Challenges of the newer generation of resorbable magnesium scaffolds: Lessons from failure mechanisms of the past generation.

Bioresorbable scaffolds (BRS) were developed to overcome the obstacles of metallic stents, mostly related to sustained presence of metallic foreign body in the coronary vessel. Following earlier success of single-arm BRS studies, randomized controlled trials of Absorb bioresorbable vascular scaffold (Abbott Vascular, Santa Clara, CA, USA) showed poor long-term clinical outcomes, particularly in terms of scaffold thrombosis. BRS made from magnesium alloy provide a promising alternative in terms of radial force, strut thickness and, potentially lower thrombogenicity. A recent clinical study demonstrated that magnesium-based BRS seems to be promising with regards to the risk of scaffold thrombosis. In this review, our aim is to describe the issues that prevented Absorb BVS from achieving favorable outcomes, provide current status of existing BRS technologies and the challenges that newer generation BRSs need to overcome, and the results of clinical studies for commercially available magnesium-based BRS, which remain the only BRS actively studied in clinical practice.

Intravascular molecular imaging: translating pathophysiology of atherosclerosis into human disease conditions.

Progression of atherosclerotic plaque in coronary arteries is characterized by complex cellular and non-cellular molecular interactions. Within recent years, atherosclerosis has been recognized as inflammation-driven disease condition, where progressive stages are characterized by morphological changes in plaque composition but also relevant molecular processes resulting in increased plaque vulnerability. While existing intravascular imaging modalities are able to resolve key morphological features during plaque progression, they lack capability to characterize the molecular profile of advanced atherosclerotic plaque. Because hybrid imaging modalities may provide incremental information related to plaque biology, they are expected to provide synergistic effects in detecting high risk patients and lesions. The aim of this article is to review existing literature on intravascular molecular imaging approaches, and to provide clinically oriented proposals of their application. In addition, we assembled an overview of future developments in this field geared towards detection of patients at risk for cardiovascular events.

Histopathology-Based Deep-Learning Predicts Atherosclerotic Lesions in Intravascular Imaging.

Background: Optical coherence tomography is a powerful modality to assess atherosclerotic lesions, but detecting lesions in high-resolution OCT is challenging and requires expert knowledge. Deep-learning algorithms can be used to automatically identify atherosclerotic lesions, facilitating identification of patients at risk. We trained a deep-learning algorithm (DeepAD) with co-registered, annotated histopathology to predict atherosclerotic lesions in optical coherence tomography (OCT). Methods: Two datasets were used for training DeepAD: (i) a histopathology data set from 7 autopsy cases with 62 OCT frames and co-registered histopathology for high quality manual annotation and (ii) a clinical data set from 51 patients with 222 OCT frames in which manual annotations were based on clinical expertise only. A U-net based deep convolutional neural network (CNN) ensemble was employed as an atherosclerotic lesion prediction algorithm. Results were analyzed using intersection over union (IOU) for segmentation. Results: DeepAD showed good performance regarding the prediction of atherosclerotic lesions, with a median IOU of 0.68 ± 0.18 for segmentation of atherosclerotic lesions. Detection of calcified lesions yielded an IOU = 0.34. When training the algorithm without histopathology-based annotations, a performance drop of >0.25 IOU was observed. The practical application of DeepAD was evaluated retrospectively in a clinical cohort (n = 11 cases), showing high sensitivity as well as specificity and similar performance when compared to manual expert analysis. Conclusion: Automated detection of atherosclerotic lesions in OCT is improved using a histopathology-based deep-learning algorithm, allowing accurate detection in the clinical setting. An automated decision-support tool based on DeepAD could help in risk prediction and guide interventional treatment decisions.