Angiogenesis is a highly regulated process. It promotes tissue regeneration and contributes to tumor growth. Existing therapeutic concepts interfere with different steps of angiogenesis. The quantification of the vasculature is of crucial importance for research on angiogenetic effects. The chorioallantoic membrane (CAM) assay is widely used in the study of angiogenesis. Ex ovo cultured chick embryos develop an easily accessible, highly vascularised membrane on the surface. Tumor xenografts can be incubated on this membrane enabling studies on cancer angiogenesis and other major hallmarks. However, there is no commonly accepted gold standard for the quantification of the vasculature of the CAM. We compared four widely used measurement techniques to identify the most appropriate one for the quantification of the vascular network of the CAM. The comparison of the different quantification methods suggested that the CAM assay application on the IKOSA platform is the most suitable image analysis application for the vasculature of the CAM. The new CAM application on the IKOSA platform turned out to be a reliable and feasible tool for practical use in angiogenesis research. This novel image analysis software enables a deeper exploration of various aspects of angiogenesis and might support future research on new anti-angiogenic strategies for cancer treatment.

This paper presents a novel evaluation approach for optical coherence tomography (OCT) image analysis of pharmaceutical solid dosage forms based on deep convolutional neural networks (CNNs). As a proof of concept, CNNs were applied to image data from both, in- and at-line OCT implementations, monitoring film-coated tablets as well as single- and multi-layered pellets. CNN results were compared against results from established algorithms based on ellipse-fitting, as well as to human-annotated ground truth data. Performance benchmarks used include, efficiency (computation speed), sensitivity (number of detections from a defined test set) and accuracy (deviation from the reference method). The results were validated by comparing the output of several algorithms to data manually annotated by human experts and microscopy images of cross-sectional cuts of the same dosage forms as a reference method. In order to guarantee comparability for all results, the algorithms were executed on the same hardware. Since modern OCT systems must operate under real-time conditions in order to be implemented in-line into manufacturing lines, the necessary steps are discussed on how to achieve this goal without sacrificing the algorithmic performance and how to tailor a deep CNN to cope with the high amount of image noise and alterations in object appearance. The developed deep learning approach outperforms static algorithms currently available in pharma applications with respect to performance benchmarks, and represents the next level in real time evaluation of challenging industrial OCT image data.