for automatic aortic dissection segmentation[J]. ACM Transactions on Computing for Healthcare (HEALTH), 2021, 3(1): 1-16.Google Scholar
- Çiçek Ö, Abdulkadir A, Lienkamp S S, 3D U-Net: learning dense volumetric segmentation from sparse annotation[C]//Medical Image Computing and Computer-Assisted Intervention–MICCAI 2016: 19th International Conference, Athens, Greece, October 17-21, 2016, Proceedings, Part II 19. Springer International Publishing, 2016: 424-432.Google Scholar
- Cao L, Shi R, Ge Y, Fully automatic segmentation of type B aortic dissection from CTA images enabled by deep learning[J]. European journal of radiology, 2019, 121: 108713.Google Scholar
- Wobben L D, Codari M, Mistelbauer G, Deep learning-based 3D segmentation of true lumen, false lumen, and false lumen thrombosis in type-B aortic dissection[C]//2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). IEEE, 2021: 3912-3915.Google Scholar
- Zhou Q, Qin J, Xiang X, MOLS-Net: Multi-organ and lesion segmentation network based on sequence feature pyramid and attention mechanism for aortic dissection diagnosis[J]. Knowledge-Based Systems, 2022, 239: 107853.Google ScholarDigital Library
- Zhang H, Wu C, Zhang Z, Resnest: Split-attention networks[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2022: 2736-2746.Google Scholar
- Isensee F, Jaeger P F, Kohl S A A, nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation[J]. Nature methods, 2021, 18(2): 203-211.Google Scholar
- Li F, Sun L, Lam K Y, Segmentation of human aorta using 3D nnU-net-oriented deep learning[J]. Review of Scientific Instruments, 2022, 93(11).Google ScholarCross Ref
- Yao Z, Xie W, Zhang J, ImageTBAD: A 3D computed tomography angiography image dataset for automatic segmentation of type-B aortic dissection[J]. Frontiers in Physiology, 2021, 12: 732711.Google ScholarCross Ref
- Radl L, Jin Y, Pepe A, AVT: Multicenter aortic vessel tree CTA dataset collection with ground truth segmentation masks[J]. Data in brief, 2022, 40: 107801.Google Scholar
- Heller N, Sathianathen N, Kalapara A, The kits19 challenge data: 300 kidney tumor cases with clinical context, ct semantic segmentations, and surgical outcomes[J]. arXiv preprint arXiv:1904.00445, 2019.Google Scholar
- Heller N, Isensee F, Maier-Hein K H, The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 challenge[J]. Medical image analysis, 2021, 67: 101821.Google Scholar
- Zhao B, Schwartz L, Kris G. Data From RIDER Lung CT (Version 2) [Data set]. The Cancer Imaging Archive. DOI: 10.7937/k9/tcia.2015.u1x8a5nrGoogle ScholarCross Ref
- Fedorov A, Beichel R, Kalpathy-Cramer J, 3D Slicer as an image computing platform for the Quantitative Imaging Network[J]. Magnetic resonance imaging, 2012, 30(9): 1323-1341.Google Scholar
- Isensee F, Petersen J, Klein A, nnu-net: Self-adapting framework for u-net-based medical image segmentation[J]. arXiv preprint arXiv:1809.10486, 2018.Google Scholar
Index Terms
- Evaluating nnU-Net for Type B Aortic Dissection segmentation on CTA images
Recommendations
MRI in CFD for chronic type B aortic dissection: Ready for prime time?
Abstract ObjectivesBetter tools are needed for risk assessment of Type B aortic dissection (TBAD) to determine optimal treatment for patients with uncomplicated disease. Magnetic resonance imaging (MRI) has the potential to inform computational fluid ...
Highlights- A systematic review of integrating magnetic resonance imaging (MRI) and computational fluid dynamics (CFD) in Type B aortic dissection (TBAD).
- MRI plays roles in providing flow data for CFD boundary conditions, validating simulation ...
Towards biomechanics-based pre-procedural planning for thoracic endovascular aortic repair of aortic dissection
Highlights- A finite element-based simulation method for stent-graft (SG) deployment in patient-specific type b aortic dissection was employed.
- Patient-specific type B aortic dissection geometry was reconstructed from the pre-procedural CTA scans ...
Abstract Background and objectiveAlthough thoracic aortic endovascular repair (TEVAR) has shown promising outcomes in the treatment of patients with complicated type B aortic dissection, complications still occur after TEVAR that can lead to catastrophic ...
Automated brain tumour segmentation techniques- A review
Automatic segmentation of brain tumour is the process of separating abnormal tissues from normal tissues, such as white matter WM, gray matter GM, and cerebrospinal fluid CSF. The process of segmentation is still challenging due to the diversity of ...
Comments