Objective.Deep learning has markedly enhanced the performance of sparse-view computed tomography reconstruction. However, the dependence of these methods on supervised training using high-quality paired datasets, and the necessity for retraining under varied physical acquisition conditions, constrain their generalizability across new imaging contexts and settings.Approach.To overcome these limitations, we propose an unsupervised approach grounded in the deep image prior framework. Our approach advances beyond the conventional single noise level input by incorporating multi-level linear diffusion noise, significantly mitigating the risk of overfitting. Furthermore, we embed non-local self-similarity as a deep implicit prior within a self-attention network structure, improving the model\'s capability to identify and utilize repetitive patterns throughout the image. Additionally, leveraging imaging physics, gradient backpropagation is performed between the image domain and projection data space to optimize network weights.Main Results.Evaluations with both simulated and clinical cases demonstrate our method\'s effective zero-shot adaptability across various projection views, highlighting its robustness and flexibility. Additionally, our approach effectively eliminates noise and streak artifacts while significantly restoring intricate image details.Significance. Our method aims to overcome the limitations in current supervised deep learning-based sparse-view CT reconstruction, offering improved generalizability and adaptability without the need for extensive paired training data.

Accurately predicting the state of health (SOH) of lithium-ion batteries is fundamental in estimating their remaining lifespan. Various parameters such as voltage, current, and temperature significantly influence the battery\'s SOH. However, existing data-driven methods necessitate substantial data from the target domain for training, which hampers the assessment of lithium-ion battery health at the initial stage. To address these challenges, this paper introduces the multi-head attention-time convolution network (MHAT-TCN), amalgamating multi-head attention learning with random block dropout techniques. Additionally, it employs grey relational analysis (GRA) to select health indicators (HIs) highly correlated with battery capacity, thereby enhancing the accuracy of the model training. Employing leave-one-out crossvalidation (LOOCV), the MHAT-TCN network is pre-trained using data from batteries of the same model to facilitate comprehensive prediction of the target battery throughout its operational period. Results demonstrate that the MHAT-TCN network trained on HIs outperforms other models, enabling precise predictions across the entire operational period.

Melanoma is a type of skin cancer that poses significant health risks and requires early detection for effective treatment. This study proposing a novel approach that integrates a transformer-based model with hand-crafted texture features and Gray Wolf Optimization, aiming to enhance efficiency of melanoma classification. Preprocessing involves standardizing image dimensions and enhancing image quality through median filtering techniques. Texture features, including GLCM and LBP, are extracted to capture spatial patterns indicative of melanoma. The GWO algorithm is applied to select the most discriminative features. A transformer-based decoder is then employed for classification, leveraging attention mechanisms to capture contextual dependencies. The experimental validation on the HAM10000 dataset and ISIC2019 dataset showcases the effectiveness of the proposed methodology. The transformer-based model, integrated with hand-crafted texture features and guided by Gray Wolf Optimization, achieves outstanding results. The results showed that the proposed method performed well in melanoma detection tasks, achieving an accuracy and F1-score of 99.54% and 99.11% on the HAM10000 dataset, and an accuracy of 99.47%, and F1-score of 99.25% on the ISIC2019 dataset. • We use the concepts of LBP and GLCM to extract features from the skin lesion images. • The Gray Wolf Optimization (GWO) algorithm is employed for feature selection. • A decoder based on Transformers is utilized for melanoma classification.

