SummaryDeep learning technology is rapidly advancing and is now used to solve complex problems. Here, we used deep learning in convolutional neural networks to establish an automated method to identify endothelial cells derived from induced pluripotent stem cells (iPSCs), without the need for immunostaining or lineage tracing. Networks were trained to predict whether phase-contrast images contain endothelial cells based on morphology only. Predictions were validated by comparison to immunofluorescence staining for CD31, a marker of endothelial cells. Method parameters were then automatically and iteratively optimized to increase prediction accuracy. We found that prediction accuracy was correlated with network depth and pixel size of images to be analyzed. Finally, K-fold cross-validation confirmed that optimized convolutional neural networks can identify endothelial cells with high performance, based only on morphology.

Advances in deep learning technology have enabled complex task solutions. The accuracy of image classification tasks has improved owing to the establishment of convolutional neural networks (CNN). Cellular senescence is a hallmark of ageing and is important for the pathogenesis of ageing-related diseases. Furthermore, it is a potential therapeutic target. Specific molecular markers are used to identify senescent cells. Moreover senescent cells show unique morphology, which can be identified. We develop a successful morphology-based CNN system to identify senescent cells and a quantitative scoring system to evaluate the state of endothelial cells by senescence probability output from pre-trained CNN optimised for the classification of cellular senescence, Deep Learning-Based Senescence Scoring System by Morphology (Deep-SeSMo). Deep-SeSMo correctly evaluates the effects of well-known anti-senescent reagents. We screen for drugs that control cellular senescence using a kinase inhibitor library by Deep-SeSMo-based drug screening and identify four anti-senescent drugs. RNA sequence analysis reveals that these compounds commonly suppress senescent phenotypes through inhibition of the inflammatory response pathway. Thus, morphology-based CNN system can be a powerful tool for anti-senescent drug screening.

No abstract

BackgroundLimiting the contrast volume to creatinine clearance (V/CrCl) ratio is crucial for preventing contrast-induced acute kidney injury (CI-AKI) after percutaneous coronary intervention (PCI). However, the incidence of CI-AKI and the distribution of V/CrCl ratios may vary according to patient body habitus.ObjectiveWe aimed to identify the clinical factors predicting CI-AKI in patients with different body mass indexes (BMIs).MethodsWe evaluated 8782 consecutive patients undergoing PCI and who were registered in a large Japanese database. CI-AKI was defined as an absolute serum creatinine increase of 0.3 mg/dL or a relative increase of 50%. The effect of the V/CrCl ratio relative to CI-AKI incidence was evaluated within the low- (≤25 kg/m2) and high- (>25 kg/m2) BMI groups, with a V/CrCl ratio > 3 considered to be a risk factor for CI-AKI.ResultsA V/CrCl ratio > 3 was predictive of CI-AKI, regardless of BMI (low-BMI group: odds ratio [OR], 1.77 [1.42–2.21]; P < 0.001; high-BMI group: OR, 1.67 [1.22–2.29]; P = 0.001). The relationship between BMI and CI-AKI followed a reverse J-curve relationship, although baseline renal dysfunction (creatinine clearance <60 mL/min, 46.9% vs. 21.5%) and V/CrCl ratio > 3 (37.3% vs. 20.4%) were predominant in the low-BMI group. Indeed, low BMI was a significant predictor of a V/CrCl ratio > 3 (OR per unit decrease in BMI, 1.08 [1.05–1.10]; P < 0.001).ConclusionsA V/CrCl ratio > 3 was strongly associated with the occurrence of CI-AKI. Importantly, we also identified a tendency for physicians to use higher V/CrCl ratios in lean patients. Thus, recognizing this trend may provide a therapeutic target for reducing the incidence of CI-AKI.

No abstract