IntroductionLeft ventricular dysfunction is a frequent and potentially severe side effect of many tyrosine kinase inhibitors (TKI). The mode of toxicity is not identified, but may include impairment of mitochondrial or sarcomeric function, autophagy or angiogenesis, either as an on-target or off-target mechanism.Methods and ResultsWe studied concentration-response curves and time courses for nine TKIs in three-dimensional, force generating engineered heart tissue (EHT) from neonatal rat heart cells. We detected a concentration- and time-dependent decline in contractile force for gefitinib, lapatinib, sunitinib, imatinib, sorafenib, vandetanib and lestaurtinib and no decline in contractile force for erlotinib and dasatinib after 96 hours of incubation. The decline in contractile force was associated with an impairment of autophagy (LC3 Western blot) and appearance of autophagolysosomes (transmission electron microscopy).ConclusionThis study demonstrates the feasibility to study TKI-mediated force effects in EHTs and identifies an association between a decline in contractility and inhibition of autophagic flux.

Currently generative adversarial networks (GANs) are rarely applied to medical images of large sizes, especially 3D volumes, due to their large computational demand. We propose a novel multi-scale patchbased GAN approach to generate large high resolution 2D and 3D images.Our key idea is to first learn a low-resolution version of the image and then generate patches of successively growing resolutions conditioned on previous scales. In a domain translation use-case scenario, 3D thorax CTs of size 512 3 and thorax X-rays of size 2048 2 are generated and we show that, due to the constant GPU memory demand of our method, arbitrarily large images of high resolution can be generated. Moreover, compared to common patch-based approaches, our multi-resolution scheme enables better image quality and prevents patch artifacts.

Utilization of the E-liac IBD is safe and effective for the treatment of aorto-iliac aneurysms.