International Journal of Neural Systems

In responding to the calls for revisiting the role that hippocampus (HIP) plays in semantic memory retrieval, this study used functional neuroimaging-based connectivity technique to elucidate the functional brain network involved in retrieving the correct and incorrect science-related semantic memories. Unlike episodic memory retrieval, the 40 scientific concepts learned during middle and high school were selected to assess 46 science majors’ semantic memory retrieval and correctness monitoring, which requires neither the support of spatial information nor events to retrieve the memory. Our results demonstrated that HIP was significantly and robustly engaged in the semantic memory retrieval of correct scientific concepts than incorrect ones. Importantly, the Granger causality analysis indicated that effective connectivity of $\mathrm{\text{INS}}\to \mathrm{\text{HIP}}$ and $\mathrm{\text{MTG}}\to \mathrm{\text{HIP}}$ was shared by the semantic memory retrieval of both correct and incorrect scientific concepts. On the other hand, the strengths of connectivity in the $\mathrm{\text{MTG}}\to \mathrm{\text{HIP}}$ and $\mathrm{\text{INS}}\to \mathrm{\text{ACC}}\to \mathrm{\text{HIP}}$ brain networks appeared more pronounced during the processing of correct scientific concepts than of incorrect ones. The shared hippocampal networks highlight the role of the HIP as a hub to coordinate the INS, ACC, and MTG, in turn, support the semantic memory retrieval of scientific concepts.

Swarm Learning (SL) is a promising approach to perform the distributed and collaborative model training without any central server. However, data sensitivity is the main concern for privacy when collaborative training requires data sharing. A neural network, especially Generative Adversarial Network (GAN), is able to reproduce the original data from model parameters, i.e. gradient leakage problem. To solve this problem, SL provides a framework for secure aggregation using blockchain methods. In this paper, we consider the scenario of compromised and malicious participants in the SL environment, where a participant can manipulate the privacy of other participant in collaborative training. We propose a method, Swarm-FHE, Swarm Learning with Fully Homomorphic Encryption (FHE), to encrypt the model parameters before sharing with the participants which are registered and authenticated by blockchain technology. Each participant shares the encrypted parameters (i.e. ciphertexts) with other participants in SL training. We evaluate our method with training of the convolutional neural networks on the CIFAR-10 and MNIST datasets. On the basis of a considerable number of experiments and results with different hyperparameter settings, our method performs better as compared to other existing methods.

Radiation therapy is a fundamental cancer treatment in the clinic. However, to satisfy the clinical requirements, radiologists have to iteratively adjust the radiotherapy plan based on experience, causing it extremely subjective and time-consuming to obtain a clinically acceptable plan. To this end, we introduce a transformer-embedded multi-task dose prediction (TransMTDP) network to automatically predict the dose distribution in radiotherapy. Specifically, to achieve more stable and accurate dose predictions, three highly correlated tasks are included in our TransMTDP network, i.e. a main dose prediction task to provide each pixel with a fine-grained dose value, an auxiliary isodose lines prediction task to produce coarse-grained dose ranges, and an auxiliary gradient prediction task to learn subtle gradient information such as radiation patterns and edges in the dose maps. The three correlated tasks are integrated through a shared encoder, following the multi-task learning strategy. To strengthen the connection of the output layers for different tasks, we further use two additional constraints, i.e. isodose consistency loss and gradient consistency loss, to reinforce the match between the dose distribution features generated by the auxiliary tasks and the main task. Additionally, considering many organs in the human body are symmetrical and the dose maps present abundant global features, we embed the transformer into our framework to capture the long-range dependencies of the dose maps. Evaluated on an in-house rectum cancer dataset and a public head and neck cancer dataset, our method gains superior performance compared with the state-of-the-art ones. Code is available at https://github.com/luuuwen/TransMTDP.

LSTM-SNP model is a recently developed long short-term memory (LSTM) network, which is inspired from the mechanisms of spiking neural P (SNP) systems. In this paper, LSTM-SNP is utilized to propose a novel model for aspect-level sentiment analysis, termed as ALS model. The LSTM-SNP model has three gates: reset gate, consumption gate and generation gate. Moreover, attention mechanism is integrated with LSTM-SNP model. The ALS model can better capture the sentiment features in the text to compute the correlation between context and aspect words. To validate the effectiveness of the ALS model for aspect-level sentiment analysis, comparison experiments with 17 baseline models are conducted on three real-life data sets. The experimental results demonstrate that the ALS model has a simpler structure and can achieve better performance compared to these baseline models.

Parkinson’s Disease (PD) is the second most prevalent neurodegenerative disorder among adults. Although its triggers are still not clear, they may be due to a combination of different types of biomarkers measured through medical imaging, metabolomics, proteomics or genetics, among others. In this context, we have proposed a Computer-Aided Diagnosis (CAD) system that combines structural and functional imaging data from subjects in Parkinson’s Progression Markers Initiative dataset by means of an Ensemble Learning methodology trained to identify and penalize input sources with low classification rates and/ or high-variability. This proposal improves results published in recent years and provides an accurate solution not only from the point of view of image preprocessing (including a comparison between different intensity preservation techniques), but also in terms of dimensionality reduction methods (Isomap). In addition, we have also introduced a bagging classification schema for scenarios with unbalanced data.

As shown by our results, the CAD proposal is able to detect PD with $96.48\%$ of balanced accuracy, and opens up the possibility of combining any number of input data sources relevant for PD.

Deep learning-based epileptic seizure recognition via electroencephalogram signals has shown considerable potential for clinical practice. Although deep learning algorithms can enhance epilepsy identification accuracy compared with classical machine learning techniques, classifying epileptic activities based on the association between multichannel signals in electroencephalogram recordings is still challenging in automated seizure classification from electroencephalogram signals. Furthermore, the performance of generalization is hardly maintained by the fact that existing deep learning models were constructed using just one architecture. This study focuses on addressing this challenge using a hybrid framework. Alternatively put, a hybrid deep learning model, which is based on the ground-breaking graph neural network and transformer architectures, was proposed. The proposed deep architecture consists of a graph model to discover the inner relationship between multichannel signals and a transformer to reveal the heterogeneous associations between the channels. To evaluate the performance of the proposed approach, the comparison experiments were conducted on a publicly available dataset between the state-of-the-art algorithms and ours. Experimental results demonstrate that the proposed method is a potentially valuable instrument for epoch-based epileptic EEG classification.