IsletSwipe, a mobile platform for expert opinion exchange on islet graft images

We previously developed a deep learning-based web service (IsletNet) for an automated counting of isolated pancreatic islets. The neural network training is limited by the absent consensus on the ground truth annotations. Here, we present a platform (IsletSwipe) for an exchange of graphical opinions among experts to facilitate the consensus formation. The platform consists of a web interface and a mobile application. In a small pilot study, we demonstrate the functionalities and the use case scenarios of the platform. Nine experts from three centers validated the drawing tools, tested precision and consistency of the expert contour drawing, and evaluated user experience. Eight experts from two centers proceeded to evaluate additional images to demonstrate the following two use case scenarios. The Validation scenario involves an automated selection of images and islets for the expert scrutiny. It is scalable (more experts, images, and islets may readily be added) and can be applied to independent validation of islet contours from various sources. The Inquiry scenario serves the ground truth generating expert in seeking assistance from peers to achieve consensus on challenging cases during the preparation for IsletNet training. This scenario is limited to a small number of manually selected images and islets. The experts gained an opportunity to influence IsletNet training and to compare other experts' opinions with their own. The ground truth-generating expert obtained feedback for future IsletNet training. IsletSwipe is a suitable tool for the consensus finding. Experts from additional centers are welcome to participate.

Coculturing Human Islets with Proangiogenic Support Cells to Improve Islet Revascularization at the Subcutaneous Transplantation Site

While subcutaneous tissue has been proposed as a clinically relevant site for pancreatic islet transplantation, a major issue of concern remains, which is its poor vascular state. In an effort to overcome this limitation, we present an efficient and reproducible method to form human composite islets (CIs) with proangiogenic cell types in a controlled manner using nonadherent agarose microwell templates. In this study, we assessed the three-dimensional structure, function, and angiogenic potential of human CIs with human mesenchymal stromal cells (hMSCs), with or without human umbilical vein endothelial cells (HUVECs), and preconditioned hMSCs (PC-hMSCs) in EGM-2 under shear stress. Distinct cellular rearrangements could be observed in CIs, but islet functionality was maintained. In vitro angiogenesis assays found significantly enhanced sprout formation in case of CIs. In particular, the number of sprouts emanating from CIs with PC-hMSCs was significantly increased compared to other conditions. Subsequent in vivo assessment confirmed the proangiogenic potential of CIs. However, in contrast to our in vitro angiogenesis assays, CIs with hMSCs and HUVECs exhibited a higher in vivo angiogenic potential compared to control islets or islets combined with hMSCs or PC-hMSCs. These findings highlight the importance and necessity of verifying in vitro studies with in vivo models to reliably predict, in this case, revascularization outcomes. Regardless, we demonstrate here the therapeutic potential of CIs with proangiogenic support cells to enhance islet revascularization at a clinically relevant, although poorly vascularized, transplantation site.