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.

Energy problem is one of the most important challenges in the application of sensor networks. With the development of wireless charging technology and intelligent mobile charger (MC), the energy problem can be solved by wireless charging strategy. In the practical application of Wireless Rechargeable Sensor Networks (WRSNs), the energy consumption rate of nodes is dynamically changed due to many uncertainties such as the death and different transmission tasks of sensor nodes. However, existing works focus on on-demand schemes, which not fully consider real-time global charging scheduling. In this paper, a novel Dynamic Charging Scheme (DCS) in WRSN based on Actor-Critic Reinforcement Learning (ACRL) algorithm is proposed. In the ACRL, we introduce Gated Recurrent Units (GRU) to capture the relationships of charging actions in time sequence. Using the Actor network with one GRU layer, we can pick up an optimal or near-optimal sensor node from candidates as the next charging target more quickly and speed up the training of the model. Meanwhile, we take the tour length and the number of dead nodes as the reward signal. Actor and Critic networks are updated by the error criterion function of R and V. Compared with current on-demand charging scheduling algorithms, extensive simulations show that the proposed ACRL algorithm surpasses heuristic algorithms such as the Greedy, DP, NJNP and TSCA in the average lifetime and tour length, especially against the size and complexity increasing of WRSNs.

The expression status of programmed cell death protein 1 (PD-1) in patients with hepatocellular carcinoma (HCC) is associated with the checkpoint blockade treatment responses of PD-1/PD-L1. Thus, accurately and preoperatively identifying the status of PD-1 has great clinical implications for constructing personalized treatment strategies. To investigate the preoperative predictive value of the transformer-based model for identifying the status of PD-1 expression, 93 HCC patients with 75 training cohorts (2859 images) and 18 testing cohorts (670 images) were included. We propose a transformer-based network architecture, ResTransNet, that efficiently employs convolutional neural networks (CNNs) and self-attention mechanisms to automatically acquire a persuasive feature to obtain a prediction score using a nonlinear classifier. The area under the curve, receiver operating characteristic curve, and decision curves were applied to evaluate the prediction model’s performance. Then, Kaplan–Meier survival analyses were applied to evaluate the overall survival (OS) and recurrence-free survival (RFS) in PD-1-positive and PD-1-negative patients. The proposed transformer-based model obtained an accuracy of 88.2% with a sensitivity of 88.5%, a specificity of 88.9%, and an area under the curve of 91.1% in the testing cohort.

In heterogeneous wireless sensor networks (HWSNs), heterogeneous sensors may follow various data-generating distributions, which makes data collection a very challenging task. Although mobile sinks (MSs) are widely used to collect data from wireless sensors, existing MS-assisted approaches are often based on the assumption of synchronized data, for example, all sensors generate data at the same time, in which data are considered delay-tolerant and -sensitive data according to delay limits, while the generation time of data is ignored. This article focuses on unsynchronized data collection for HWSNs, in which unsynchronized data generation of sensors is allowed as real as actual monitoring applications. First, to reflect the timeliness of data, we use a rigid collection window to represent the lifetime of sensing data to refine the visiting time of the MS. Second, a graph attention network (GAT) structure is adopted to describe node locations, accessible paths, and data with collection windows for path planning. Third, a new deep reinforcement learning (DRL)-based MS path planning (MSPP) framework is proposed to tackle the path of the MS by minimizing total energy cost while satisfying data lifetime constraints. MSPP first uses the Target Selector module to plan the moving targets and adopts the MS Controller module to control MS mobility for achieving fast convergence and better optimality. Finally, extensive simulations show that our scheme provides explicit data collection guarantees and minimum energy consumption.

In a convolutional neural network (CNN), dropout cannot work well because dropped information is not entirely obscured in convolutional layers where features are correlated spatially. Except for randomly discarding regions or channels, many approaches try to overcome this defect by dropping influential units. In this paper, we propose a non-random dropout method named FocusedDropout, aiming to make the network focus more on the target. In FocusedDropout, we use a simple but effective method to search for the target-related features, retain these features and discard others, which is contrary to the existing methods. We find that this novel method can improve network performance by making the network more target focused. Additionally, increasing the weight decay while using FocusedDropout can avoid overfitting and increase accuracy. Experimental results show that with a slight cost, 10% of batches employing FocusedDropout, can produce a nice performance boost over the baselines on multiple datasets of classification, including CIFAR10, CIFAR100 and Tiny ImageNet, and has a good versatility for different CNN models.

In vehicular communication, roadside infrastructure, such as WiFi APs, often requires a large amount of investment. In this paper, we propose the idea of Mobile Vehicular Offloading (MoVeOff), which doesn’t require extra investment, but allows data transfer from on-board devices to mobile devices of drivers and passengers, for uploading to the Internet in the future. When they arrive at their homes, offices, or other places where WiFi connection is available, vehicular data will be offloaded in a delay-tolerant manner, by the ferrying of mobile devices. We build a realistic system to investigate the regularities in people’s daily travelling and WiFi usage, analyze individual mobility, and establish a Long Short Term Memory (LSTM) model to predict one’s future WiFi connectivity. Moreover, a mobility-aware routing scheme is developed for inter-vehicle communication. Each vehicle broadcasts its expected offloading probability and delay, so that messages are dynamically delivered to the nodes, whose offloading can guarantee delay and delivery ratio bounds required by applications. Thus, our scheme overcomes traditional opportunistic forwarding, and introduces predictable ferrying guaranteed by individual mobility. Through system running and simulations, we demonstrate that our scheme provides extra and stable offloading service for delay-tolerant data in the areas with sparse roadside infrastructures.