Automatic Abdominal Aortic Aneurysm segmentation in MR images

Abstract

1 Highlights  We use a spatial fuzzy C-means algorithm to detect and segment the lumen  We use a graph cut algorithm to segment the aortic wall  The detection and segmentation process is fully automatic  We get a 79% overlapping between our segmentation and the one from the specialist ACCEPTED MANUSCRIPT A C C E P T E D M A N U S C R I P T Abdominal Aortic Aneurism is a disease related to a weakening in the aortic wall that can cause a break in the aorta and the death. The detection of an unusual dilatation of a section of the aorta is an indicative of this disease. However, it is difficult to diagnose because it is necessary image diagnosis using computed tomography or magneticresonance. An automatic diagnosis system would allow to analyze abdominal magnetic resonance images and to warn doctors if any anomaly is detected. We focus our research in magnetic resonance images because of the absence of ionizing radiation.Although there are proposals to identify this disease in magnetic resonance images, they need an intervention from clinicians to be precise and some of them are computationally hard. In this paper we develop a novel approach to analyze magnetic resonance abdominal images and detect the lumen and the aortic wall. The method combines different algorithms in two stages to improve the detection and the segmentation so it can be applied to similar problems with other type of images or structures. In a first stage, we use a spatial fuzzy C-means algorithm with morphological image analysis to detect and segment the lumen; and subsequently, in a second stage, we apply a graph cut algorithm to segment the aortic wall. The obtained results in the analyzed images are pretty successful obtaining an average of 79% of overlapping between the automatic segmentation provided by our method and the aortic wall identified by a medical specialist. The main impact of the proposed method is that it works in a completely automatic way with a low computational cost, which is of great significance for any expert and intelligent system.

Computer-aided quantification of non-contrast 3D black blood MRI as an efficient alternative to reference standard manual CT angiography measurements of abdominal aortic aneurysms

“…Segmentation of both the AAA lumen and outer wall from non-contrast black blood MRI is more challenging than from CTA, in part due to reduced contrast between the aneurysm and peri-aortic tissues, potential motion artifacts given the longer scan time required (compared to seconds for CTA), and incomplete suppression of flowing blood necessary to delineate the vessel lumen. To the best of our knowledge, the work from our group was the [36]. Segmentation of AAA from MRI is more challenging than from CTA, an evidenced by the results of that study, which achieved an overlap of only 79 % between the automated method and reference standard.…”

“…first to use the 3D black blood MRI technique in AAA disease[22], and the first to develop an algorithm for automatically segmenting both the AAA lumen and outer wall from such imaging[21]. A larger body of prior work has investigated automatic AAA segmentation from CTA[34][35][36][37][38]. Deep convolutional neural networks including fully convolutional networks and holistically nested edge detection network were used by Lopez-Linares et al to perform fully automatic segmentation[34,35].…”

Generation and Visual Exploration of Medical Flow Data: Survey, Research Trends and Future Challenges

“…There, the centreline is the only frequently extracted feature despite work on, e.g. aortic aneurysm segmentation [MMRFGM16] and coarctation detection [NGG*16].…”

Interactive image segmentation using label propagation through complex networks

“…Fully automatic segmentation is still very challenging and difficult to accomplish. Many automatic approaches are domain-dependant, usually applied in the medical field (Christ et al, 2016;Moeskops et al, 2016;Avendi et al, 2016;Bozkurt et al, 2018;Martinez-Muoz et al, 2016;Patino-Correa et al, 2014).…”