3D segmentation of the true and false lumens on CT aortic dissection images

CT-based True- and False-Lumen Segmentation in Type B Aortic Dissection Using Machine Learning

“…A variety of methods have been used to detect the dissection flap, including multiscale template filters (30) and analysis of Hessian matrix eigenvectors (28,31). These efforts have generally been validated on few if any patients (25,30,32,33) and often explicitly assume that the dissection flap is a low-attenuation edge surrounded by a well-opacified lumen on either side. Therefore, it is questionable whether they would be robust to the wide variations of aortic structure in the setting of dissection related to poor lumen opacification or the presence of thrombi.…”

Multi-stage learning for segmentation of aortic dissections using a prior aortic anatomy simplification

“…For the separation of the dual lumen in preoperative CT images, one of the most difficult tasks was grasping the distinction of TL and FL locally at the aortic arch (Fetnaci et al, 2013;Kovács et al, 2006). We qualitatively compared the local segmentation results by visualizing the performances on identifying primary tears, which have been delineated as the interfaces between the dual lumen in Figure 9.…”

“…Some of the AD-related work achieved the identification of type B AD from original images (Dehghan et al, 2017) or (semi-) automatically extracting dissection walls (or flaps) (Krissian et al, 2013;Morariu et al, 2016), while they did not segment the vascular structure. For the segmenta-tion of type B AD, several strategies were proposed by using deformable model (Fetnaci et al, 2013), Hough transformation (Kovács et al, 2006), spatial continuity prior model (Duan et al, 2016), multi-scale wavelet analysis (Lee et al, 2008) and boundary cost minimization combined with image denoising (Fitria et al, 2019). These methods have made meaningful explorations and achieved good segmentation performances for AD based on a relatively small number of datasets.…”

Dissected aorta segmentation using convolutional neural networks

“…Cattin et al [17] combined Hough transformation and an arch model to segment dissected aorta arch. Lee et al [18] proposed a wavelet-based algorithm for true-false lumen segmentation and Fetnaci et al And deformable models are used in [19] to fulfill the same purpose.…”