Evaluation of U-Net Based Architectures for Automatic Aortic Dissection Segmentation

Segmentation and reconstruction of arteries is important for a variety of medical and engineering fields, such as surgical planning and physiological modeling. However, manual methods can be laborious and subject to a high degree of human variability. In this work, we developed various convolutional neural network ( CNN ) architectures to segment Stanford type B aortic dissections ( TBADs ), characterized by a tear in the descending aortic wall creating a normal channel of blood flow called a true lumen and a pathologic channel within the wall called a false lumen. We introduced several variations to the two-dimensional ( 2D ) and three-dimensional (3 D ) U-Net, where small stacks of slices were inputted into the networks instead of individual slices or whole geometries. We compared these variations with a variety of CNN segmentation architectures and found that stacking the input data slices in the upward direction with 2D U-Net improved segmentation accuracy, as measured by the Dice similarity coefficient ( DC ) and point-by-point average distance ( AVD ), by more than 15\% . Our optimal architecture produced DC scores of 0.94, 0.88, and 0.90 and AVD values of 0.074, 0.22, and 0.11 in the whole aorta, true lumen, and false lumen, respectively. Altogether, the predicted reconstructions closely matched manual reconstructions.

Reverse Cheese-Wire Septotomy to Create a Distal Landing Zone for Thoracic Endovascular Aortic Repair

Purpose: The objective of this study is to describe a novel method for creating a distal landing zone for thoracic endovascular aortic repair (TEVAR) in chronic aortic dissection. The technique is described in a patient with prior total arch and descending aortic replacement, with false lumen expansion. Technique: A cheese-wire endovascular septotomy was desired to create a single lumen above the celiac axis. To avoid dividing the septum caudally across the visceral segment, we performed a modified septotomy in a cephalad direction. Stiff wires were passed into the prior surgical graft, through true lumen on the right and false lumen on the left. An additional wire was passed across an existing fenestration at the level of the celiac axis, and snared and externalized. 7F Ansel sheaths were advanced and positioned tip-to-tip at the fenestration. Using the stiff wires as tracks, the through-wire was pushed cephalad to endovascularly cut the septum. Angiogram demonstrated successful septotomy, and TEVAR was performed to just above the celiac with successful aneurysm exclusion and no endoleak or retrograde false lumen perfusion. Follow-up computed tomography angiogram (CTA) showed continued exclusion without false lumen perfusion. Conclusions: This novel modification in a reverse direction provides an alternative method for endovascular septotomy, when traditional septotomy may threaten the visceral vessels.

Use of On-Site Digital Subtraction Angiography for Left Subclavian Artery Management During Hybrid Aortic Arch Repair in DeBakey I Dissection

Purpose: A hybrid aortic repair using the frozen elephant trunk (FET) technique with an open distal anastomosis in zone 2 and debranching of the left subclavian artery (LSA) has been demonstrated to be favorable and safe. Although a transposition of the LSA reduces the risk of cerebellar or medullar ischemia, this may be challenging in difficult LSA anatomies. Case Report: We present the case of a 61-year old patient with DeBakey I aortic dissection, treated with FET in moderate hypothermic circulatory arrest (26°C) and selective cerebral perfusion using a Thoraflex-Hybrid (Vascutek Terumo) prosthesis anchored in zone 2, with overstenting of the LSA orifice and no additional LSA debranching. Sufficient perfusion of the LSA was proved intraoperatively using LSA backflow analysis during selective cerebral perfusion in combination with on-site digital subtraction angiography (ARTIS Pheno syngo software). No neurologic dysfunction or ischemia occurred in the postoperative course. An angiographic computed tomography revealed physiologic LSA perfusion, with subsequent thrombotic occlusion of the false lumen in the proximal descending aorta after 7 days. Conclusion: Using an angiography-guided management in patients with complex DeBakey I dissection and difficult anatomy may simplify a proximalization of the distal anastomosis in zone 2 for FET, even without an additional LSA debranching.

Criteria for Endovascular Intervention in Type B Aortic Dissection

Background The use of thoracic endovascular aortic repair (TEVAR) for the management of uncomplicated type B aortic dissection (un-TBAD) remains controversial. There is a lack of consensus over whether pre-emptive TEVAR should be carried out in patients with un-TBAD at risk of progression to complicated TBAD. We present a review of current evidence and seek to suggest criteria where endovascular intervention in un-TBAD may prove beneficial relative to pharmacotherapy alone. Methods and Materials PubMed and Cochrane databases were searched using terms including: type B aortic dissection, risk factors, medical therapy, TEVAR, false lumen expansion, and mortality. Papers were selected based on title and abstract. Results Optimal medical therapy remains the mainstay treatment for patients with un-TBAD, however patients with un-TBAD present with varying degrees of disease progression risk. Factors such as age, aortic morphology, history of connective tissue disorders, false lumen thrombosis, and aortic branch involvement may potentiate progression from un-TBAD to complicated TBAD. Short- and long-term outcomes associated with TEVAR for TBAD remain promising. Conclusion Pre-emptive TEVAR may be beneficial in patients with un-TBAD presenting with the above factors, however further prospective research into the optimal timing for TEVAR in un-TBAD is required.

