Development and Validation of a 3D Resnet Model for Prediction of Lymph Node Metastasis in Head and Neck Cancer Patients.

The accurate diagnosis and staging of lymph node metastasis (LNM) are crucial for determining the optimal treatment strategy for head and neck cancer patients. We aimed to develop a 3D Resnet model and investigate its prediction value in detecting LNM. This study enrolled 156 head and neck cancer patients and analyzed 342 lymph nodes segmented from surgical pathologic reports. The patients' clinical and pathological data related to the primary tumor site and clinical and pathology T and N stages were collected. To predict LNM, we developed a dual-pathway 3D Resnet model incorporating two Resnet models with different depths to extract features from the input data. To assess the model's performance, we compared its predictions with those of radiologists in a test dataset comprising 38 patients. The study found that the dimensions and volume of LNM + were significantly larger than those of LNM-. Specifically, the Y and Z dimensions showed the highest sensitivity of 84.6% and specificity of 72.2%, respectively, in predicting LNM + . The analysis of various variations of the proposed 3D Resnet model demonstrated that Dual-3D-Resnet models with a depth of 34 achieved the highest AUC values of 0.9294. In the validation test of 38 patients and 86 lymph nodes dataset, the 3D Resnet model outperformed both physical examination and radiologists in terms of sensitivity (80.8% compared to 50.0% and 91.7%, respectively), specificity(90.0% compared to 88.5% and 65.4%, respectively), and positive predictive value (77.8% compared to 66.7% and 55.0%, respectively) in detecting individual LNM + . These results suggest that the 3D Resnet model can be valuable for accurately identifying LNM + in head and neck cancer patients. A prospective trial is needed to evaluate further the role of the 3D Resnet model in determining LNM + in head and neck cancer patients and its impact on treatment strategies and patient outcomes.

Representative Data Selection for Efficient Medical Incremental Learning.

To train a deep neural network relies on a large amount of annotated data. In special scenarios like industry defect detection and medical imaging, it is hard to collect sufficient labeled data all at once. Newly annotated data may arrive incrementally. In practice, we also prefer our target model to improve its capability gradually as new data comes in by quick re-training. This work tackles this problem from a data selection prospective by constraining ourselves to always retrain the target model with a fix amount of data after new data comes in. A variational autoencoder (VAE) and an adversarial network are combined for data selection, achieving fast model retraining. This enables the target model to continually learn from a small training set while not losing the information learned from previous iterations, thus incrementally adapting itself to new-coming data. We validate our framework on the LGG Segmentation dataset for the semantic segmentation task.Clinical relevance- The proposed VAE-based data selection model combined with adversarial training can choose a representative and reliable subset of data for time-efficient medical incremental learning. Users can immediately see the improvement of the medical segmentation model whenever new annotated images are contributed (after a few minutes of model retraining).

MPVF: 4D Medical Image Inpainting by Multi-Pyramid Voxel Flows.

Generatinga detailed 4D medical image usually accompanies with prolonged examination time and increased radiation exposure risk. Modern deep learning solutions have exploited interpolation mechanisms to generate a complete 4D image with fewer 3D volumes. However, existing solutions focus more on 2D-slice information, thus missing the changes on the z-axis. This article tackles the 4D cardiac and lung image interpolation problem by synthesizing 3D volumes directly. Although heart and lung only account for a fraction of chest, they constantly undergo periodical motions of varying magnitudes in contrast to the rest of the chest volume, which is more stationary. This poses big challenges to existing models. In order to handle various magnitudes of motions, we propose a Multi-Pyramid Voxel Flows (MPVF) model that takes multiple multi-scale voxel flows into account. This renders our generation network rich information during interpolation, both globally and regionally. Focusing on periodic medical imaging, MPVF takes the maximal and the minimal phases of an organ motion cycle as inputs and can restore a 3D volume at any time point in between. MPVF is featured by a Bilateral Voxel Flow (BVF) module for generating multi-pyramid voxel flows in an unsupervised manner and a Pyramid Fusion (PyFu) module for fusing multiple pyramids of 3D volumes. The model is validated to outperform the state-of-the-art model in several indices with significantly less synthesis time.

Mobile Charging Strategy for Wireless Rechargeable Sensor Networks.

