Deep Supervision by Gaussian Pseudo-label-based Morphological Attention for Abdominal Aorta Segmentation in Non-Contrast CTs (2402.02514v1)
Abstract: The segmentation of the abdominal aorta in non-contrast CT images is a non-trivial task for computer-assisted endovascular navigation, particularly in scenarios where contrast agents are unsuitable. While state-of-the-art deep learning segmentation models have been proposed recently for this task, they are trained on manually annotated strong labels. However, the inherent ambiguity in the boundary of the aorta in non-contrast CT may undermine the reliability of strong labels, leading to potential overfitting risks. This paper introduces a Gaussian-based pseudo label, integrated into conventional deep learning models through deep supervision, to achieve Morphological Attention (MA) enhancement. As the Gaussian pseudo label retains the morphological features of the aorta without explicitly representing its boundary distribution, we suggest that it preserves aortic morphology during training while mitigating the negative impact of ambiguous boundaries, reducing the risk of overfitting. It is introduced in various 2D/3D deep learning models and validated on our local data set of 30 non-contrast CT volumes comprising 5749 CT slices. The results underscore the effectiveness of MA in preserving the morphological characteristics of the aorta and addressing overfitting concerns, thereby enhancing the performance of the models.
- “Derivation and validation of a practical risk score for prediction of mortality after open repair of ruptured abdominal aortic aneurysms in a us regional cohort and comparison to existing scoring systems,” Journal of vascular surgery, vol. 57, no. 2, pp. 354–361, 2013.
- “Safety and accuracy of endovascular aneurysm repair without pre-operative and intra-operative contrast agent,” European Journal of Vascular and Endovascular Surgery, vol. 49, no. 3, pp. 255–261, 2015.
- “Renal consequences of endovascular abdominal aortic aneurysm repair,” Journal of Endovascular Therapy, vol. 15, no. 1, pp. 73–82, 2008.
- R Mehran and E Nikolsky, “Contrast-induced nephropathy: definition, epidemiology, and patients at risk,” Kidney international, vol. 69, pp. S11–S15, 2006.
- “U-net: Convolutional networks for biomedical image segmentation,” in Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer, 2015, pp. 234–241.
- “Attention u-net: Learning where to look for the pancreas,” arXiv preprint arXiv:1804.03999, 2018.
- “V-net: Fully convolutional neural networks for volumetric medical image segmentation,” in 2016 fourth international conference on 3D vision (3DV). Ieee, 2016, pp. 565–571.
- “Transunet: Transformers make strong encoders for medical image segmentation,” arXiv preprint arXiv:2102.04306, 2021.
- “Transbts: Multimodal brain tumor segmentation using transformer,” in Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part I 24. Springer, 2021, pp. 109–119.
- “Deepaaa: clinically applicable and generalizable detection of abdominal aortic aneurysm using deep learning,” in Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part II 22. Springer, 2019, pp. 723–731.
- “A deep learning approach to automate high-resolution blood vessel reconstruction on computerized tomography images with or without the use of contrast agent,” arXiv preprint arXiv:2002.03463, 2020.
- “Deep-learning approach to automate the segmentation of aorta in non-contrast cts,” Journal of Medical Imaging, vol. 10, no. 2, pp. 024001–024001, 2023.
- “Deeply-supervised nets,” in Artificial intelligence and statistics. Pmlr, 2015, pp. 562–570.
- “Numerically stable direct least squares fitting of ellipses,” in Proc. 6th International Conference in Central Europe on Computer Graphics and Visualization. WSCG. Citeseer, 1998, vol. 98, pp. 125–132.
- “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.