Fate of the Dissected Thoraco-Abdominal Aorta Distal to TEVAR (Thoracic Endovascular Aortic Repair) for Complicated Acute and Subacute Type B Aortic Dissection

Purpose: This study assessed morphological changes in the aortic true and false lumens during follow-up of patients undergoing TEVAR (Thoracic Endovascular Aortic Repair) for complicated acute and subacute type B dissection. The study analyzes the effectiveness of TEVAR in preventing distal aneurysmal progression. Materials and Methods: All patients between 2009 and 2019 undergoing TEVAR for complicated acute and subacute type B dissection at the study institution were retrospectively reviewed. Maximal diameters were measured on the proximal descending aorta right below the left subclavian artery, thoraco-abdominal junction right above the celiac trunk, and infrarenal aortic right above the inferior mesenteric artery, pre-operatively and during follow-up, analyzing either expansion or shrinkage of true and false lumens at these 3 sites. Results: Forty-one patients were included. Thirty-day incidence of death, stroke, paraplegia, and visceral ischemia was, respectively, 8% (n = 4), 6% (n = 3), 2% (n = 1), and 2% (n = 1). Three patients (6%) died from intervention-related cause. Mortality was 17% (n = 8) during a mean follow-up of 54 months. One patient had aneurysmal dilation of the descending aorta needing additional coverage and only 2 (4%) developed thoraco-abdominal aneurysms requiring re-intervention. In the remaining patients, both significant expansion of the true lumen and shrinkage of false lumen were observed at all 3 sites. Conclusion: Proximal coverage of the main entry tear appears to prevent aneurysmal progression in most patients (96%). With such promising results, TEVAR should be considered as a first-line treatment in acute and subacute type B dissection.

Safety and Effectiveness of TEVAR in Native Proximal Landing Zone 2 for Chronic Type B Aortic Dissection in Patients With Genetic Aortic Syndrome

Objectives The aim of this study is to report the safety and effectiveness of thoracic endovascular aortic repair (TEVAR) in a native proximal landing zone (PLZ) 2 for chronic type B aortic dissection (TBAD) patients with genetic aortic syndrome (GAS). Methods A retrospective review of a single center database to identify patients with GAS treated with TEVAR in native PLZ 2 for chronic TBAD and thoracic false lumen aneurysm between February 2012 and February 2018 was undertaken. Results In total, 31 patients with GAS (24 Marfan syndrome [MFS], 5 Loeys-Dietz syndrome [LDS], and 2 vascular Ehlers-Danlos syndrome [vEDS]) were treated by endovascular repair. Nineteen patients were treated by TEVAR as index procedures with 8 patients (5 females, mean age = 55, range = 36–79 years old) receiving TEVAR in native PLZ 2. Left subclavian artery (LSA) perfusion was preserved in all 8 patients: by left common carotid artery-LSA bypass in 6 patients, chimney stenting of the LSA in 1 patient, and partial coverage of LSA ostium in 1 patient. Technical success was achieved in all patients (100%). There was no 30 day mortality (0%). The 30 day morbidity (0%) was free from major complications. The median follow-up was 40 months (range = 7–79). One patient died due to non-aortic-related cause. Native PLZ 2 was free from complications in MFS patients (5/8). Two patients with LDS developed type Ia endoleak with aneurysmal progression. One patient was treated by proximal extension with a double inner branched arch stent-graft landing in the replaced ascending aorta. The other one was treated with frozen elephant trunk. Conclusion Thoracic endovascular aortic repair in native PLZ 2 was safe and effective with no early or midterm PLZ complications in patients with MFS with chronic TBAD in this limited series. Native PLZ 2 is not safe in patients with LDS and should only be used in emergencies as a bridging to open repair.

Cross-Entropy Learning for Aortic Pathology Classification of Artificial Multi-Sensor Impedance Cardiography Signals

An aortic dissection, a particular aortic pathology, occurs when blood pushes through a tear between the layers of the aorta and forms a so-called false lumen. Aortic dissection has a low incidence compared to other diseases, but a relatively high mortality that increases with disease progression. An early identification and treatment increases patients’ chances of survival. State-of-the-art medical imaging techniques have several disadvantages; therefore, we propose the detection of aortic dissections through their signatures in impedance cardiography signals. These signatures arise due to pathological blood flow characteristics and a blood conductivity that strongly depends on the flow field, i.e., the proposed method is, in principle, applicable to any aortic pathology that changes the blood flow characteristics. For the signal classification, we trained a convolutional neural network (CNN) with artificial impedance cardiography data based on a simulation model for a healthy virtual patient and a virtual patient with an aortic dissection. The network architecture was tailored to a multi-sensor, multi-channel time-series classification with a categorical cross-entropy loss function as the training objective. The trained network typically yielded a specificity of (93.9±0.1)% and a sensitivity of (97.5±0.1)%. A study of the accuracy as a function of the size of an aortic dissection yielded better results for a small false lumen with larger noise, which emphasizes the question of the feasibility of detecting aortic dissections in an early state.