Intracranial aneurysm (IA) is a vascular disease of the brain arteries caused by pathological dilation, which can result in subarachnoid hemorrhage if ruptured. Automatically classification and segmentation intracranial aneurysms are essential for their diagnosis treatment. However, majority current research focused on two-dimensional images, ignoring 3D spatial information that also critical. In this work, we propose novel dual-branch fusion network called Point Cloud Multi-View Medical...

Intensity-modulated radiotherapy (IMRT) is one of the most popular techniques for cancer treatment. However, existing IMRT planning methods can only generate solution at a time and, consequently, medical physicists should perform process many times to obtain diverse solutions meet requirement clinical case. Meanwhile, multiobjective evolutionary algorithms (MOEAs) have not been fully exploited in since they are ineffective optimizing large number discrete variables IMRT. To bridge gap, this...

Interleukin-6 (IL-6) is a potent glycoprotein that plays crucial role in regulating innate and adaptive immunity, as well metabolism. The expression release of IL-6 are closely correlated with the severity various diseases. IL-6-inducing peptides critical for development immunotherapy diagnostic biomarkers some Most existing methods predicting IL-6-induced use traditional machine learning methods, whose feature selection based on prior knowledge. In addition, none these take into account...

Single-cell RNA sequencing (scRNA-seq) enables the reconstruction of cell type-specific gene regulatory networks (GRNs), offering detailed insights into regulation at high resolution. While graph neural have become widely used for GRN inference, their message-passing mechanisms are often limited by issues such as over-smoothing and over-squashing, which hinder preservation essential network structure. To address these challenges, we propose a novel transformer-based model, AttentionGRN,...

Lots of experimental studies have revealed the significant associations between lncRNAs and diseases. Identifying accurate will provide a new perspective for disease therapy. Calculation-based methods been developed to solve these problems, but some limitations. In this paper, we proposed an method, named MLGCNET, discover potential lncRNA-disease associations. Firstly, reconstructed similarity networks both diseases using top k similar information, constructed heterogeneous network (LDN)....

Circular RNAs (circRNAs) are covalently closed single-stranded RNA molecules, which have many biological functions. Previous experiments shown that circRNAs involved in numerous processes, especially regulatory It has also been found associated with complex diseases of human beings. Therefore, predicting the associations circRNA disease (called circRNA-disease associations) is useful for prevention, diagnosis and treatment. In this work, we propose a novel computational approach called GGCDA...

Abstract The inference of gene regulatory networks (GRNs) from expression profiles has been a key issue in systems biology, prompting many researchers to develop diverse computational methods. However, most these methods do not reconstruct directed GRNs with types because the lack benchmark datasets or defects Here, we collect and propose deep learning-based model, DeepFGRN, for reconstructing fine (FGRNs) both regulation directions. In addition, real species are always large graphs...

Abstract Background Circular RNAs (circRNAs) are a class of single-stranded RNA molecules with closed-loop structure. A growing body research has shown that circRNAs closely related to the development diseases. Because biological experiments verify circRNA-disease associations time-consuming and wasteful resources, it is necessary propose reliable computational method predict potential candidate for make them more efficient. Results In this paper, we double matrix completion (DMCCDA)...

An emerging type of therapeutic agent, anticancer peptides (ACPs), has attracted attention because its lower risk toxic side effects. However process identifying ACPs using experimental methods is both time-consuming and laborious. In this study, we developed a new efficient algorithm that predicts by fusing multi-view features based on dual-channel deep neural network ensemble model. the model, one channel used convolutional CNN to automatically extract potential spatial sequence. Another...

Radiotherapy plays an important role in controlling the local recurrence of esophageal cancer after radical surgery. Segmentation clinical target volume is a key step radiotherapy treatment planning, but it time-consuming and operator-dependent. This paper introduces deep dilated convolutional U-network to achieve fast accurate auto-segmentation The U-network, which integrates advantages convolution end-to-end architecture that enables rapid training testing. A module for extracting...

