Dataset Information

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.

SUBMITTER: Zhang H

PROVIDER: S-EPMC3776471 | biostudies-literature | 2013 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Robust infrarenal aortic aneurysm lumen centerline detection for rupture status classification.

Zhang Hong H Kheyfets Vitaly O VO Finol Ender A EA

Medical engineering & physics 20130420 9

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 ...[more]

PMID: 23608300

Similar Datasets

Project description:BackgroundOpen repair of abdominal aortic aneurysms (AAAs) is occasionally performed in conjunction with additional procedures; however, how these concomitant procedures affect outcome is unclear. This study determined the frequency of additional procedures during elective open AAA repair and the effect on perioperative outcomes.MethodsAll elective infrarenal open AAA repairs between January 2003 and November 2014 in the Vascular Study Group of New England (VSGNE) were identified. Patients were grouped by concomitant procedures, which included no concomitant procedure, renal artery bypass, lower extremity bypass, other abdominal procedure, or thromboembolectomy. Analyses were performed using multivariable logistic regression.ResultsOf 1314 patients who underwent elective AAA repair, 153 (11.6%) had a concomitant procedure, including renal bypass in 27 (2.1%), lower extremity bypass in 28 (2.1%), other abdominal procedures in 64 (4.9%), and thromboembolectomy in 48 (3.7%). Independent risk factors for 30-day mortality were renal bypass (odds ratio [OR], 7.2; 95% confidence interval [CI], 1.9-27.7), other abdominal procedures (OR, 4.8; 95% CI, 1.6-14.1), and thromboembolectomy (OR, 8.8; 95% CI, 3.1-24.9). Deterioration of renal function was predicted by renal bypass (OR, 5.1; 95% CI, 2.1-12.4) and thromboembolectomy (OR, 3.7; 95% CI, 1.8-7.6). Lower extremity bypass and thromboembolectomy were predictive of postoperative leg ischemia (OR, 8.9; 95% CI, 2.7-29.0; OR, 11.2; 95% CI, 4.4-28.8, respectively), and thromboembolectomy was also predictive of postoperative bowel ischemia (OR, 4.4; 95% CI, 1.6-12.0).ConclusionsPerforming additional procedures during infrarenal open AAA repair is associated with increased morbidity and mortality in the postoperative period. Careful deliberation of the operative risks and the necessity of the additional interventions are therefore advised during operative planning. This study also highlights the importance of avoiding perioperative thromboembolic events.

Project description:BackgroundClinical and imaging surveillance practices following endovascular aneurysm repair (EVAR) for intact abdominal aortic aneurysm (AAA) vary considerably and compliance with recommended lifelong surveillance is poor. The aim of this study was to develop a dynamic prognostic model to enable stratification of patients at risk of future secondary aortic rupture or the need for intervention to prevent rupture (rupture-preventing reintervention) to enable the development of personalized surveillance intervals.MethodsBaseline data and repeat measurements of postoperative aneurysm sac diameter from the EVAR-1 and EVAR-2 trials were used to develop the model, with external validation in a cohort from a single-centre vascular database. Longitudinal mixed-effects models were fitted to trajectories of sac diameter, and model-predicted sac diameter and rate of growth were used in prognostic Cox proportional hazards models.ResultsSome 785 patients from the EVAR trials were included, of whom 155 (19·7 per cent) experienced at least one rupture or required a rupture-preventing reintervention during follow-up. An increased risk was associated with preoperative AAA size, rate of sac growth and the number of previously detected complications. A prognostic model using predicted sac growth alone had good discrimination at 2 years (C-index 0·68), 3 years (C-index 0·72) and 5 years (C-index 0·75) after operation and had excellent external validation (C-index 0·76-0·79). More than 5 years after operation, growth rates above 1 mm/year had a sensitivity of over 80 per cent and specificity over 50 per cent in identifying events occurring within 2 years.ConclusionSecondary sac growth is an important predictor of rupture or rupture-preventing reintervention to enable the development of personalized surveillance intervals. A dynamic prognostic model has the potential to tailor surveillance by identifying a large proportion of patients who may require less intensive follow-up.

Project description:BACKGROUND:Ultrasmall superparamagnetic particles of iron oxide (USPIO) detect cellular inflammation on magnetic resonance imaging (MRI). In patients with abdominal aortic aneurysm, we assessed whether USPIO-enhanced MRI can predict aneurysm growth rates and clinical outcomes. METHODS:In a prospective multicenter open-label cohort study, 342 patients with abdominal aortic aneurysm (diameter ?40 mm) were classified by the presence of USPIO enhancement and were monitored with serial ultrasound and clinical follow-up for ?2 years. The primary end point was the composite of aneurysm rupture or repair. RESULTS:Participants (85% male, 73.1±7.2 years) had a baseline aneurysm diameter of 49.6±7.7 mm, and USPIO enhancement was identified in 146 (42.7%) participants, absent in 191 (55.8%), and indeterminant in 5 (1.5%). During follow-up (1005±280 days), 17 (5.0%) abdominal aortic aneurysm ruptures, 126 (36.8%) abdominal aortic aneurysm repairs, and 48 (14.0%) deaths occurred. Compared with those without uptake, patients with USPIO enhancement have increased rates of aneurysm expansion (3.1±2.5 versus 2.5±2.4 mm/year, P=0.0424), although this was not independent of current smoking habit (P=0.1993). Patients with USPIO enhancement had higher rates of aneurysm rupture or repair (47.3% versus 35.6%; 95% confidence intervals, 1.1-22.2; P=0.0308). This finding was similar for each component of rupture (6.8% versus 3.7%, P=0.1857) or repair (41.8% versus 32.5%, P=0.0782). USPIO enhancement was associated with reduced event-free survival for aneurysm rupture or repair (P=0.0275), all-cause mortality (P=0.0635), and aneurysm-related mortality (P=0.0590). Baseline abdominal aortic aneurysm diameter (P<0.0001) and current smoking habit (P=0.0446) also predicted the primary outcome, and the addition of USPIO enhancement to the multivariate model did not improve event prediction (c-statistic, 0.7935-0.7936). CONCLUSIONS:USPIO-enhanced MRI is a novel approach to the identification of aortic wall cellular inflammation in patients with abdominal aortic aneurysms and predicts the rate of aneurysm growth and clinical outcome. However, it does not provide independent prediction of aneurysm expansion or clinical outcomes in a model incorporating known clinical risk factors. CLINICAL TRIAL REGISTRATION:URL: http://www.isrctn.com. Unique identifier: ISRCTN76413758.

Dataset Information

Robust infrarenal aortic aneurysm lumen centerline detection for rupture status classification.

Publications

Robust infrarenal aortic aneurysm lumen centerline detection for rupture status classification.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets