A recurrent neural network (RNN) called CrackNet‐R is proposed in the article for fully automated pixel‐level crack detection on three‐dimensional (3D) asphalt pavement surfaces. In the article, a new recurrent unit, gated recurrent multilayer perceptron (GRMLP), is proposed to recursively update the internal memory of CrackNet‐R. Unlike the widely used long short‐term memory (LSTM) and gated recurrent unit (GRU), GRMLP is intended for deeper abstractions on the inputs and hidden states by conducting multilayer nonlinear transforms at gating units. CrackNet‐R implements a two‐phase sequence processing: sequence generation and sequence modeling. Sequence generation is specifically developed in the study to find the best local paths that are most likely to form crack patterns. Sequence modeling predicts timely probabilities of the input sequence being a crack pattern. In terms of sequence modeling, GRMLP slightly outperforms LSTM and GRU by using only one more nonlinear layer at each gate. In addition to sequence processing, an output layer is proposed to produce pixel probabilities based on timely probabilities predicted for sequences. The proposed output layer is critical for pixel‐perfect accuracy, as it accomplishes the transition from sequence‐level learning to pixel‐level learning. Using 3,000 diverse 3D images, the training of CrackNet‐R is completed through optimizing sequence modeling, sequence generation, and the output layer serially. The experiment using 500 testing pavement images shows that CrackNet‐R can achieve high Precision (88.89%), Recall (95.00%), and F‐measure (91.84%) simultaneously. Compared with the original CrackNet, CrackNet‐R is about four times faster and introduces tangible improvements in detection accuracy.
Objective: We aimed to evaluate the activity of the human glymphatic system in type 2 diabetes mellitus (T2DM) using diffusion tensor image analysis along with the perivascular space (DTI-ALPS). Methods: Diffusion tensor images were acquired to calculate the diffusivities in the direction of the x-axis (right-to-left; Dx), y-axis (anterior-to-posterior; Dy), and z-axis (inferior-to-superior; Dz) of the plane of the lateral ventricle body in 20 patients with type 2 diabetes and 10 people in a control group. We evaluated the diffusivity along with the perivascular spaces, as well as the projection fibers and association fibers, separately. The analysis along the perivascular space (ALPS-index) was defined as the mean (Dxpro, Dypro)/mean (Dypro, Dzasc), where the Dxpro and Dxasc were the Dx values in the projection and association fiber areas, respectively. Results: There were significant differences in diffusivity along the projection fibers and the association fibers among the groups. The significant differences among the groups along the perivascular spaces, shown as the ALPS-index and medical history of T2DM, indicating lower water diffusivity along the perivascular space concerning type 2 diabetes severity, was also observed. Conclusion: Lower diffusivity along the perivascular space on DTI-APLS can reflect impairment of the glymphatic system in T2DM. This study showed that the activity of the glymphatic system could be evaluated by diffusion tensor image analysis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.