Combining the YOLOv4 Deep Learning Model with UAV Imagery Processing Technology in the Extraction and Quantization of Cracks in Bridges.

Bridges are often at risk due to the effects of natural disasters, such as earthquakes and typhoons. Bridge inspection assessments normally focus on cracks. However, numerous concrete structures with cracked surfaces are highly elevated or over water, and is not easily accessible to a bridge inspector. Furthermore, poor lighting under bridges and a complex visual background can hinder inspectors in their identification and measurement of cracks. In this study, cracks on bridge surfaces were photographed using a UAV-mounted camera. A YOLOv4 deep learning model was used to train a model for identifying cracks; the model was then employed in object detection. To perform the quantitative crack test, the images with identified cracks were first converted to grayscale images and then to binary images the using local thresholding method. Next, the two edge detection methods, Canny and morphological edge detectors were applied to the binary images to extract the edges of the cracks and obtain two types of crack edge images. Then, two scale methods, the planar marker method, and the total station measurement method, were used to calculate the actual size of the crack edge image. The results indicated that the model had an accuracy of 92%, with width measurements as precise as 0.22 mm. The proposed approach can thus enable bridge inspections and obtain objective and quantitative data.

Non-metallic nanomaterials in cancer theranostics: a review of silica- and carbon-based drug delivery systems.

The rapid development in nanomaterials has brought great opportunities to cancer theranostics, which aims to combine diagnostics and therapy for cancer treatment and thereby improve the healthcare of patients. In this review we focus on the recent progress of several cancer theranostic strategies using mesoporous silica nanoparticles and carbon-based nanomaterials. Silicon and carbon are both group IV elements; they have been the most abundant and significant non-metallic substances in human life. Their intrinsic physical/chemical properties are of critical importance in the fabrication of multifunctional drug delivery systems. Responsive nanocarriers constructed using these nanomaterials have been promising in cancer-specific theranostics during the past decade. In all cases, either a controlled texture or the chemical functionalization is coupled with adaptive properties, such as pH-, light-, redox- and magnetic field- triggered responses. Several studies in cells and mice models have implied their underlying therapeutic efficacy; however, detailed and long-term in vivo clinical evaluations are certainly required to make these bench-made materials compatible in real bedside circumstances.

Immunoprotectivity of HLA-A2 CTL peptides derived from respiratory syncytial virus fusion protein in HLA-A2 transgenic mouse.

Identification of HLA-restricted CD8+ T cell epitopes is important to study RSV-induced immunity and illness. We algorithmically analyzed the sequence of the fusion protein (F) of respiratory syncytial virus (RSV) and generated synthetic peptides that can potentially bind to HLA-A*0201. Four out of the twenty-five 9-mer peptides tested: peptides 3 (F33-41), 13 (F214-222), 14 (F273-281), and 23 (F559-567), were found to bind to HLA-A*0201 with moderate to high affinity and were capable of inducing IFN-γ and IL-2 secretion in lymphocytes from HLA-A*0201 transgenic (HLA-Tg) mice pre-immunized with RSV or recombinant adenovirus expressing RSV F. HLA-Tg mice were immunized with these four peptides and were found to induce both Th1 and CD8+ T cell responses in in vitro secondary recall. Effector responses induced by these peptides were observed to confer differential protection against live RSV challenge. These peptides also caused better recovery of body weight loss induced by RSV. A significant reduction of lung viral load was observed in mice immunized with peptide 23, which appeared to enhance the levels of inflammatory chemokines (CCL17, CCL22, and IL-18) but did not increase eosinophil infiltration in the lungs. Whereas, significant reduction of infiltrated eosinophils induced by RSV infection was found in mice pre-immunized with peptide 13. Our results suggest that HLA-A2-restricted epitopes of RSV F protein could be useful for the development of epitope-based RSV vaccine.