BACKGROUND: Autism spectrum disorder (ASD) is a neurodevelopmental disorder exhibiting heterogeneous characteristics in patients, including variability in developmental progression and distinct neuroanatomical features influenced by sex and age. Recent advances in deep learning models based on functional connectivity (FC) graphs have produced promising results, but they have focused on generalized global activation patterns and failed to capture specialized regional characteristics and accurately assess disease indications.
METHODS: To overcome these limitations, we propose a novel deep learning method that models FC with multi-head attention, which enables simultaneous modeling of the intricate and variable patterns of brain connectivity associated with ASD, effectively extracting abnormal patterns of brain connectivity. The proposed method not only identifies region-specific correlations but also emphasizes connections at specific, transient time points from diverse perspectives. The extracted FC is transformed into a graph, assigning weighted labels to the edges to reflect the degree of correlation, which is then processed using a graph neural network capable of handling edge labels.
RESULTS: Experiments on the autism brain imaging data exchange (ABIDE) I and II datasets, which include a heterogeneous cohort, showed superior performance over the state-of-the-art methods, improving accuracy by up to 3.7%p. The incorporation of multi-head attention in FC analysis markedly improved the distinction between typical brains and those affected by ASD. Additionally, the ablation study validated diverse brain characteristics in ASD patients across different ages and sexes, offering insightful interpretations.
CONCLUSIONS: These results emphasize the effectiveness of the method in enhancing diagnostic accuracy and its potential in advancing neurological research for ASD diagnosis.

Peptides are pivotal in numerous biological activities by engaging in up to 40 % of protein-protein interactions in many cellular processes. Due to their exceptional specificity and effectiveness, peptides have emerged as promising candidates for drug design. However, accurately predicting protein-peptide binding affinity remains a challenging. Aiming at the problem, we develop a prediction model PepPAP based on convolutional neural network and multi-head attention, which relies solely on sequence features. These features include physicochemical properties, intrinsic disorder, sequence encoding, and especially interface propensity which is extracted from 16,689 non-redundant protein-peptide complexes. Notably, the adopted regression stratification cross-validation scheme proposed in our previous work is beneficial to improve the prediction for the cases with extreme binding affinity values. On three benchmark test datasets: T100, a series of peptides targeting to PDZ domain and CXCR4, PepPAP shows excellent performance, outperforming the existing methods and demonstrating its good generalization ability. Furthermore, PepPAP has good results in binary interaction prediction, and the analysis of the feature space distribution visualization highlights PepPAP\'s effectiveness. To the best of our knowledge, PepPAP is the first sequence-based deep attention model for wide-genome protein-peptide binding affinity prediction, and holds the potential to offer valuable insights for the peptide-based drug design.

The secreted proteins of human body fluid have the potential to be used as biomarkers for diseases. These biomarkers can be used for early diagnosis and risk prediction of diseases, so the study of secreted proteins of human body fluid has great application value. In recent years, the deep-learning-based transformer language model has transferred from the field of natural language processing (NLP) to the field of proteomics, leading to the development of protein language models (PLMs) for protein sequence representation. Here, we propose a deep learning framework called ESM Predict Secreted Proteins (ESMSec) to predict three types of proteins secreted in human body fluid. The ESMSec is based on the ESM2 model and attention architecture. Specifically, the protein sequence data are firstly put into the ESM2 model to extract the feature information from the last hidden layer, and all the input proteins are encoded into a fixed 1000 × 480 matrix. Secondly, multi-head attention with a fully connected neural network is employed as the classifier to perform binary classification according to whether they are secreted into each body fluid. Our experiment utilized three human body fluids that are important and ubiquitous markers. Experimental results show that ESMSec achieved average accuracy of 0.8486, 0.8358, and 0.8325 on the testing datasets for plasma, cerebrospinal fluid (CSF), and seminal fluid, which on average outperform the state-of-the-art (SOTA) methods. The outstanding performance results of ESMSec demonstrate that the ESM can improve the prediction performance of the model and has great potential to screen the secretion information of human body fluid proteins.

