Using Multi-Scale Convolutional Neural Network Based on Multi-Instance Learning to Predict the Efficacy of Neoadjuvant Chemoradiotherapy for Rectal Cancer.

BACKGROUND: At present, radical total mesorectal excision after neoadjuvant chemoradiotherapy is crucial for locally advanced rectal cancer. Therefore, the use of histopathological images analysis technology to predict the efficacy of neoadjuvant chemoradiotherapy for rectal cancer is of great significance for the subsequent treatment of patients. METHODS: In this study, we propose a new pathological images analysis method based on multi-instance learning to predict the efficacy of neoadjuvant chemoradiotherapy for rectal cancer. Specifically, we proposed a gated attention normalization mechanism based on the multilayer perceptron, which accelerates the convergence of stochastic gradient descent optimization and can speed up the training process. We also proposed a bilinear attention multi-scale feature fusion mechanism, which organically fuses the global features of the larger receptive fields and the detailed features of the smaller receptive fields and alleviates the problem of pathological images context information loss caused by block sampling. At the same time, we also designed a weighted loss function to alleviate the problem of imbalance between cancerous instances and normal instances. RESULTS: We evaluated our method on a locally advanced rectal cancer dataset containing 150 whole slide images. In addition, to verify our method's generalization performance, we also tested on two publicly available datasets, Camelyon16 and MSKCC. The results show that the AUC values of our method on the Camelyon16 and MSKCC datasets reach 0.9337 and 0.9091, respectively. CONCLUSION: Our method has outstanding performance and advantages in predicting the efficacy of neoadjuvant chemoradiotherapy for rectal cancer. Clinical and Translational Impact Statement -This study aims to predict the efficacy of neoadjuvant chemoradiotherapy for rectal cancer to assist clinicians quickly diagnose and formulate personalized treatment plans for patients.

Combined transplantation of neural stem cells and bone marrow mesenchymal stem cells promotes neuronal cell survival to alleviate brain damage after cardiac arrest via microRNA-133b incorporated in extracellular vesicles.

Neural stem cell (NSC) transplantation has prevailed as a promising protective strategy for cardiac arrest (CA)-induced brain damage. Surprisingly, the poor survival of neuronal cells in severe hypoxic condition restricts the utilization of this cell-based therapy. Extracellular vesicles (EVs) transfer microRNAs (miRNAs) between cells are validated as the mode for the release of several therapeutic molecules. The current study reports that the bone marrow mesenchymal stem cells (BMSCs) interact with NSCs via EVs thereby affecting the survival of neuronal cells. Hypoxic injury models of neuronal cells were established using cobalt chloride, followed by co-culture with BMSCs and NSCs alone or in combination. BMSCs combined with NSCs elicited as a superior protocol to stimulate neuronal cell survival. BMSCs-derived EVs could protect neuronal cells against hypoxic injury. Silencing of miR-133b incorporated in BMSCs-derived EVs could decrease the cell viability and the number of NeuN-positive cells and increase the apoptosis in the CA rat model. BMSCs-derived EVs could transfer miR-133b to neuronal cells to activate the AKT-GSK-3ß-WNT-3 signaling pathway by targeting JAK1. Our study demonstrates that NSCs promotes the release of miR-133b from BMSCs-derived EVs to promote neuronal cell survival, representing a potential therapeutic strategy for the treatment of CA-induced brain damage.

Mesenchymal stem cell­derived extracellular vesicles prevent neural stem cell hypoxia injury via promoting miR­210­3p expression.

Neural stem cells (NSCs) have the potential to give rise to offspring cells and hypoxic injury can impair the function of NSCs. The present study investigated the effects of mesenchymal stem cell (MSC)­derived extracellular vesicles (EVs) on NSC injury, as well as the underlying mechanisms. MSC­EVs were isolated and identified via morphological and particle size analysis. Cobalt chloride was used to establish a hypoxic injury model in NSCs. Terminal deoxynucleotidyl transferase dUTP nick end labeling assay was conducted to detect apoptosis. Reverse transcription­quantitative PCR was performed to detect the expression levels of miR­210­3p, and western blotting was used to detect the expression levels of apoptosis­inducing factor (AIF) and Bcl­2 19 kDa interacting protein (BNIP3). Compared with the control group, NSC apoptosis, and the expression of miR­210­3p, AIF and BNIP3 were significantly higher in the cobalt chloride­induced hypoxia group. By contrast, treatment with MSC­EVs further increased miR­210­3p expression levels, but reduced NSC apoptosis and the expression levels of AIF and BNIP3 compared with the model group (P<0.05). In addition, miR­210­3p inhibitor reduced miR­210­3p expression, but promoted hypoxia­induced apoptosis and the expression levels of AIF and BNIP3 compared with the model group (P<0.05). Collectively, the results suggested that MSC­EVs prevented NSC hypoxia injury by promoting miR­210­3p expression, which might reduce AIF and BNIP3 expression levels and NSC apoptosis.