Deep Learning Prediction for Distal Aortic Remodeling After Thoracic Endovascular Aortic Repair in Stanford Type B Aortic Dissection.

PURPOSE: This study aimed to develop a deep learning model for predicting distal aortic remodeling after proximal thoracic endovascular aortic repair (TEVAR) in patients with Stanford type B aortic dissection (TBAD) using computed tomography angiography (CTA). METHODS: A total of 147 patients with acute or subacute TBAD who underwent proximal TEVAR at a single center were retrospectively reviewed. The boundary of aorta was manually segmented, and the point clouds of each aorta were obtained. Prediction of negative aortic remodeling or reintervention was accomplished by a convolutional neural network (CNN) and a point cloud neural network (PC-NN), respectively. The discriminatory value of the established models was mainly evaluated by the area under the receiver operating characteristic curve (AUC) in the test set. RESULTS: The mean follow-up time was 34.0 months (range: 12-108 months). During follow-up, a total of 25 (17.0%) patients were identified as having negative aortic remodeling, and 16 (10.9%) patients received reintervention. The AUC (0.876) by PC-NN for predicting negative aortic remodeling was superior to that obtained by CNN (0.612, p=0.034) and similar to the AUC by PC-NN combined with clinical features (0.884, p=0.92). As to reintervention, the AUC by PC-NN was significantly higher than that by CNN (0.805 vs 0.579; p=0.042), and AUCs by PC-NN combined with clinical features and PC-NN alone were comparable (0.836 vs 0.805; p=0.81). CONCLUSION: The CTA-based deep learning algorithms may assist clinicians in automated prediction of distal aortic remodeling after TEVAR for acute or subacute TBAD. CLINICAL IMPACT: Negative aortic remodeling is the leading cause of late reintervention after proximal thoracic endovascular aortic repair (TEVAR) for Stanford type B aortic dissection (TBAD), and possesses great challenge to endovascular repair. Early recognizing high-risk patients is of supreme importance for optimizing the follow-up interval and therapy strategy. Currently, clinicians predict the prognosis of these patients based on several imaging signs, which is subjective. The computed tomography angiography-based deep learning algorithms may incorporate abundant morphological information of aorta, provide with a definite and objective output value, and finally assist clinicians in automated prediction of distal aortic remodeling after TEVAR for acute or subacute TBAD.

YOLOv5s-CA: A Modified YOLOv5s Network with Coordinate Attention for Underwater Target Detection.

Underwater target detection techniques have been extensively applied to underwater vehicles for marine surveillance, aquaculture, and rescue applications. However, due to complex underwater environments and insufficient training samples, the existing underwater target recognition algorithm accuracy is still unsatisfactory. A long-term effort is essential to improving underwater target detection accuracy. To achieve this goal, in this work, we propose a modified YOLOv5s network, called YOLOv5s-CA network, by embedding a Coordinate Attention (CA) module and a Squeeze-and-Excitation (SE) module, aiming to concentrate more computing power on the target to improve detection accuracy. Based on the existing YOLOv5s network, the number of bottlenecks in the first C3 module was increased from one to three to improve the performance of shallow feature extraction. The CA module was embedded into the C3 modules to improve the attention power focused on the target. The SE layer was added to the output of the C3 modules to strengthen model attention. Experiments on the data of the 2019 China Underwater Robot Competition were conducted, and the results demonstrate that the mean Average Precision (mAP) of the modified YOLOv5s network was increased by 2.4%.

Theoretical analysis of effects of transcranial magneto-acoustical stimulation on neuronal spike-frequency adaptation.

BACKGROUND: Transcranial magneto-acoustical stimulation (TMAS) is a noninvasive technique that has advantages in spatial resolution and penetration depth. It changes the firing properties of neurons through the current generated by focused ultrasound and a static magnetic field. Spike-frequency adaptation is an important dynamic characteristic of neural information processing. METHODS: To address the effects of TMAS on neural spike-frequency adaptation, this study employs some ultrasound and magnetic field parameters, such as magnetic flux density, ultrasonic intensity, fundamental ultrasonic frequency, modulation frequency, and duty cycle. Using these different ultrasound and magnetic field parameters, membrane potential curves, spike-frequency curves, and adapted onset spike-frequency curves are exhibited and analyzed. RESULTS: The results show that spike-frequency adaptation is strongly dependent on ultrasonic intensity and magnetic flux density and is rarely affected by other parameters. However, modulation frequency and duty cycle influence membrane potentials and spike frequencies to some degree. CONCLUSIONS: This study reveals the mechanism of the effects of TMAS on neural spike-frequency adaptation and serves as theoretical guidance for TMAS experiments.

Virtual-Lattice Based Intrusion Detection Algorithm over Actuator-Assisted Underwater Wireless Sensor Networks.

Due to the lack of a physical line of defense, intrusion detection becomes one of the key issues in applications of underwater wireless sensor networks (UWSNs), especially when the confidentiality has prime importance. However, the resource-constrained property of UWSNs such as sparse deployment and energy constraint makes intrusion detection a challenging issue. This paper considers a virtual-lattice-based approach to the intrusion detection problem in UWSNs. Different from most existing works, the UWSNs consist of two kinds of nodes, i.e., sensor nodes (SNs), which cannot move autonomously, and actuator nodes (ANs), which can move autonomously according to the performance requirement. With the cooperation of SNs and ANs, the intruder detection probability is defined. Then, a virtual lattice-based monitor (VLM) algorithm is proposed to detect the intruder. In order to reduce the redundancy of communication links and improve detection probability, an optimal and coordinative lattice-based monitor patrolling (OCLMP) algorithm is further provided for UWSNs, wherein an equal price search strategy is given for ANs to find the shortest patrolling path. Under VLM and OCLMP algorithms, the detection probabilities are calculated, while the topology connectivity can be guaranteed. Finally, simulation results are presented to show that the proposed method in this paper can improve the detection accuracy and save the energy consumption compared with the conventional methods.

Defect Detection of Adhesive Layer of Thermal Insulation Materials Based on Improved Particle Swarm Optimization of ECT.

This paper studies the defect detection problem of adhesive layer of thermal insulation materials. A novel detection method based on an improved particle swarm optimization (PSO) algorithm of Electrical Capacitance Tomography (ECT) is presented. Firstly, a least squares support vector machine is applied for data processing of measured capacitance values. Then, the improved PSO algorithm is proposed and applied for image reconstruction. Finally, some experiments are provided to verify the effectiveness of the proposed method in defect detection for adhesive layer of thermal insulation materials. The performance comparisons demonstrate that the proposed method has higher precision by comparing with traditional ECT algorithms.

Negative Instance Guided Self-Distillation Framework for Whole Slide Image Analysis.

Histopathology image classification is an important clinical task, and current deep learning-based whole-slide image (WSI) classification methods typically cut WSIs into small patches and cast the problem as multi-instance learning. The mainstream approach is to train a bag-level classifier, but their performance on both slide classification and positive patch localization is limited because the instance-level information is not fully explored. In this article, we propose a negative instance-guided, self-distillation framework to directly train an instance-level classifier end-to-end. Instead of depending only on the self-supervised training of the teacher and the student classifiers in a typical self-distillation framework, we input the true negative instances into the student classifier to guide the classifier to better distinguish positive and negative instances. In addition, we propose a prediction bank to constrain the distribution of pseudo instance labels generated by the teacher classifier to prevent the self-distillation from falling into the degeneration of classifying all instances as negative. We conduct extensive experiments and analysis on three publicly available pathological datasets: CAMELYON16, PANDA, and TCGA, as well as an in-house pathological dataset for cervical cancer lymph node metastasis prediction. The results show that our method outperforms existing methods by a large margin. Code will be publicly available.

Robust Point Cloud Registration Framework Based on Deep Graph Matching.

3D point cloud registration is a fundamental problem in computer vision and robotics. Recently, learning-based point cloud registration methods have made great progress. However, these methods are sensitive to outliers, which lead to more incorrect correspondences. In this paper, we propose a novel deep graph matching-based framework for point cloud registration. Specifically, we first transform point clouds into graphs and extract deep features for each point. Then, we develop a module based on deep graph matching to calculate a soft correspondence matrix. By using graph matching, not only the local geometry of each point but also its structure and topology in a larger range are considered in establishing correspondences, so that more correct correspondences are found. We train the network with a loss directly defined on the correspondences, and in the test stage the soft correspondences are transformed into hard one-to-one correspondences so that registration can be performed by a correspondence-based solver. Furthermore, we introduce a transformer-based method to generate edges for graph construction, which further improves the quality of the correspondences. Extensive experiments on object-level and scene-level benchmark datasets show that the proposed method achieves state-of-the-art performance.

