Lensless imaging-based discrimination between tumour cells and blood cells towards circulating tumour cell cultivation.

Circulating tumour cells (CTCs) are recognized as important markers for cancer research. Nonetheless, the extreme rarity of CTCs in blood samples limits their availability for multiple characterization. The cultivation of CTCs is still technically challenging due to the lack of information of CTC proliferation, and it is difficult for conventional microscopy to monitor CTC cultivation owing to low throughput. In addition, for precise monitoring, CTCs need to be distinguished from the blood cells which co-exist with CTCs. Lensless imaging is an emerging technique to visualize micro-objects over a wide field of view, and has been applied for various cytometry analyses including blood tests. However, discrimination between tumour cells and blood cells was not well studied. In this study, we evaluated the potential of the lensless imaging system as a tool for monitoring CTC cultivation. Cell division of model tumour cells was examined using the lensless imaging system composed of a simple setup. Subsequently, we confirmed that tumour cells, JM cells (model lymphocytes), and erythrocytes exhibited cell line-specific patterns on the lensless images. After several discriminative parameters were extracted, discrimination between the tumour cells and other blood cells was demonstrated based on linear discriminant analysis. We also combined the highly efficient CTC recovery device, termed microcavity array, with the lensless-imaging to demonstrate recovery, monitoring and discrimination of the tumour cells spiked into whole blood samples. This study indicates that lensless imaging can be a powerful tool to investigate CTC proliferation and cultivation.

Colony Fingerprint-Based Discrimination of Staphylococcus species with Machine Learning Approaches.

Detection and discrimination of bacteria are crucial in a wide range of industries, including clinical testing, and food and beverage production. Staphylococcus species cause various diseases, and are frequently detected in clinical specimens and food products. In particular, S. aureus is well known to be the most pathogenic species. Conventional phenotypic and genotypic methods for discrimination of Staphylococcus spp. are time-consuming and labor-intensive. To address this issue, in the present study, we applied a novel discrimination methodology called colony fingerprinting. Colony fingerprinting discriminates bacterial species based on the multivariate analysis of the images of microcolonies (referred to as colony fingerprints) with a size of up to 250 µm in diameter. The colony fingerprints were obtained via a lens-less imaging system. Profiling of the colony fingerprints of five Staphylococcus spp. (S. aureus, S. epidermidis, S. haemolyticus, S. saprophyticus, and S. simulans) revealed that the central regions of the colony fingerprints showed species-specific patterns. We developed 14 discriminative parameters, some of which highlight the features of the central regions, and analyzed them by several machine learning approaches. As a result, artificial neural network (ANN), support vector machine (SVM), and random forest (RF) showed high performance for discrimination of theses bacteria. Bacterial discrimination by colony fingerprinting can be performed within 11 h, on average, and therefore can cut discrimination time in half compared to conventional methods. Moreover, we also successfully demonstrated discrimination of S. aureus in a mixed culture with Pseudomonas aeruginosa. These results suggest that colony fingerprinting is useful for discrimination of Staphylococcus spp.