Focal liver lesion diagnosis with deep learning and multistage CT imaging.

Diagnosing liver lesions is crucial for treatment choices and patient outcomes. This study develops an automatic diagnosis system for liver lesions using multiphase enhanced computed tomography (CT). A total of 4039 patients from six data centers are enrolled to develop Liver Lesion Network (LiLNet). LiLNet identifies focal liver lesions, including hepatocellular carcinoma (HCC), intrahepatic cholangiocarcinoma (ICC), metastatic tumors (MET), focal nodular hyperplasia (FNH), hemangioma (HEM), and cysts (CYST). Validated in four external centers and clinically verified in two hospitals, LiLNet achieves an accuracy (ACC) of 94.7% and an area under the curve (AUC) of 97.2% for benign and malignant tumors. For HCC, ICC, and MET, the ACC is 88.7% with an AUC of 95.6%. For FNH, HEM, and CYST, the ACC is 88.6% with an AUC of 95.9%. LiLNet can aid in clinical diagnosis, especially in regions with a shortage of radiologists.

Enhanced Multimodal Brain Tumor Classification in MR Images using 2D ResNet as backbone with Explicit Tumor Size Information.

It's a major public health problem of global concern that malignant gliomas tend to grow rapidly and infiltrate surrounding tissues. Accurate grading of the tumor can determine the degree of malignancy to formulate the best treatment plan, which can eliminate the tumor or limit widespread metastasis of the tumor, saving the patient's life and improving their prognosis. To more accurately predict the grading of gliomas, we proposed a novel method of combining the advantages of 2D and 3D Convolutional Neural Networks for tumor grading by multimodality on Magnetic Resonance Imaging. The core of the innovation lies in our combination of tumor 3D information extracted from multimodal data with those obtained from a 2D ResNet50 architecture. It solves both the lack of temporal-spatial information provided by 3D imaging in 2D convolutional neural networks and avoids more noise from too much information in 3D convolutional neural networks, which causes serious overfitting problems. Incorporating explicit tumor 3D information, such as tumor volume and surface area, enhances the grading model's performance and addresses the limitations of both approaches. By fusing information from multiple modalities, the model achieves a more precise and accurate characterization of tumors. The model I s trained and evaluated using two publicly available brain glioma datasets, achieving an AUC of 0.9684 on the validation set. The model's interpretability is enhanced through heatmaps, which highlight the tumor region. The proposed method holds promise for clinical application in tumor grading and contributes to the field of medical diagnostics for prediction.

Deep-Reinforcement-Learning-Based Joint Energy Replenishment and Data Collection Scheme for WRSN.

With the emergence of wireless rechargeable sensor networks (WRSNs), the possibility of wirelessly recharging nodes using mobile charging vehicles (MCVs) has become a reality. However, existing approaches overlook the effective integration of node energy replenishment and mobile data collection processes. In this paper, we propose a joint energy replenishment and data collection scheme (D-JERDG) for WRSNs based on deep reinforcement learning. By capitalizing on the high mobility of unmanned aerial vehicles (UAVs), D-JERDG enables continuous visits to the cluster head nodes in each cluster, facilitating data collection and range-based charging. First, D-JERDG utilizes the K-means algorithm to partition the network into multiple clusters, and a cluster head selection algorithm is proposed based on an improved dynamic routing protocol, which elects cluster head nodes based on the remaining energy and geographical location of the cluster member nodes. Afterward, the simulated annealing (SA) algorithm determines the shortest flight path. Subsequently, the DRL model multiobjective deep deterministic policy gradient (MODDPG) is employed to control and optimize the UAV instantaneous heading and speed, effectively planning UAV hover points. By redesigning the reward function, joint optimization of multiple objectives such as node death rate, UAV throughput, and average flight energy consumption is achieved. Extensive simulation results show that the proposed D-JERDG achieves joint optimization of multiple objectives and exhibits significant advantages over the baseline in terms of throughput, time utilization, and charging cost, among other indicators.

Deep Reinforcement Learning-Based Online One-to-Multiple Charging Scheme in Wireless Rechargeable Sensor Network.

Wireless rechargeable sensor networks (WRSN) have been emerging as an effective solution to the energy constraint problem of wireless sensor networks (WSN). However, most of the existing charging schemes use Mobile Charging (MC) to charge nodes one-to-one and do not optimize MC scheduling from a more comprehensive perspective, leading to difficulties in meeting the huge energy demand of large-scale WSNs; therefore, one-to-multiple charging which can charge multiple nodes simultaneously may be a more reasonable choice. To achieve timely and efficient energy replenishment for large-scale WSN, we propose an online one-to-multiple charging scheme based on Deep Reinforcement Learning, which utilizes Double Dueling DQN (3DQN) to jointly optimize the scheduling of both the charging sequence of MC and the charging amount of nodes. The scheme cellularizes the whole network based on the effective charging distance of MC and uses 3DQN to determine the optimal charging cell sequence with the objective of minimizing dead nodes and adjusting the charging amount of each cell being recharged according to the nodes' energy demand in the cell, the network survival time, and MC's residual energy. To obtain better performance and timeliness to adapt to the varying environments, our scheme further utilizes Dueling DQN to improve the stability of training and uses Double DQN to reduce overestimation. Extensive simulation experiments show that our proposed scheme achieves better charging performance compared with several existing typical works, and it has significant advantages in terms of reducing node dead ratio and charging latency.

A community-based event delivery protocol in publish/subscribe systems for delay tolerant sensor networks.

The basic operation of a Delay Tolerant Sensor Network (DTSN) is to finish pervasive data gathering in networks with intermittent connectivity, while the publish/subscribe (Pub/Sub for short) paradigm is used to deliver events from a source to interested clients in an asynchronous way. Recently, extension of Pub/Sub systems in DTSNs has become a promising research topic. However, due to the unique frequent partitioning characteristic of DTSNs, extension of a Pub/Sub system in a DTSN is a considerably difficult and challenging problem, and there are no good solutions to this problem in published works. To ad apt Pub/Sub systems to DTSNs, we propose CED, a community-based event delivery protocol. In our design, event delivery is based on several unchanged communities, which are formed by sensor nodes in the network according to their connectivity. CED consists of two components: event delivery and queue management. In event delivery, events in a community are delivered to mobile subscribers once a subscriber comes into the community, for improving the data delivery ratio. The queue management employs both the event successful delivery time and the event survival time to decide whether an event should be delivered or dropped for minimizing the transmission overhead. The effectiveness of CED is demonstrated through comprehensive simulation studies.