The CrackNet, an efficient architecture based on the Convolutional Neural Network (CNN), is proposed in this article for automated pavement crack detection on 3D asphalt surfaces with explicit objective of pixel‐perfect accuracy. Unlike the commonly used CNN, CrackNet does not have any pooling layers which downsize the outputs of previous layers. CrackNet fundamentally ensures pixel‐perfect accuracy using the newly developed technique of invariant image width and height through all layers. CrackNet consists of five layers and includes more than one million parameters that are trained in the learning process. The input data of the CrackNet are feature maps generated by the feature extractor using the proposed line filters with various orientations, widths, and lengths. The output of CrackNet is the set of predicted class scores for all pixels. The hidden layers of CrackNet are convolutional layers and fully connected layers. CrackNet is trained with 1,800 3D pavement images and is then demonstrated to be successful in detecting cracks under various conditions using another set of 200 3D pavement images. The experiment using the 200 testing 3D images showed that CrackNet can achieve high Precision (90.13%), Recall (87.63%) and F‐measure (88.86%) simultaneously. Compared with recently developed crack detection methods based on traditional machine learning and imaging algorithms, the CrackNet significantly outperforms the traditional approaches in terms of F‐measure. Using parallel computing techniques, CrackNet is programmed to be efficiently used in conjunction with the data collection software.

Type 2 inflammation underlies allergic diseases such as atopic dermatitis (AD), which is characterized by the accumulation of basophils and group 2 innate lymphoid cells (ILC2s) in inflamed skin lesions. Although murine studies have demonstrated that cutaneous basophil and ILC2 responses are dependent on thymic stromal lymphopoietin (TSLP), whether these cell populations interact to regulate the development of cutaneous type 2 inflammation is poorly defined. Here, we identify that basophils and ILC2s significantly accumulate in inflamed human and murine skin and form clusters not observed in control skin. We demonstrate that murine basophil responses precede ILC2 responses and that basophils are the dominant IL-4-eGFP-expressing cell type in inflamed skin. Further, basophils and IL-4 were necessary for the optimal accumulation of ILC2s and induction of AD-like disease. We show that ILC2s express the IL-4 receptor alpha (IL-4Rα) and proliferate in an IL-4-dependent manner. In addition, basophil-derived IL-4 was required for cutaneous ILC2 responses in vivo and directly regulated ILC2 proliferation ex vivo. Collectively, these data reveal a previously unrecognized role for basophil-derived IL-4 in promoting ILC2 responses during cutaneous inflammation.

Breaches in the skin barrier initiate an inflammatory immune response that is critical for successful wound healing. Innate lymphoid cells (ILCs) are a recently identified population of immune cells that reside at epithelial barrier surfaces such as the skin, lung and gut and promote pro-inflammatory or epithelial repair functions following exposure to allergens, pathogens or chemical irritants. However, the potential role of ILCs in regulating cutaneous wound healing remains undefined. Here, we demonstrate that cutaneous injury promotes an IL-33-dependent group 2 ILC (ILC2) response and that abrogation of this response impairs re-epithelialization and efficient wound closure. Additionally, we provide evidence suggesting that an analogous ILC2 response is operational in acute wounds of human skin. Together, these results indicate that IL-33-responsive ILC2s are an important link between the cutaneous epithelium and the immune system, acting to promote the restoration of skin integrity following injury.

We report the laser-induced periodic surface structure (LIPSS) with periodicity about a quarter of the laser wavelength on unpolished diamond film treated by a P-polarized femtosecond laser. The short period LIPSS is parallel to the laser polarization and independent on the incidence angle. The LIPSS perpendicular to the laser polarization with periodicity shorter than a third of the laser wavelength slightly dependent on the incidence angle is also observed as well as the LIPSS perpendicular to the laser polarization with periodicity dependent on the incidence angle. The results are explained by interference of the incident laser and surface scattered wave related to the excited electrons during laser interactions with diamond, being in excellent agreement with a previously developed theory.