Search

Aiming to address the problem of low classification accuracy caused by the different shapes of meniscus tears in the computer-aided diagnosis (CAD) system for meniscus, a multidimensional information fusion network (MDIFNet) model for menissus tear classification was proposed. Firstly, a convolutional neural network (CNN) architecture consisting of four sub-networks was used to obtain meniscus feature information from different perspectives and dimensions. Simultaneously, multi-scale attention mechanism was proposed to enrich fine-grained features. Finally, a multi kernel model based on support vector machines (SVM) was constructed as the final classifier. The experimental results on the MRNet dataset show that the proposed method has a meniscal tear classification accuracy of 0.782, which has promotion compared to the existing state-of-the-art meniscus tear classification methods based on deep learning.

Functional connectome has revealed remarkable potential in the diagnosis of neurological disorders, e.g. autism spectrum disorder. However, existing studies have primarily focused on a single connectivity pattern, such as full correlation, partial correlation, or causality. Such an approach fails in discovering the potential complementary topology information of FCNs at different connection patterns, resulting in lower diagnostic performance. Consequently, toward an accurate autism spectrum disorder diagnosis, a straightforward ambition is to combine the multiple connectivity patterns for the diagnosis of neurological disorders. To this end, we conduct functional magnetic resonance imaging data to construct multiple brain networks with different connectivity patterns and employ kernel combination techniques to fuse information from different brain connectivity patterns for autism diagnosis. To verify the effectiveness of our approach, we assess the performance of the proposed method on the Autism Brain Imaging Data Exchange dataset for diagnosing autism spectrum disorder. The experimental findings demonstrate that our method achieves precise autism spectrum disorder diagnosis with exceptional accuracy (91.30%), sensitivity (91.48%), and specificity (91.11%)., (© The Author(s) 2023. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permission@oup.com.)

In this paper, a novel approach to single image super-resolution based on the multi-kernel regression is presented. This approach focuses on learning the map between the space of high-resolution image patches and the space of blurred high-resolution image patches, which are the interpolation results generated from the corresponding low-resolution images. Kernel regression based super-resolution approaches are promising, but kernel selection is a critical problem. In order to avoid demanding and time-consuming cross validation for kernel selection, we propose multi-kernel regression (MKR) model for image Super-Resolution (SR). Considering the multi-kernel regression model is prohibited when the training data is large-scale, we further propose a prototype MKR algorithm which can reduce the computational complexity. Extensive experimental results demonstrate that our approach is effective and achieves a high quality performance in comparison with other super-resolution methods. [ABSTRACT FROM AUTHOR]

The prediction of novel drug-target interactions (DTIs) has intrinsic significance in drug discovery research. Wet-lab experiments of DTIs are laborious and expensive; computational methods can help minimize the complexity of identifying unknown DTIs and accelerate the drug repositioning process. Nowadays, the number of drug-target features and their interactions regularly increases, disabling traditional computational methods' prediction and analyzing ability. Therefore, developing a new robust model to derive the reduced features for effective prediction is important. Further, accurate interactions also depend on the negative drug-target pairs, and it is worthwhile to build a technique to generate perfect negative pairs. To this end, we propose a new multi-label approach, called idti-MLKdr, by introducing multi-kernel learning (MKL) based SVM for DTIs prediction with various dimensionality reduction techniques. First, we have extracted the drug-target features from chemical structures and protein sequences, applying different feature extraction methods. A new technique has been developed to construct the negative drug-target pairs based on drug-drug (or protein-protein) similarity scores. Then, three-dimensionality reduction techniques have been applied to the extracted drug-target features. Finally, we trained a multi kernel-based learner together with the reduced features and combined their prediction scores to show the final results. In this experiment, we considered auROC as an evaluation metric. The proposed method has been compared with the various existing methods under five-fold cross-validation, and the experimental results indicated that idti-MLKdr attains the best auROC for predicting DTIs. We believe that improved prediction performance will motivate the researchers for further drug development. [Display omitted] • Computational model idti-MLKdr is proposed for predicting Drug-Target Interactions. • FP2, AAC, DC and TC descriptors are used for extracting Drug-target features. • CluMS technique is proposed for resolving class imbalance problem, and three DR techniques are utilized to manage the high dimensionality. • Multi-kernel Learning (MKL) based SVM algorithm is used as a classifier. • Achieves the best prediction performance and can effectively predict the potential DTIs. [ABSTRACT FROM AUTHOR]