In a wireless sensor network, the sensing and data transmission for sensors will cause energy depletion, which will lead to the inability to complete the tasks. To solve this problem, wireless rechargeable sensor networks (WRSNs) have been developed to extend the lifetime of the entire network. In WRSNs, a mobile charging robot (MR) is responsible for wireless charging each sensor battery and collecting sensory data from the sensor simultaneously. Thereby, MR needs to traverse along a designed path for all sensors in the WRSNs. In this paper, dual-side charging strategies are proposed for MR traversal planning, which minimize the MR traversal path length, energy consumption, and completion time. Based on MR dual-side charging, neighboring sensors in both sides of a designated path can be wirelessly charged by MR and sensory data sent to MR simultaneously. The constructed path is based on the power diagram according to the remaining power of sensors and distances among sensors in a WRSN. While the power diagram is built, charging strategies with dual-side charging capability are determined accordingly. In addition, a clustering-based approach is proposed to improve minimizing MR moving total distance, saving charging energy and total completion time in a round. Moreover, integrated strategies that apply a clustering-based approach on the dual-side charging strategies are presented in WRSNs. The simulation results show that, no matter with or without clustering, the performances of proposed strategies outperform the baseline strategies in three respects, energy saving, total distance reduced, and completion time reduced for MR in WSRNs.

Dynamic Set Planning for Coordinated Multi-Point in B4G/5G Networks.

Coordinated Multi-Point (CoMP) is an important technique in B4G/5G networks. With CoMP, multiple base stations can be clustered to compose a cooperating set to improve system throughput, especially for the users in cell edges. Existed studies have discussed how to mitigate overloading scenarios and enhance system throughput with CoMP statically. However, static cooperation fixes the set size and neglects the fast-changing of B4G/5G networks. Thus, this paper provides a full study of off-peak hours and overloading scenarios. During off-peak hours, we propose to reduce BSs' transmission power and use the free radio resource to save energy while guaranteeing users' QoS. In addition, if large-scale activities happen with crowds gathering or in peak hours, we dynamically compose the cooperating set based on instant traffic requests to adjust base stations' BSs' transmission power; thus, the system will efficiently offload the traffic to the member cells which have available radio resources in the cooperating set. Experimental results show that the proposed schemes enhance system throughput, radio resource utilization, and energy efficiency, compared to other existing schemes.

Detection of Cytopathic Effects Induced by Influenza, Parainfluenza, and Enterovirus Using Deep Convolution Neural Network.

The isolation of a virus using cell culture to observe its cytopathic effects (CPEs) is the main method for identifying the viruses in clinical specimens. However, the observation of CPEs requires experienced inspectors and excessive time to inspect the cell morphology changes. In this study, we utilized artificial intelligence (AI) to improve the efficiency of virus identification. After some comparisons, we used ResNet-50 as a backbone with single and multi-task learning models to perform deep learning on the CPEs induced by influenza, enterovirus, and parainfluenza. The accuracies of the single and multi-task learning models were 97.78% and 98.25%, respectively. In addition, the multi-task learning model increased the accuracy of the single model from 95.79% to 97.13% when only a few data of the CPEs induced by parainfluenza were provided. We modified both models by inserting a multiplexer and de-multiplexer layer, respectively, to increase the correct rates for known cell lines. In conclusion, we provide a deep learning structure with ResNet-50 and the multi-task learning model and show an excellent performance in identifying virus-induced CPEs.

Smart Interactive Education System Based on Wearable Devices.

Due to the popularity of smart devices, traditional one-way teaching methods might not deeply attract school students' attention, especially for the junior high school students, elementary school students, or even younger students, which is a critical issue for educators. Therefore, we develop an intelligent interactive education system, which leverages wearable devices (smart watches) to accurately capture hand gestures of school students and respond instantly to teachers so as to increase the interaction and attraction of school students in class. In addition, through multiple physical information of school students from the smart watch, it can find out the crux points of the learning process according to the deep data analysis. In this way, it can provide teachers to make instant adjustments and suggest school students to achieve multi-learning and innovative thinking. The system is mainly composed of three components: (1) smart interactive watch; (2) teacher-side smart application (App); and (3) cloud-based analysis system. Specifically, the smart interactive watch is responsible for detecting the physical information and interaction results of school students, and then giving feedback to the teachers. The teacher-side app will provide real-time learning suggestions to adjust the teaching pace to avoid learning disability. The cloud-based analysis system provides intelligent learning advices, academic performance prediction and anomaly learning detection. Through field trials, our system has been verified that can potentially enhance teaching and learning processes for both educators and school students.