Prediction of cerebral aneurysm rupture using a point cloud neural network.

OBJECTIVE: Accurate prediction of cerebral aneurysm (CA) rupture is of great significance. We intended to evaluate the accuracy of the point cloud neural network (PC-NN) in predicting CA rupture using MR angiography (MRA) and CT angiography (CTA) data. METHODS: 418 CAs in 411 consecutive patients confirmed by CTA (n=180) or MRA (n=238) in a single hospital were retrospectively analyzed. A PC-NN aneurysm model with/without parent artery involvement was used for CA rupture prediction and compared with ridge regression, support vector machine (SVM) and neural network (NN) models based on radiomics features. Furthermore, the performance of the trained PC-NN and radiomics-based models was prospectively evaluated in 258 CAs of 254 patients from five external centers. RESULTS: In the internal test data, the area under the curve (AUC) of the PC-NN model trained with parent artery (AUC=0.913) was significantly higher than that of the PC-NN model trained without parent artery (AUC=0.851; p=0.041) and of the ridge regression (AUC=0.803; p=0.019), SVM (AUC=0.788; p=0.013) and NN (AUC=0.805; p=0.023) radiomics-based models. Additionally, the PC-NN model trained with MRA source data achieved a higher prediction accuracy (AUC=0.936) than that trained with CTA source data (AUC=0.824; p=0.043). In external data of prospective cohort patients, the AUC of PC-NN was 0.835, significantly higher than ridge regression (0.692; p<0.001), SVM (0.701; p<0.001) and NN (0.681; p<0.001) models. CONCLUSION: PC-NNs can achieve more accurate CA rupture prediction than traditional radiomics-based models. Furthermore, the performance of the PC-NN model trained with MRA data was superior to that trained with CTA data.

Prediction of return to work outcomes under an injured worker case management program.

INTRODUCTION: Many factors affect worker return to work (RTW) after occupational injury, among which effective case management strategies play a particularly vital role in prompting workers for a successful RTW. Objectives This study aimed at predicting the RTW outcome and optimizing the intervention scheme of a case management program initiated in China. METHODS: A retrospective cohort was formed with 523 injured workers treated at a rehabilitation center for work injuries in southern China. The social demographic information, medical data and intervention process were extracted from the medical records of the rehabilitation center. A Cox Regression Model was used to examine the predictors of RTW case management. RESULTS: 261 patients (77.9%) out of the 335 valid subjects successfully returned to work after median absence duration of 36.0 days. A computer skills training program was a positive factor for RTW outcomes (hazard ratio 1.5, P < 0.001). Psychological counseling was possibly an important measure to improve RTW with a hazard ratio of 3.4 (95% CI 0.94-16, P > 0.05). Disability adjustment accommodations did not specifically benefit RTW. Education level, family's attitude to RTW, personal perceptions about social support for RTW, and injury severity were significantly associated with outcomes of RTW. CONCLUSIONS: It was implied that RTW intervention should be focused on a specific skill reconstruction and training which was presumably related with labor market needs. However, tailored psychological counseling and disability adjustment activity should not be ignored in RTW.

Case management after long-term absence from work in China: a case report.

INTRODUCTION: Return-to-work (RTW) after occupational injuries is an important and challenging issue. Case managers are expected to play a vital role in successful RTW. In China, RTW intervention is in its early phase and requires further research and practice. OBJECTIVES: This case report describes Mr. H's RTW process for illustrating the work of a case management team in China. Suggestions on developing and optimizing the process in China are given. METHODS: After 9 years of absence from work due to severe burn injuries at work, Mr. H was referred for RTW interventions. Mr. H received social and occupational rehabilitation services of 3 months, and the following workplace visits and work trials. After the job placement, the case manager continued the liaison with the worker and employer. RESULTS: Mr. H showed positive changes in occupational and social adjustment after the case management interventions. This was reflected from the shift from the contemplation to action stage on the Lam Assessment of Stages of Employment Readiness. Despite he did not show significant changes on functional capacity and fear avoidance beliefs, Mr. H passed the job credential test and was offered a maintenance technician position at a new company. Both the worker and the employer were satisfied with the outcome of the case management. CONCLUSIONS: The RTW interventions carried out by the case managers appeared to be effective within the Chinese system. The results suggested that professional training of case managers, RTW-related policies and technological standards, early integrated interventions should be further developed in China. Disability Adjustment Group Therapy and RTW Support Groups perhaps are useful approaches in workers' returning to work.

