Deep-learning workflows of microscopic image analysis are sufficient for handling the contextual variations because they employ biological samples and have numerous tasks. The use of well-defined annotated images is important for the workflow. Cancer stem cells (CSCs) are identified by specific cell markers. These CSCs were extensively characterized by the stem cell (SC)-like gene expression and proliferation mechanisms for the development of tumors. In contrast, the morphological characterization remains elusive. This study aims to investigate the segmentation of CSCs in phase contrast imaging using conditional generative adversarial networks (CGAN). Artificial intelligence (AI) was trained using fluorescence images of the Nanog-Green fluorescence protein, the expression of which was maintained in CSCs, and the phase contrast images. The AI model segmented the CSC region in the phase contrast image of the CSC cultures and tumor model. By selecting images for training, several values for measuring segmentation quality increased. Moreover, nucleus fluorescence overlaid-phase contrast was effective for increasing the values. We show the possibility of mapping CSC morphology to the condition of undifferentiation using deep-learning CGAN workflows.

Cognitive remediation therapy (CRT) effectively reduces neurocognitive impairment in patients with schizophrenia, but few studies have used structural neuroimaging methods to assess its neuroanatomical effects. We investigated these effects, as well as the association between changes in cortical volume and neurocognitive performance. Between August 2013 and September 2016, we performed a randomized controlled study comprising a CRT group (16 individuals) and a treatment-as-usual (TAU) group (15 individuals) of patients with schizophrenia. CRT participants engaged in twice-weekly computer-assisted CRT sessions and weekly group meetings for 12 weeks. T1-weighted magnetic resonance imaging was performed before and after the intervention period, and whole-brain voxel-based morphometric analysis was used to detect significant cortical gray matter volume changes. We also assessed the correlation between cortical volume changes and CRT-derived neurocognitive improvements. The CRT group exhibited significantly greater improvements than the TAU group in verbal fluency (P = 0.012) and global cognitive scores (P = 0.049). The CRT group also exhibited significantly greater increases in right hippocampal volume than the TAU group (P < 0.001). Changes in verbal fluency scores and right hippocampal volumes were positively correlated (r = 0.53, P = 0.001). We found that CRT significantly increased right hippocampal volumes and that these enhancements were positively correlated with changes in verbal fluency scores. Our results indicate that CRT induces cognitive improvement through hippocampal plasticity. Registration number: UMIN000026146 , 2017/02/15, retrospectively registered.

Artificial intelligence (AI) technology for image recognition has the potential to identify cancer stem cells (CSCs) in cultures and tissues. CSCs play an important role in the development and relapse of tumors. Although the characteristics of CSCs have been extensively studied, their morphological features remain elusive. The attempt to obtain an AI model identifying CSCs in culture showed the importance of images from spatially and temporally grown cultures of CSCs for deep learning to improve accuracy, but was insufficient. This study aimed to identify a process that is significantly efficient in increasing the accuracy values of the AI model output for predicting CSCs from phase-contrast images. An AI model of conditional generative adversarial network (CGAN) image translation for CSC identification predicted CSCs with various accuracy levels, and convolutional neural network classification of CSC phase-contrast images showed variation in the images. The accuracy of the AI model of CGAN image translation was increased by the AI model built by deep learning of selected CSC images with high accuracy previously calculated by another AI model. The workflow of building an AI model based on CGAN image translation could be useful for the AI prediction of CSCs.

Deep learning is being increasingly applied for obtaining digital microscopy image data of cells. Well-defined annotated cell images have contributed to the development of the technology. Cell morphology is an inherent characteristic of each cell type. Moreover, the morphology of a cell changes during its lifetime because of cellular activity. Artificial intelligence (AI) capable of recognizing a mouse-induced pluripotent stem (miPS) cell cultured in a medium containing Lewis lung cancer (LLC) cell culture-conditioned medium (cm), miPS-LLCcm cell, which is a cancer stem cell (CSC) derived from miPS cell, would be suitable for basic and applied science. This study aims to clarify the limitation of AI models constructed using different datasets and the versatility improvement of AI models. The trained AI was used to segment CSC in phase-contrast images using conditional generative adversarial networks (CGAN). The dataset included blank cell images that were used for training the AI but they did not affect the quality of predicting CSC in phase contrast images compared with the dataset without the blank cell images. AI models trained using images of 1-day culture could predict CSC in images of 2-day culture; however, the quality of the CSC prediction was reduced. Convolutional neural network (CNN) classification indicated that miPS-LLCcm cell image classification was done based on cultivation day. By using a dataset that included images of each cell culture day, the prediction of CSC remains to be improved. This is useful because cells do not change the characteristics of stem cells owing to stem cell marker expression, even if the cell morphology changes during culture.

Face swapping technology is approaching maturity, and it is difficult to distinguish between real images and fake images. In order to prevent malicious face swapping and ensure the privacy and security of personal photos, we propose a new way to disable the face detector in the face detection stage, which is to add a black line structure to the face part. Using neural network visualization, we found that the black line structure can interrupt the continuity of facial features extracted by the face detector, thus making the three face detectors MTCNN, S3FD, and SSD fail simultaneously. By widening the width of the black line, MTCNN, S3FD, and SSD are able to reach probability of failure levels up to 95.7%. To reduce the amount of perturbation added and determine the effective range of perturbation addition, we firstly experimentally prove that adding perturbation to the background cannot interfere with the detector’s detection of faces.