Emerging chemotherapy drugs and targeted therapies have been widely applied in anticancer treatment and have given oncologists a promising future. Nevertheless, regeneration and recurrence are still huge obstacles on the way to cure cancer. Cancer stem cells (CSCs) are capable of self-renewal, tumor initiation, recurrence, metastasis, therapy resistance, and reside as a subset in many, if not all, cancers. Therefore, therapeutics specifically targeting and killing CSCs are being identified, and may be promising and effective strategies to eliminate cancer. MicroRNAs (miRNAs, miRs), small noncoding RNAs regulating gene expression in a post-transcriptional manner, are dysregulated in most malignancies and are identified as important regulators of CSCs. However, limited knowledge exists for biological and molecular mechanism by which miRNAs regulate CSCs. In this article, we review CSCs, miRNAs and the interactions between miRNA regulation and CSCs, with a specific focus on the molecular mechanisms and clinical applications. This review will help us to know in detail how CSCs are regulated by miRNAs networks and also help to develop more effective and secure miRNA-based clinical therapies.

The oncogenic role of estrogen receptor (ER)α and its correlation with let-7 microRNAs (miRNAs) have been studied and confirmed in breast tumors; however, this correlation has not been investigated in breast cancer stem cells (BCSCs). In the present study, we detected the expression of let-7 and ERα in ER-positive breast tumor tissues. Furthermore, we used a FACSAria cell sorter to separate side population (SP) cells from the MCF-7 and T47-D cell lines by Hoechst 33342 staining. The expression of let-7 miRNAs, ERα and its downstream genes in SP and non-SP (NSP) cells were analyzed. In additional experiments, we transfected a plasmid expressing let-7a into SP cells isolated from the MCF-7 and T47-D cell lines in order to observe changes in the expression of downstream genes (cyclin D1 and pS2). The correlation among let-7, ERα and ERα downstream genes suggested that let-7 acts as a tumor suppressor by inhibiting ERα-mediated cellular malignant growth in ER-positive breast cancer stem cells. The suppression of ERα by the upregulation of let-7 expression may be a promising strategy for the inhibition of the ER signaling pathway and for the elimination of cancer stem cells, thus aiding in the treatment of breast cancer.

Building change detection is important for urban area monitoring, disaster assessment and updating geo-database. 3D information derived from image dense matching or airborne light detection and ranging (LiDAR) is very effective for building change detection. However, combining 3D data from different sources is challenging, and so far few studies have focused on building change detection using both images and LiDAR data. This study proposes an automatic method to detect building changes in urban areas using aerial images and LiDAR data. First, dense image matching is carried out to obtain dense point clouds and then co-registered LiDAR point clouds using the iterative closest point (ICP) algorithm. The registered point clouds are further resampled to a raster DSM (Digital Surface Models). In a second step, height difference and grey-scale similarity are calculated as change indicators and the graph cuts method is employed to determine changes considering the contexture information. Finally, the detected results are refined by removing the non-building changes, in which a novel method based on variance of normal direction of LiDAR points is proposed to remove vegetated areas for positive building changes (newly building or taller) and nEGI (normalized Excessive Green Index) is used for negative building changes (demolish building or lower). To evaluate the proposed method, a test area covering approximately 2.1 km 2 and consisting of many different types of buildings is used for the experiment. Results indicate 93% completeness with correctness of 90.2% for positive changes, while 94% completeness with correctness of 94.1% for negative changes, which demonstrate the promising performance of the proposed method.

Background: Bacterial vaginosis (BV) is caused by the excessive and imbalanced growth of bacteria in vagina, affecting 30-50% of women in their lives. Gram stain followed by Nugent scoring based on bacterial morphotypes under the microscope (NS) has been considered the golden standard for BV diagnosis, which is often labor-intensive, time-consuming, and variable results from person to person. Methods: We developed and optimized a convolutional neural networks (CNN) model, and evaluated its ability to automatically identify and classify three categories of Nugent scores from microscope images. The CNN model was first established with a panel of microscopic images with Nugent scores determined by experts. The model was trained by minimizing the cross entropy loss function and optimized by using a momentum optimizer. The separate test sets of images collected from three hospitals were evaluated by the CNN models. Results: The CNN model consisted of 25 convolutional layers, 2 pooling layers, and a fully connected layer. The model obtained 82.4% sensitivity and 96.6% specificity on the 5,815 validation images when considered altered vaginal flora and BV as the positive samples, which was better than the top-level technologists and obstetricians in China. The ability of generalization for our model was strong that it obtained 75.1% accuracy of three categories of Nugent scores on the independent test set of 1082 images, which was 6.6% higher than the average of three technologists, who are with a bachelor degree in medicine and eligible making diagnostic decisions. When three technologists ran one specimen in triplicate, the precision of three categories of Nugent scores was 54.0%. 103 samples diagnosed by two technologists at different days showed repeatability of 90.3%. Conclusion: The CNN model over-performed human healthcare practitioners on accuracy and stability for three categories of Nugent scores diagnosis. The deep learning model may offer translational applications in automating diagnosis of bacterial vaginosis with proper supporting hardware.