Medical image segmentation plays a crucial role in clinical diagnosis, treatment planning, and disease monitoring. The automatic method based on deep learning has developed rapidly, with results comparable to experts for large objects, but the accuracy small objects is still unsatisfactory. Current methods find it difficult extract multiple scale features of medical images, leading an insufficient detection capability smaller objects. In this paper, we propose context feature fusion...

Antiviral peptides (AVPs) are widely found in animals and plants, with high specificity strong sensitivity to drug-resistant viruses. However, due the great heterogeneity of different viruses, most AVPs have specific antiviral activities. Therefore, it is necessary identify activities on virus types. Most existing studies only AVPs, a few identifying subclasses by training multiple binary classifiers. We develop two-stage prediction tool named FFMAVP that can simultaneously predict their...

The multi-objective optimization of inverse planning based on the Pareto solution set, according to character in accurate radiotherapy, was studied this paper. Firstly, clinical requirements a treatment plan were transformed into problem with multiple constraints. Then, fast and elitist Non-dominated Sorting Genetic Algorithm (NSGA- II) introduced optimize problem. A example tested using method. results show that an obtained set non-dominated solutions uniformly distributed corresponding...

Gene regulatory networks (GRNs) are crucial for understanding organismal molecular mechanisms and processes. Construction of GRN in the epithelioma papulosum cyprini (EPC) cells cyprinid fish by spring viremia carp virus (SVCV) infection helps understand immune that enhance survival capabilities fish. Although many computational methods have been used to infer GRNs, specialized approaches predicting EPC following SVCV lacking. In addition, most existing focus primarily on gene expression...

Abstract Intensity-modulated radiotherapy (IMRT) is one of the most applied techniques for cancer treatment. The fluence map optimization an essential part IMRT plan designing, which has a significant impact on treatment effect. In fact, planing inverse multi-objective problem. Existing approaches solving problem (FMOP) obtain satisfied via trying different coupling weights, process needs to be conducted many times and weight setting completely based experience radiation physicist. For fast...

For resolving the problem that a conventional intensity modulated radiotherapy (IMRT) plan designed with "two-step method" creates greater number of apertures and total Monitor Units (MU), direct aperture optimization1 (DAO) method using genetic algorithm conjugate gradient was studied based on Accurate/Advanced Radiation Therapy System (ARTS)2,3 developed by FDS Team (www.fds.org.cn). METHODS The parameters to adjust in DAO were shape MU each aperture. Based characteristics, encoded as 0/1...

Immunotherapy is an excellent treatment option for many solid tumors, and the therapeutic effect has been proved in clinical. Microsatellite instability (MSI) important predictive marker response to immune checkpoint inhibitors Colorectal cancer (CRC). CRC patients with high-level MSI can be provided immunotherapy benefit from it. Some studies have attempted predict using pathological images based on deep learning, but accuracy of prediction model needs improved. In this study, considering...

The voxel models representing human anatomy have been developed to calculate dose distribution in body, while the density and elemental composition are most important physical properties of model.Usually, when creating Monte Carlo input files, average tissue densities recommended ICRP Publication were used assign each existing models.As consists many voxels with different densities, conventional method failed take account voxel's discrepancy, therefore could not represent faithfully.To more...

Radiotherapy treatment plan may be replanned due the changes of tumors and organs at risk (OARs) during treatment. Deformable image registration (DIR) based Computed Tomography (CT) contour propagation in routine clinical setting is expected to reduce time needed for necessary manual OARs delineations increase efficiency replanning. In this study, a DIR method was developed CT propagation. Prior structure were incorporated into Demons DIR, which represented by adding an intensity matching...

Abstract This study mainly focused on the key technologies, photon dose calculation based Monte Carlo Finite-Size Pencil Beam (MCFSPB) model in Accurate Radiotherapy System (ARTS). In MCFSPB model, acquisition of pencil beam kernel is one most important technologies. this study, by analyzing demerits clinical methods, a new was developed (MC) simulation and technology medical accelerator energy spectrum reconstruction. which greatly improved accuracy calculated result. According to axial...