Search

The aim of our study is to validate a totally automated deep learning (DL)-based segmentation pipeline to screen abdominal aortic aneurysms (AAA) in computed tomography angiography (CTA) scans. We retrospectively evaluated 73 thoraco-abdominal CTAs (48 AAA and 25 control CTA) by means of a DL-based segmentation pipeline built on a 2.5D convolutional neural network (CNN) architecture to segment lumen and thrombus of the aorta. The maximum aortic diameter of the abdominal tract was compared using a threshold value (30 mm). Blinded manual measurements from a radiologist were done in order to create a true comparison. The screening pipeline was tested on 48 patients with aneurysm and 25 without aneurysm. The average diameter manually measured was 51.1 ± 14.4 mm for patients with aneurysms and 21.7 ± 3.6 mm for patients without aneurysms. The pipeline correctly classified 47 AAA out of 48 and 24 control patients out of 25 with 97% accuracy, 98% sensitivity, and 96% specificity. The automated pipeline of aneurysm measurements in the abdominal tract reported a median error with regard to the maximum abdominal diameter measurement of 1.3 mm. Our approach allowed for the maximum diameter of 51.2 ± 14.3 mm in patients with aneurysm and 22.0 ± 4.0 mm in patients without an aneurysm. The DL-based screening for AAA is a feasible and accurate method, calling for further validation using a larger pool of diagnostic images towards its clinical use. [ABSTRACT FROM AUTHOR]

Purpose: Although segmentation of Abdominal Aortic Aneurysms (AAA) thrombus is a crucial step for both the planning of endovascular treatment and the monitoring of the intervention's outcome, it is still performed manually implying time consuming operations as well as operator dependency. The present paper proposes a fully automatic pipeline to segment the intraluminal thrombus in AAA from contrast-enhanced Computed Tomography Angiography (CTA) images and to subsequently analyze AAA geometry. Methods: A deep-learning-based pipeline is developed to localize and segment the thrombus from the CTA scans. The thrombus is first identified in the whole sub-sampled CTA, then multi-view U-Nets are combined together to segment the thrombus from the identified region of interest. Polygonal models are generated for the thrombus and the lumen. The lumen centerline is automatically extracted from the lumen mesh and used to compute the aneurysm and lumen diameters. Results: The proposed multi-view integration approach returns an improvement in thrombus segmentation with respect to the single-view prediction. The thrombus segmentation model is trained over a training set of 63 CTA and a validation set of 8 CTA scans. By comparing the thrombus segmentation predicted by the model with the ground truth data, a Dice Similarity Coefficient (DSC) of 0.89 ± 0.04 is achieved. The AAA geometry analysis provided an Intraclass Correlation Coefficient (ICC) of 0.92 and a mean-absolute difference of 3.2 ± 2.4 mm, for the measurements of the total diameter of the aneurysm. Validation of both thrombus segmentation and aneurysm geometry analysis is performed over a test set of 14 CTA scans. Conclusion: The developed deep learning models can effectively segment the thrombus from patients affected by AAA. Moreover, the diameters automatically extracted from the AAA show high correlation with those manually measured by experts. [ABSTRACT FROM AUTHOR]

Purpose: Ruptured descending thoracic aorta (rDTA) is an harmful condition requiring emergent treatment. Thoracic endovascular aortic repair (TEVAR) is replacing the traditional open repair in the majority of descending thoracic aortic disease. An unanimous agreement regarding the optimal approach to treat rDTA has not been reached yet due to the lack of evidences supporting the improvement of long-term survival. The present meta-analysis of observational cohort studies aims to estimate the outcome of endovascular (TEVAR) versus surgical (OR) approach in the treatment of rDTA. Methods: Prisma Statement for performing and reporting meta-analysis has been used. MEDLINE, Scopus and the Cochrane Library databases were searched. A meta-analysis of observational cohort studies that examined the outcomes after OR and TEVAR for the management of rDTA was performed. Results: A total of 10,466 patients with rDTA were screened. Endovascular therapy was associated with a lower risk of in-hospital mortality compared with open repair (Risk Ratio[RR] 0.63; 95% CI0.57–0.70). The risk of stroke rate was not statistically different between endovascular versus open approach (RR0.86; 95% CI0.62–1.19). Endovascular treatment had benefits on paraplegia (RR0.70; 95% CI0.55–0.91) and other neurological complications (RR0.24; 95% CI0.10–0.56). TEVAR was associated with lower renal failure, cardiac complications and vascular injuries. Late mortality (Hazard Ratio[HR] 0.84; 95% CI0.63–1.13) and re-intervention rate (RR1.48; 95% CI0.80–2.74) were not significantly different between TEVAR and OR. Conclusions: TEVAR seems to offer advantages in terms of early mortality and complications rate. Moreover, data on late mortality and re-intervention are encouraging to consider endovascular treatment comparable to open repair for acute thoracic aorta emergency on long-term follow-up. [ABSTRACT FROM AUTHOR]

