Automated Measurement and Three-Dimensional Fitting of Corneal Ulcerations and Erosions via AI-Based Image Analysis.

PURPOSE: Artificial intelligence (AI)-tools hold great potential to compensate for missing resources in health-care systems but often fail to be implemented in clinical routine. Intriguingly, no-code and low-code technologies allow clinicians to develop Artificial intelligence (AI)-tools without requiring in-depth programming knowledge. Clinician-driven projects allow to adequately identify and address real clinical needs and, therefore, hold superior potential for clinical implementation. In this light, this study aimed for the clinician-driven development of a tool capable of measuring corneal lesions relative to total corneal surface area and eliminating inaccuracies in two-dimensional measurements by three-dimensional fitting of the corneal surface. METHODS: Standard slit-lamp photographs using a blue-light filter after fluorescein instillation taken during clinical routine were used to train a fully convolutional network to automatically detect the corneal white-to-white distance, the total fluorescent area and the total erosive area. Based on these values, the algorithm calculates the affected area relative to total corneal surface area and fits the area on a three-dimensional representation of the corneal surface. RESULTS: The developed algorithm reached dice scores >0.9 for an automated measurement of the relative lesion size. Furthermore, only 25% of conventional manual measurements were within a ± 10% range of the ground truth. CONCLUSIONS: The developed algorithm is capable of reliably providing exact values for corneal lesion sizes. Additionally, three-dimensional modeling of the corneal surface is essential for an accurate measurement of lesion sizes. Besides telemedicine applications, this approach harbors great potential for clinical trials where exact quantitative and observer-independent measurements are essential.

A Novel Artificial Intelligence-Based Approach for Quantitative Assessment of Angiogenesis in the Ex Ovo CAM Model.

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.

Deep convolutional neural networks: Outperforming established algorithms in the evaluation of industrial optical coherence tomography (OCT) images of pharmaceutical coatings.

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.

Shedding light on coatings: Real-time monitoring of coating quality at industrial scale.

Optical Coherence Tomography (OCT) is increasingly being used for studies of pharmaceutical film coating. OCT allows fast and non-destructive analysis of the coating thickness and quality via high-resolution cross-sectional images. Information about both the coating thickness and the coating quality can be extracted. Most studies and OCT applications performed to date have been limited to off-line measurements and off-line computations of coating features based on data acquired in-line. This study examines OCT's applicability to an industrial-scale pan coating process. Automated layer detection, classification and thickness calculation were executed in real time. To evaluate the system's performance, runs with various tablet size, coating solution concentration and operating parameters were carried out and monitored. Our results indicate that, in addition to correct end-point determination, OCT enables real-time monitoring of the coating processes (thickness, homogeneity and roughness) and can support active process control by supplying information about the coating thickness and quality.