An emerging occupational rehabilitation system in the People's Republic of China.

INTRODUCTION: China has become a major economic influence in Asia and globally. The country is in the position to further develop its workers' insurance and compensation system. This paper aims to introduce the existing workers' compensation policies, explain how these policies guide the operation of the occupational rehabilitation system for injured workers, and suggest ways to further develop an effective and sustainable system for the country. METHODS: Major government policies and initiative documents and existing literature on occupational rehabilitation were critically reviewed. Shortfalls in our current system were identified and potential further development regimes were propose. RESULTS: Since 2004, China has implemented its national policy on providing timely and comprehensive rehabilitation and return-to-work interventions for workers who are injured at work. The three-tier medical and occupational rehabilitation system appears effective for enabling injured workers to access these services. Such a system is regarded as the most optimal for the country in spearheading the development of quality occupational rehabilitation services, and at the same time incorporating the existing expertise in acute medical care and rehabilitation within the public medical and health system. Problems encountered in the system can be classified under the culture, system and competence building aspects. CONCLUSION: The future workers' insurance and compensation system can probably put more emphasis on using bio-psychosocial and work disability prevention models in guiding its service development and delivery. Efforts need to be placed on building the competence of professionals in the system who provide services for injured workers. The empowerment of important stakeholders in the workers' insurance and compensation system and their inclusion in the planning of service delivery are crucial for developing a sustainable and effective system for China.

Unidirectional Synchronization of Hodgkin-Huxley Neurons With Prescribed Performance Under Transcranial Magneto-Acoustical Simulation.

This paper exploits the unidirectional synchronization dynamics of two Hodgkin-Huxley (HH) neurons under transcranial magneto-acoustical stimulation (TMAS). The major purpose is to explore a control scheme to make the spiking modes of the neural potentials stimulated by TMAS achieve synchronization states under the feedback input. For this purpose, an adaptive neural controller, which makes the neurons satisfy the prescribed master-slaver synchronization performance, is designed by introducing a tracking error into Lyapunov analysis. Under the proposed control scheme, the slaver neuron can not only overcome the model uncertainties and the difficulties brought by prescribed performance, but also track the spiking patterns of the master neuron. Finally, the simulations are implemented to demonstrate the effectiveness of the proposed controller, that is, the TMAS induced synchronization states of the HH neuron system can achieve the prescribed performance under the proposed controller.

The effect of demographic and social factors on return to work of injured workers with musculoskeletal disorders.

OBJECTIVES: This paper aims to explore the effects of demographic and social factors for those suffering from work-related injuries with musculoskeletal disorders and their employment status after discharge within three months. METHOD: The employment status and compensation-related information was caught by adopting telephone follow up with the designated data collection questionnaire; other demographic characteristic and social factors were obtained by reviewing injured workers' original admission records. RESULTS: In total sixty-eight injured workers were involved with a 67.6% return to work rate. Time of hospitalization (t=2.34, p=0.02) and area of registered residence (x;(2)=8.37, p=0.02) significant differences were found between the return to work group and non-return to work group. The only predictor found by using Logistic Regression analysis was the length of hospitalization (OR=0.978, 95%CI: 0.959-0.998). CONCLUSIONS: The shorter the length of hospitalization during the rehabilitation process, the greater the rate of return to work for those workers suffering from work-related injuries with musculoskeletal disorders.

Output Consensus of Heterogeneous Linear Discrete-Time Multiagent Systems With Structural Uncertainties.

This paper investigates the output consensus problem of heterogeneous discrete-time multiagent systems with individual agents subject to structural uncertainties and different disturbances. A novel distributed control law based on internal reference models is first presented for output consensus of heterogeneous discrete-time multiagent systems without structural uncertainties, where internal reference models embedded in controllers are designed with the objective of reducing communication costs. Then based on the distributed internal reference models and the well-known internal model principle, a distributed control law is further presented for output consensus of heterogeneous discrete-time multiagent systems with structural uncertainties. It is shown in both cases that the consensus trajectory of the internal reference models determines the output trajectories of agents. Finally, numerical simulation results are provided to illustrate the effectiveness of the proposed control schemes.