Purpose: To evaluate bridging stent geometry in patients who underwent branched endovascular aortic repair (B-EVAR) and to correlate the outcomes with intrinsic bridging stent characteristics aiming to identify the stent(s) that guarantees the best performance. Methods: Pre-operative and post-operative computed tomography images of all patients undergoing B-EVAR between September 2016 and April 2019 were retrospectively analyzed. Following geometrical features were measured: target vessel take-off angle (TOA); longitudinal stent shortening; shape index (SI), intended as ratio between minimum and maximum diameter of the lumen cross sections, averaged on three segments: zone 1 (proximal stented zone), zone 2 (intermediate), and zone 3 (distal). Results: Thirty-eight branches (8 right (RRA) and 8 left renal arteries (LRA), 11 superior mesenteric arteries (SMA), 11 celiac trunks (CTR)) were treated. Fluency (Bard Peripheral Vascular), COVERA (Bard Peripheral Vascular), and VBX (WLGore&Assoc) stent-grafts were implanted in 10, 12, and 16 branches, respectively. Pre-operative TOA was more acute in RRA and LRA when compared to CTR and SMA, and straightened in post-operative configuration (109.86 ± 28.65° to 150.27 ± 21.0°; P < 0.001). Comparable values of SI among the stent types were found in zone 1 (P = 0.08), whereas higher SI in VBX group was detected in zones 2 (P < 0.001) and 3 (P < 0.001). The VBX group was also the most affected by stent shortening (11.12 ± 5.65%; P = 0.001). Conclusion: Our early experience showed that the VBX stent offers greater stent circularity than the other devices even if a greater shortening has been observed drawing attention with regards to the decision of the nominal stent length. [ABSTRACT FROM AUTHOR]

Purpose: The quantitative analysis of contrast-enhanced Computed Tomography Angiography (CTA) is essential to assess aortic anatomy, identify pathologies, and perform preoperative planning in vascular surgery. To overcome the limitations given by manual and semi-automatic segmentation tools, we apply a deep learning-based pipeline to automatically segment the CTA scans of the aortic lumen, from the ascending aorta to the iliac arteries, accounting for 3D spatial coherence. Methods: A first convolutional neural network (CNN) is used to coarsely segment and locate the aorta in the whole sub-sampled CTA volume, then three single-view CNNs are used to effectively segment the aortic lumen from axial, sagittal, and coronal planes under higher resolution. Finally, the predictions of the three orthogonal networks are integrated to obtain a segmentation with spatial coherence. Results: The coarse segmentation performed to identify the aortic lumen achieved a Dice coefficient (DSC) of 0.92 ± 0.01. Single-view axial, sagittal, and coronal CNNs provided a DSC of 0.92 ± 0.02, 0.92 ± 0.04, and 0.91 ± 0.02, respectively. Multi-view integration provided a DSC of 0.93 ± 0.02 and an average surface distance of 0.80 ± 0.26 mm on a test set of 10 CTA scans. The generation of the ground truth dataset took about 150 h and the overall training process took 18 h. In prediction phase, the adopted pipeline takes around 25 ± 1 s to get the final segmentation. Conclusion: The achieved results show that the proposed pipeline can effectively localize and segment the aortic lumen in subjects with aneurysm. [ABSTRACT FROM AUTHOR]

