Robotic search for optimal cell culture in regenerative medicine.

Induced differentiation is one of the most experience- and skill-dependent experimental processes in regenerative medicine, and establishing optimal conditions often takes years. We developed a robotic AI system with a batch Bayesian optimization algorithm that autonomously induces the differentiation of induced pluripotent stem cell-derived retinal pigment epithelial (iPSC-RPE) cells. From 200 million possible parameter combinations, the system performed cell culture in 143 different conditions in 111 days, resulting in 88% better iPSC-RPE production than that obtained by the pre-optimized culture in terms of the pigmentation scores. Our work demonstrates that the use of autonomous robotic AI systems drastically accelerates systematic and unbiased exploration of experimental search space, suggesting immense use in medicine and research.

Automated evaluation of retinal pigment epithelium disease area in eyes with age-related macular degeneration.

The retinal pigment epithelium (RPE) is essential for the survival and function of retinal photoreceptor cells. RPE dysfunction causes various retinal diseases including age-related macular degeneration (AMD). Clinical studies on ES/iPS cell-derived RPE transplantation for RPE dysfunction-triggered diseases are currently underway. Quantification of the diseased RPE area is important to evaluate disease progression or the therapeutic effect of RPE transplantation. However, there are no standard protocols. To address this issue, we developed a 2-step software that enables objective and efficient quantification of RPE-disease area changes by analyzing the early-phase hyperfluorescent area in fluorescein angiography (FA) images. We extracted the Abnormal region. This extraction was based on deep learning-based discrimination. We scored the binarized extracted area using an automated program. Our program's performance for the same eye from the serial image captures was within 3.1 ± 7.8% error. In progressive AMD, the trend was consistent with human assessment, even when FA images from two different visits were compared. This method was applicable to quantifying RPE-disease area changes over time, evaluating iPSC-RPE transplantation images, and a disease other than AMD. Our program may contribute to the assessment of the clinical course of RPE-disease areas in routine clinics and reduce the workload of researchers.

Different cell imaging methods did not significantly improve immune cell image classification performance.

Developments in high-throughput microscopy have made it possible to collect huge amounts of cell image data that are difficult to analyse manually. Machine learning (e.g., deep learning) is often employed to automate the extraction of information from these data, such as cell counting, cell type classification and image segmentation. However, the effects of different imaging methods on the accuracy of image processing have not been examined systematically. We studied the effects of different imaging methods on the performance of machine learning-based cell type classifiers. We observed lymphoid-primed multipotential progenitor (LMPP) and pro-B cells using three imaging methods: differential interference contrast (DIC), phase contrast (Ph) and bright-field (BF). We examined the classification performance of convolutional neural networks (CNNs) with each of them and their combinations. CNNs achieved an area under the receiver operating characteristic (ROC) curve (AUC) of ~0.9, which was significantly better than when the classifier used only cell size or cell contour shape as input. However, no significant differences were found between imaging methods and focal positions.