Individual tooth segmentation from cone beam computed tomography (CBCT) images is an essential prerequisite for an anatomical understanding of orthodontic structures in several applications, such as tooth reformation planning and implant guide simulations. However, the presence of severe metal artifacts in CBCT images hinders the accurate segmentation of each individual tooth. In this study, we propose a neural network for pixel-wise labeling to exploit an instance segmentation framework that is robust to metal artifacts. Our method comprises of three steps: 1) image cropping and realignment by pose regressions, 2) metal-robust individual tooth detection, and 3) segmentation. We first extract the alignment information of the patient by pose regression neural networks to attain a volume-of-interest (VOI) region and realign the input image, which reduces the interoverlapping area between tooth bounding boxes. Then, individual tooth regions are localized within a VOI realigned image using a convolutional detector. We improved the accuracy of the detector by employing non-maximum suppression and multiclass classification metrics in the region proposal network. Finally, we apply a convolutional neural network (CNN) to perform individual tooth segmentation by converting the pixel-wise labeling task to a distance regression task. Metal-intensive image augmentation is also employed for a robust segmentation of metal artifacts. The result shows that our proposed method outperforms other state-of-the-art methods, especially for teeth with metal artifacts. Our method demonstrated 5.68% and 30.30% better accuracy in the F1 score and aggregated Jaccard index, respectively, when compared to the best performing state-of-the-art algorithms. The primary significance of the proposed method is two-fold: 1) an introduction of pose-aware VOI realignment followed by a robust tooth detection and 2) a metal-robust CNN framework for accurate tooth segmentation.Index Terms-Cone beam computed tomography image segmentation, pose-aware tooth detection, pose regression neural network, tooth instance segmentation.
The aim of this study was to determine the effects of motor dual-task training (MDT), cognitive dual-task training (CDT), and motor and cognitive dual-task training (MCDT) on balance and daily living abilities of stroke patients. In addition, the relationships among assessment tools such as center of pressure (COP), Korean version of Berg Balance Scale (K-BBS), and the Functional Independence Measure (FIM) were investigated. [Subjects and Method] Thirty-eight stroke patients were randomly allocated to a MDT group, a CDT group, and a MCDT group, and training was performed three times a week for six weeks. The patients' balance was assessed with the mean area of COP movement and K-BBS, and the daily living abilities were evaluated with FIM before and after the training. [Results] Post-training, a significant difference in COP was found in each of the three groups, and between the CDT group and the MCDT group. K-BBS and FIM also showed a significant difference in each of the three groups, and comparison among the three groups showed that the improvement in the MCDT group was significantly better than those of the other two groups. Highly negative correlations were found between COP and K-BBS and between COP and FIM (r=-0.960,-0.874, respectively), and a highly positive correlation was found between K-BBS and FIM (r=0.870). [Conclusion] For effective training of balance and daily living abilities for stroke patients, it is more effective to implement both motor and cognitive dual-tasks than motor or cognitive dualtasks alone.
This project presents pavement treatment practice guidelines and a distress identification manual for the purpose of improving the INDOT pavement preservation practices. The treatment guidelines consist of 10 treatment types for asphalt pavements and composite pavements and 8 treatment types for Portland cement concrete pavement (PCCP). The treatment guidelines include treatment descriptions, benefits, applicable pavement conditions, treatment materials, and treatment procedures. The guidelines are based on information obtained mainly from the INDOT Standard Specification, the INDOT Design Manual, and the INDOT Field Operations Handbook for Crew Leaders. The treatments are covered in the guidelines. The distress identification manual presents the different types of distresses found on the surfaces of asphalt pavement, composite pavement, and PCCP. Each distress type in this manual is presented along with descriptions, causes, measurements, and pictures of each type of distress. The manual is mainly based on the Distress Identification Manual for the Long Term Pavement Performance Program (LTPP) and the INDOT Design Manual. To implement the guidelines and the manuals, training slides were developed and are enclosed in this report. The training slides were developed to address all topics of the pavement preservation treatment area and combine to make one set of training materials suitable for Indiana. The training slides for pavement preservation implementation can help to enhance the overall construction quality of treatments by illustrating the appropriate use of such treatments in applications, thereby contributing to their improved performance. This improvement will help to ensure that the treatments are used to their maximum benefit and efficiency.
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.