Isolated spontaneous renal artery dissection: endovascular management.

We report a rare case of isolated spontaneous renal artery dissection treated by stent placement. A 59-year-old man presented with a sudden onset of left flank pain and severe hypertension together with elevated creatinine levels. A computed tomography scan revealed a focal dissection at the left renal artery (LRA) with an infarcted left kidney. Despite medical treatment with 4 drugs, the patient's blood pressure remained uncontrolled. Angiography confirmed the diagnosis. A 6- × 60-mm Xpert stent (Abbott Vascular, Temecula, CA) was deployed at the LRA, achieving an enlarged true lumen with a patent stent. After the procedure, acute renal impairment was observed but pain subsided and blood pressure normalized under the treatment prescribed. At 12 months of follow-up, the patient was normotensive and asymptomatic with mild chronic renal failure and a patent LRA stent on doppler ultrasonography. The endovascular treatment of isolated spontaneous renal artery dissection appears to be feasible and effective and could be the first-line treatment when revascularization is needed.

Fully automatic detection and segmentation of abdominal aortic thrombus in post-operative CTA images using Deep Convolutional Neural Networks.

Computerized Tomography Angiography (CTA) based follow-up of Abdominal Aortic Aneurysms (AAA) treated with Endovascular Aneurysm Repair (EVAR) is essential to evaluate the progress of the patient and detect complications. In this context, accurate quantification of post-operative thrombus volume is required. However, a proper evaluation is hindered by the lack of automatic, robust and reproducible thrombus segmentation algorithms. We propose a new fully automatic approach based on Deep Convolutional Neural Networks (DCNN) for robust and reproducible thrombus region of interest detection and subsequent fine thrombus segmentation. The DetecNet detection network is adapted to perform region of interest extraction from a complete CTA and a new segmentation network architecture, based on Fully Convolutional Networks and a Holistically-Nested Edge Detection Network, is presented. These networks are trained, validated and tested in 13 post-operative CTA volumes of different patients using a 4-fold cross-validation approach to provide more robustness to the results. Our pipeline achieves a Dice score of more than 82% for post-operative thrombus segmentation and provides a mean relative volume difference between ground truth and automatic segmentation that lays within the experienced human observer variance without the need of human intervention in most common cases.

Standard and fenestrated endograft sizing in EVAR planning: Description and validation of a semi-automated 3D software.

An abdominal aortic aneurysm (AAA) is a pathological dilation of the abdominal aorta that may lead to a rupture with fatal consequences. Endovascular aneurysm repair (EVAR) is a minimally invasive surgical procedure consisting of the deployment and fixation of a stent-graft that isolates the damaged vessel wall from blood circulation. The technique requires adequate endovascular device sizing, which may be performed by vascular analysis and quantification on Computerized Tomography Angiography (CTA) scans. This paper presents a novel 3D CTA image-based software for AAA inspection and EVAR sizing, eVida Vascular, which allows fast and accurate 3D endograft sizing for standard and fenestrated endografts. We provide a description of the system and its innovations, including the underlying vascular image analysis and visualization technology, functional modules and user interaction. Furthermore, an experimental validation of the tool is described, assessing the degree of agreement with a commercial, clinically validated software, when comparing measurements obtained for standard endograft sizing in a group of 14 patients.