Robust infrarenal aortic aneurysm lumen centerline detection for rupture status classification

Abstract

The objective of this work is to develop a robust method for human abdominal aortic aneurysm (AAA) centerline detection that can contribute to the accurate computation of features for the prediction of AAA rupture risk. A semiautomatic algorithm is proposed for detecting the lumen centerline in contrast-enhanced abdominal computed tomography images based on online adaboost classifiers, which does not require prior image segmentation. The algorithm was developed and applied to thirty ruptured and thirty unruptured AAA image data sets and the tortuosities of the detected centerline were measured to assess the correlation between AAA tortuosity and the binary ruptured and unruptured labels. The lumen of each data set was segmented manually by a trained radiologist and the resulting centerlines of each data set were defined as the gold standard to evaluate the accuracy of the algorithm and to compare it against two widely used segmentation techniques. The average mean relative accuracy of the offline adaboost classifier is 91.9% with a standard deviation of 1.6%; for the online adaboost classifier it is 93.6% with a standard deviation of 1.9% (p<0.05). The online adaboost classifier outperforms the offline adaboost classifier while their computational costs are similar. Aneurysm tortuosity computed from an accurately derived lumen centerline using online adaboost is statistically higher for ruptured aneurysms compared to unruptured aneurysms, indicating that tortuosity can be used to assess rupture risk in the vascular clinic.

Artificial intelligence framework to predict wall stress in abdominal aortic aneurysm

“…Continual advancements in artificial intelligence (AI) algorithms and software tools have provided methods to perform automated image segmentation using U-NETs, a type of convolutional neural network (CNN) optimized for biomedical image sets ( Martufi et al, 2009 , Zhang, Kheyfets, and Finol, 2013 , López-Linares et al, 2019 , Wang et al, 2018 ) and for improved machine learning (ML) based regression models for accurate prediction ( Chen, 2016 , Olson and Moore, 2019 ). A few groups have demonstrated that CNN can be used for reliable segmentation of AAA image sets to provide volume reconstructions on axial CT image stacks for the extraction of ILT, the aneurysm wall and the lumen ( López-Linares et al, 2019 , Wang et al, 2018 , Ronneberger, Fischer, and Brox, 2015 ).…”

Progression of Abdominal Aortic Aneurysm Towards Rupture: Refining Clinical Risk Assessment Using a Fully Coupled Fluid–Structure Interaction Method

“…Data mining which facilitates the identification of patterns within data sets was used to correlate geometrical parameters with the AAA repair status concluding that sac length, sac height, volume, surface area, maximum diameter, bulge height and ILT volume can offer useful information 7 . Image based detection of the lumen centerline was also considered for AAA classification prior to rupture risk estimations 8 . Surface curvature was also analyzed as a classifier-proven to yield more accuracy in the risk prediction than diameter 9 .…”

Structure Preserving Large Imagery Reconstruction

“…Moreover, with the recent advance in image processing techniques, such as feature descriptors [1], pixel-domain matrix factorization approaches [2][3][4] or probabilistic optimization [5], images can be read in an automatic manner rather than relying on the associated text. This leads to a revolutionary impact to a broad range of applications, from image clustering or recognition [6][7][8][9][10][11][12] to video synthesis or reconstruction [13][14][15] to cybersecurity via online images analysis [16][17][18][19] to other scientific applications [20][21][22][23][24].…”