N6-methyladenosine (m6A) is the most abundant epitranscriptome modification in mammalian mRNA. Recent years have seen substantial progress in m6A epitranscriptomics, indicating its crucial roles in the initiation and progression of cancer through regulation of RNA stabilities, mRNA splicing, microRNA processing and mRNA translation. However, by what means m6A is dynamically regulated or written by enzymatic components represented by methyltransferase-like 3 (METTL3) and how m6A is significant for each of the numerous genes remain unclear. We focused on METTL3 in pancreatic cancer, the prognosis of which is not satisfactory despite the development of multidisciplinary therapies. We established METTL3-knockdown pancreatic cancer cell line using short hairpin RNA. Although morphologic and proliferative changes were unaffected, METTL3-depleted cells showed higher sensitivity to anticancer reagents such as gemcitabine, 5-fluorouracil, cisplatin and irradiation. Our data suggest that METTL3 is a potent target for enhancing therapeutic efficacy in patients with pancreatic cancer. In addition, we performed cDNA expression analysis followed by gene ontology and protein-protein interaction analysis using the Database for Annotation, Visualization, and Integrated Discovery and Search Tool for the Retrieval of Interacting Genes/Proteins databases, respectively. The results demonstrate that METTL3 was associated with mitogen-activated protein kinase cascades, ubiquitin-dependent process and RNA splicing and regulation of cellular process, suggesting functional roles and targets of METTL3.

Artificial intelligence (AI) trained with a convolutional neural network (CNN) is a recent technological advancement. Previously, several attempts have been made to train AI using medical images for clinical applications. However, whether AI can distinguish microscopic images of mammalian cells has remained debatable. This study assesses the accuracy of image recognition techniques using the CNN to identify microscopic images. We also attempted to distinguish between mouse and human cells and their radioresistant clones. We used phase-contrast microscopic images of radioresistant clones from two cell lines, mouse squamous cell carcinoma NR-S1, and human cervical carcinoma ME-180. We obtained 10,000 images of each of the parental NR-S1 and ME-180 controls as well as radioresistant clones. We trained the CNN called VGG16 using these images and obtained an accuracy of 96%. Features extracted by the trained CNN were plotted using t-distributed stochastic neighbor embedding, and images of each cell line were well clustered. Overall, these findings suggest the utility of image recognition using AI for predicting minute differences among phase-contrast microscopic images of cancer cells and their radioresistant clones. Significance: This study demonstrates rapid and accurate identification of radioresistant tumor cells in culture using artifical intelligence; this should have applications in future preclinical cancer research. Cancer Res; 78(23); 6703-7. Ó2018 AACR.

The immobilization of patients with a bite block (BB) carries the risk of interpersonal infection, particularly in the context of pandemics such as COVID-19. Here, we compared the intra-fractional patient setup error (intra-SE) with and without a BB during fractionated intracranial stereotactic irradiation (STI). Fifteen patients with brain metastases were immobilized using a BB without a medical mask, while 15 patients were immobilized without using a BB and with a medical mask. The intra-SEs in six directions (anterior–posterior (AP), superior–inferior (SI), left–right (LR), pitch, roll, and yaw) were calculated by using cone-beam computed tomography images acquired before and after the treatments. We analyzed a total of 53 and 67 treatment sessions for the with- and without-BB groups, respectively. A comparable absolute mean translational and rotational intra-SE was observed (P > 0.05) in the AP (0.19 vs 0.23 mm with- and without-BB, respectively), SI (0.30 vs 0.29 mm), LR (0.20 vs 0.29 mm), pitch (0.18 vs 0.27°), roll (0.23 vs 0.23°) and yaw (0.27 vs 22°) directions. The resultant planning target volume (PTV) margin to compensate for intra-SE was <1 mm. No statistically significant correlation was observed between the intra-SE and treatment times. A PTV margin of <1 mm was achieved even when patients were immobilized without a BB during STI dose delivery.

It is known that single or isolated tumor cells enter cancer patients’ circulatory systems. These circulating tumor cells (CTCs) are thought to be an effective tool for diagnosing cancer malignancy. However, handling CTC samples and evaluating CTC sequence analysis results are challenging. Recently, the convolutional neural network (CNN) model, a type of deep learning model, has been increasingly adopted for medical image analyses. However, it is controversial whether cell characteristics can be identified at the single-cell level by using machine learning methods. This study intends to verify whether an AI system could classify the sensitivity of anticancer drugs, based on cell morphology during culture. We constructed a CNN based on the VGG16 model that could predict the efficiency of antitumor drugs at the single-cell level. The machine learning revealed that our model could identify the effects of antitumor drugs with ~0.80 accuracies. Our results show that, in the future, realizing precision medicine to identify effective antitumor drugs for individual patients may be possible by extracting CTCs from blood and performing classification by using an AI system.