BACKGROUND: Accurately identifying the risk level of drug combinations is of great significance in investigating the mechanisms of combination medication and adverse reactions. Most existing methods can only predict whether there is an interaction between two drugs, but cannot directly determine their accurate risk level.
METHODS: In this study, we propose a multi-class drug combination risk prediction model named AERGCN-DDI, utilizing a relational graph convolutional network with a multi-head attention mechanism. Drug-drug interaction events with varying risk levels are modeled as a heterogeneous information graph. Attribute features of drug nodes and links are learned based on compound chemical structure information. Finally, the AERGCN-DDI model is proposed to predict drug combination risk level based on heterogenous graph neural network and multi-head attention modules.
RESULTS: To evaluate the effectiveness of the proposed method, five-fold cross-validation and ablation study were conducted. Furthermore, we compared its predictive performance with baseline models and other state-of-the-art methods on two benchmark datasets. Empirical studies demonstrated the superior performances of AERGCN-DDI.
CONCLUSIONS: AERGCN-DDI emerges as a valuable tool for predicting the risk levels of drug combinations, thereby aiding in clinical medication decision-making, mitigating severe drug side effects, and enhancing patient clinical prognosis.

BACKGROUND: Drug-drug interaction events influence the effectiveness of drug combinations and can lead to unexpected side effects or exacerbate underlying diseases, jeopardizing patient prognosis. Most existing methods are restricted to predicting whether two drugs interact or the type of drug-drug interactions, while very few studies endeavor to predict the specific risk levels of side effects of drug combinations.
METHODS: In this study, we propose MathEagle, a novel approach to predict accurate risk levels of drug combinations based on multi-head attention and heterogeneous attribute graph learning. Initially, we model drugs and three distinct risk levels between drugs as a heterogeneous information graph. Subsequently, behavioral and chemical structure features of drugs are utilized by message passing neural networks and graph embedding algorithms, respectively. Ultimately, MathEagle employs heterogeneous graph convolution and multi-head attention mechanisms to learn efficient latent representations of drug nodes and estimates the risk levels of pairwise drugs in an end-to-end manner.
RESULTS: To assess the effectiveness and robustness of the model, five-fold cross-validation, ablation experiments, and case studies were conducted. MathEagle achieved an accuracy of 85.85 % and an AUC of 0.9701 on the drug risk level prediction task and is superior to all comparative models. The MathEagle predictor is freely accessible at http://120.77.11.78/MathEagle/.
CONCLUSIONS: The experimental results indicate that MathEagle can function as an effective tool for predicting accurate risk of drug combinations, aiding in guiding clinical medication, and enhancing patient outcomes.

Detecting cracks in the pavement is a vital component of ensuring road safety. Since manual identification of these cracks can be time-consuming, an automated method is needed to speed up this process. However, creating such a system is challenging due to factors including crack variability, variations in pavement materials, and the occurrence of miscellaneous objects and anomalies on the pavement. Motivated by the latest progress in deep learning applied to computer vision, we propose an effective U-Net-shaped model named DepthCrackNet. Our model employs the Double Convolution Encoder (DCE), composed of a sequence of convolution layers, for robust feature extraction while keeping parameters optimally efficient. We have incorporated the TriInput Multi-Head Spatial Attention (TMSA) module into our model; in this module, each head operates independently, capturing various spatial relationships and boosting the extraction of rich contextual information. Furthermore, DepthCrackNet employs the Spatial Depth Enhancer (SDE) module, specifically designed to augment the feature extraction capabilities of our segmentation model. The performance of the DepthCrackNet was evaluated on two public crack datasets: Crack500 and DeepCrack. In our experimental studies, the network achieved mIoU scores of 77.0% and 83.9% with the Crack500 and DeepCrack datasets, respectively.

Accurate and fast recognition of vehicle license plates from natural scene images is a crucial and challenging task. Existing methods can recognize license plates in simple scenarios, but their performance degrades significantly in complex environments. A novel license plate detection and recognition model YOLOv5-PDLPR is proposed, which employs YOLOv5 target detection algorithm in the license plate detection part and uses the PDLPR algorithm proposed in this paper in the license plate recognition part. The PDLPR algorithm is mainly designed as follows: (1) A Multi-Head Attention mechanism is used to accurately recognize individual characters. (2) A global feature extractor network is designed to improve the completeness of the network for feature extraction. (3) The latest parallel decoder architecture is adopted to improve the inference efficiency. The experimental results show that the proposed algorithm has better accuracy and speed than the comparison algorithms, can achieve real-time recognition, and has high efficiency and robustness in complex scenes.