The inherent characteristics of high-dimensional feature redundancy of biomedical data lead to the "curse of dimensionality" in bioinformatics, which brings new challenges to feature selection problems. Recently, the two-stage approach combining the filter and wrapper methods has become popular for feature selection tasks. However, these two-stage or previous one-stage algorithms suffer from blindness in the setting of thresholds, and the search methods tend to fall into local optimum solutions. To this end, we propose a three-stage feature selection method that combines ReliefF and Particle swarm optimization as a specific case, called TS-RePSO, including the filter stage, grouping stage, and wrapper stage. Specifically, in the filter stage, ReliefF is utilized to compute the weights of the features and sort them in descending order. In the grouping stage, the ranked features are grouped based on the density equalization strategy so that the weight of groups in all groups is equal. In the wrapper stage, the proposed grouping PSO is employed to search for the grouped features and select them according to the in-group and out-group evaluation strategies. Extensive experiments are conducted on 5 benchmark datasets and 6 real-world datasets, and experiment results show that the proposed method achieves the best performance.

Clinical research highlights the interaction between human-residing microorganisms and drug efficacy/toxicity, making microbes innovative targets for antibacterial drug development. The growing availability of microbiome and drug data offers opportunities to use machine learning to predict microbedrug associations, enhancing research and development. Previous computational approaches typically learned microbe representations from the entire graph of microbe-drug associations. Drugs exhibit different mechanisms of action for various microbes, while learning drug representations remains static and agnostic to different microorganisms. When the same microbe interacts with different drugs, it becomes crucial to discern relevant contextual information. With this in mind, we introduce a novel method, MDPAGCN, which utilizes a dual-attention GCN to extract contextual information from microbe-drug pairs within larger microbe-drug association graphs. We then employ a graph convolutional network to learn feature representations for specific microbe-drug subgraphs. Treating microbe-drug associations as a graph classification task, we generate a fixed-size matrix that integrates graph representations using an attention pooling layer, and the graphs are classified using a fully connected module. Experimental results under different cross-validation settings show that our proposed method outperforms seven benchmark methods. A case study on the prediction of microbe-drug associations further demonstrates the effectiveness of our proposed MDPAGCN method.

Accurate segmentation of lesions in medical images is crucial for early diagnosis and treatment, significantly improving patient survival rates. However, the inherent characteristics of medical imaging render precise lesion segmentation a highly challenging task. Traditional manual segmentation methods are time-consuming and heavily dependent on expert knowledge, while the standard convolutions used in the U-Net model fail to capture sufficient contextual information. To address these challenges, we propose an enhanced context-separable attention U-Net model for lesion segmentation in medical images. This model introduces Separable Attention (SA) block and Context Attention (CA) block to extract and integrate local and global contextual information, thereby enhancing the model’s feature extraction capabilities. The proposed method increases the model’s receptive field while reducing the number of parameters, incorporating attention mechanisms to improve segmentation accuracy and efficiency. Experimental results across various datasets demonstrate that the proposed model outperforms the original U-Net in terms of segmentation accuracy and efficiency, achieving higher mean Intersection over Union values in lesion segmentation while reducing the model’s parameters.

To accurately detect and track the thyroid nodules in a video is a crucial step in the thyroid screening for identification of benign and malignant nodules in computer-aided diagnosis (CAD) systems. Most existing methods just perform excellent on static frames selected manually from ultrasound videos. However, manual acquisition is labor-intensive work. To make the thyroid screening process in a more natural way with less labor operations, we develop a well-designed framework suitable for practical applications for thyroid nodule detection in ultrasound videos. Particularly, in order to make full use of the characteristics of thyroid videos, we propose a novel post-processing approach, called Cache-Track, which exploits the contextual relation among video frames to propagate the detection results into adjacent frames to refine the detection results. Additionally, our method can not only detect and count thyroid nodules, but also track and monitor surrounding tissues, which can greatly reduce the labor work and achieve computer-aided diagnosis. Experimental results show that our method performs better in balancing accuracy and speed.

Fingerprints are widely used for biometric recognition. However, many spoofing attacks based on an artificially made fingerprint occur. In this study, the authors propose an approach to detect fingerprint liveness which uses the guided filtering and hybrid image analysis. This study deals with the problem of ignoring the contribution that is brought by the sharp features when analysing the denoised image. The method described utilises both the enhanced sharp features and denoised features from the hybrid images to get better results. The input fingerprint is pre‐processed by region of interest extraction and then is filtered by a guidance image for obtaining the denoised image. Then, histogram equalisation is introduced to eliminate the impact of illumination condition. The authors extract the co‐occurrence of adjacent local binary pattern features from both the cropped images and the denoised images. Whilst concatenating both the features together to form a long feature, t‐Distributed Stochastic Neighbour Embedding is applied to reduce the data dimension. The authors consider the fingerprint liveness detection as a two‐class classification problem and use support vector machine with radial basis function kernel to solve this problem. The authors evaluate the experiments on three benchmark data sets. Experimental results demonstrate that the accuracy of the proposed method can outperform most of the state‐of‐art methods.