Purpose: Acute mesenteric ischemia (AMI) is a life-threatening disease that leads to bowel infarction and death. The optimal management of AMI remains controversial. The present meta-analysis aimed to estimate the prognostic impact of surgical (SG) versus endovascular or hybrid intervention (EV) as the first-line treatment for acute arterial occlusive mesenteric ischemia and to assess whether endovascular strategy was actually effective in reducing bowel resection.Methods: MEDLINE, Scopus and the Cochrane Library databases were searched. There have been no randomized controlled trials comparing SG versus EV for the treatment of AMI. We undertook this systematic review and meta-analysis according to MOOSE (Meta-analysis of Observational Studies in Epidemiology) guidelines, assessing the included study quality with the Newcastle-Ottawa scale.Results: Seven studies comparing EV versus SG as first strategy for the treatment of AMI were selected for the analyses, reporting of 3020 patients. EV was associated with a reduced risk of in-hospital mortality (RR 0.68; 95% CI 0.59-0.79; fixed-effects analysis; p < 0.0001; I 2 = 4.9%; τ 2 = 0.025). Pooled prevalence of mortality was 19% for EV and 34% for SG. EV also showed a benefit impact on risk of bowel resection and second-look laparotomy.Conclusions: The present meta-analysis outlines that endovascular revascularization strategy seems to offer advantages in terms of in-hospital mortality and morbidity in case of arterial occlusive AMI. A multidisciplinary team consisting of radiologists, interventional radiologists, cardiovascular and general surgeons comes out to be essential to tailor the right procedure to the patient and improve the outcomes associated with AMI. [ABSTRACT FROM AUTHOR]

Chronic kidney disease (CKD), cardiac damage (CD) and the combination of the two are associated with increased morbidity and death in patients admitted to vascular surgery units. We assessed the prevalence of cardiac and renal damage and cardiorenal syndrome (CRS) in 563 patients with abdominal aortic aneurysms (AAA) who underwent cardiac screening before either an endovascular procedure (EVAR) or open surgery (OS) for aneurysm repair. CD was defined by ≥stage B as per the ACC/AHA classification of congestive heart failure (CHF), while CKD was defined by estimated GFR <60 mL/min/1.73 m(2) (CKD-EPI). Anemia [World Health Organization (WHO) guidelines] and iron deficiency (ID) (criteria for CHF patients) were also calculated. AAA patients were stratified into the following groups: CD, CKD, CRS or none of these conditions [no risk factors (NoRF)]. The prevalence of isolated cardiac and renal structural damage, of combined cardiorenal damage and of ID was 24.1, 15.0, 20.6 and 23.4 %, respectively. The frequency of anemia (mostly unrecognized) among the groups increased from NoRF (12.8 %)/CKD (19 %)/CD (25 %) up to CRS (38.8 %). This large-scale observational study provides clues for the increased CD/CKD risk profiles of unselected AAA patients, and underlines the need for better identification of ID/anemia and for appropriate treatment of CKD and CD before these patients undergo EVAR/OS. [ABSTRACT FROM AUTHOR]

Purpose: Conflicting results have been reported about the clinical value of fluorodeoxyglucose (FDG) imaging in predicting the risk of rupture of abdominal aortic aneurysm (AAA). The present study tests the hypothesis that FDG uptake is low in asymptomatic noninflammatory AAA due to the low cell density in aneurysmal walls. Methods: Positron emission tomography (PET)/CT imaging was performed in 12 consecutive candidates for AAA surgical repair and in 12 age- and sex-matched controls. At intervention, aneurysmal walls were cut into three sequential blocks. Block A was frozen to cut three 5-μm slices for incubation with 2-3 MBq of FDG for 5 min. Block C was first incubated with the same tracer solution for the same time and subsequently frozen to cut three 5-μm slices. Autoradiographic images were coregistered with immunohistochemical pictures of cell density, type and DNA synthesis as assessed on block B. Results: No visible uptake in abdominal aorta occurred in any patient or control subject. Immunohistochemistry documented a severe loss of wall structure, with low numbers of cells. Tracer retention directly correlated with overall cell density and with prevalence of cells synthesizing DNA. The metabolic nature of FDG uptake was confirmed by the selective effect of preliminary freezing that decreased tracer content by 90% in regions with high cell density and only by 34% in cold acellular areas. Conclusion: The loss of tissue structure and the marked decrease in cell density account for the low prevalence of positive findings at FDG PET imaging, at least in asymptomatic patients bearing AAAs whose diameter is close to surgical indication. [ABSTRACT FROM AUTHOR]