Features Of Nodes Research Articles

Subgraph autoencoder with bridge nodes

Subgraph representation learning is a burgeoning field within graph representation learning. However, current methods in this field face several issues, including the inability to facilitate information interaction between subgraphs, the destruction of original node feature information, and the detrimental effect of the structural information of the entire graph on the extracted subgraph structural information. To address these issues, this paper proposes a method named the subgraph autoencoder with bridge nodes (SAWBN). Specifically, first, SAWBN enhances the data interaction capability by adding a bridge node and connecting it to all nodes within a subgraph. The addition of the bridge node creates indirect connections between subgraphs, enabling them to interact and exchange information during the message-passing phase. To the best of our knowledge, this is the first paper to propose the concept of bridge nodes and to introduce bridge nodes into subgraph representation learning. Second, SAWBN utilizes a new message-passing paradigm called graph convolution with different weights (GDW). During the convolution process, GDW can assign different weights to nodes inside and outside a subgraph, effectively distinguishing the importance of nodes without compromising the original node feature information. Third, SAWBN uses an autoencoder to reconstruct subgraph node features. This reconstruction can eliminate the interference of the structural information of the entire graph and regenerate subgraph node features that are rich in subgraph structural information. Finally, these subgraph node features are aggregated to achieve a good representation of the subgraph structural information. Extensive results on four real-world subgraph datasets demonstrate that SAWBN outperforms state-of-the-art baselines. The source code of SAWBN is publicly available at https://github.com/denggaoqin/SAWBN.

GKE-TUNet: Geometry-Knowledge Embedded TransUNet Model for Retinal Vessel Segmentation Considering Anatomical Topology.

Automated retinal vessel segmentation is crucial for computer-aided clinical diagnosis and retinopathy screening. However, deep learning faces challenges in extracting complex intertwined structures and subtle small vessels from densely vascularized regions. To address these issues, we propose a novel segmentation model, called Geometry-Knowledge Embedded TransUNet (GKE-TUNet), which incorporates explicit embedding of topological features of retinal vessel anatomy. In the proposed GKE-TUNet model, a skeleton extraction network is pre-trained to extract the anatomical topology of retinal vessels from refined segmentation labels. During vessel segmentation, the dense skeleton graph is sampled as a graph of key-points and connections and is incorporated into the skip connection layer of TransUNet. The graph vertices are used as node features and correspond to positions in the low-level feature maps. The graph attention network (GAT) is used as the graph convolution backbone network to capture the shape semantics of vessels and the interaction of key locations along the topological direction. Finally, the node features obtained by graph convolution are read out as a sparse feature map based on their corresponding spatial coordinates. To address the problem of sparse feature maps, we employ convolution operators to fuse sparse feature maps with low-level dense feature maps. This fusion is weighted and connected to deep feature maps. Experimental results on the DRIVE, CHASE-DB1, and STARE datasets demonstrate the competitiveness of our proposed method compared to existing ones.

Drug repositioning based on residual attention network and free multiscale adversarial training

BackgroundConducting traditional wet experiments to guide drug development is an expensive, time-consuming and risky process. Analyzing drug function and repositioning plays a key role in identifying new therapeutic potential of approved drugs and discovering therapeutic approaches for untreated diseases. Exploring drug-disease associations has far-reaching implications for identifying disease pathogenesis and treatment. However, reliable detection of drug-disease relationships via traditional methods is costly and slow. Therefore, investigations into computational methods for predicting drug-disease associations are currently needed.ResultsThis paper presents a novel drug-disease association prediction method, RAFGAE. First, RAFGAE integrates known associations between diseases and drugs into a bipartite network. Second, RAFGAE designs the Re_GAT framework, which includes multilayer graph attention networks (GATs) and two residual networks. The multilayer GATs are utilized for learning the node embeddings, which is achieved by aggregating information from multihop neighbors. The two residual networks are used to alleviate the deep network oversmoothing problem, and an attention mechanism is introduced to combine the node embeddings from different attention layers. Third, two graph autoencoders (GAEs) with collaborative training are constructed to simulate label propagation to predict potential associations. On this basis, free multiscale adversarial training (FMAT) is introduced. FMAT enhances node feature quality through small gradient adversarial perturbation iterations, improving the prediction performance. Finally, tenfold cross-validations on two benchmark datasets show that RAFGAE outperforms current methods. In addition, case studies have confirmed that RAFGAE can detect novel drug-disease associations.ConclusionsThe comprehensive experimental results validate the utility and accuracy of RAFGAE. We believe that this method may serve as an excellent predictor for identifying unobserved disease-drug associations.

Predicting Disease-Metabolite Associations Based on the Metapath Aggregation of Tripartite Heterogeneous Networks.

The exploration of the interactions between diseases and metabolites holds significant implications for the diagnosis and treatment of diseases. However, traditional experimental methods are time-consuming and costly, and current computational methods often overlook the influence of other biological entities on both. In light of these limitations, we proposed a novel deep learning model based on metapath aggregation of tripartite heterogeneous networks (MAHN) to explore disease-related metabolites. Specifically, we introduced microbes to construct a tripartite heterogeneous network and employed graph convolutional network and enhanced GraphSAGE to learn node features with metapath length 3. Additionally, we utilized node-level and semantic-level attention mechanisms, a more granular approach, to aggregate node features with metapath length 2. Finally, the reconstructed association probability is obtained by fusing features from different metapaths into the bilinear decoder. The experiments demonstrate that the proposed MAHN model achieved superior performance in five-fold cross-validation with Acc (91.85%), Pre (90.48%), Recall (93.53%), F1 (91.94%), AUC (97.39%), and AUPR (97.47%), outperforming four state-of-the-art algorithms. Case studies on two complex diseases, irritable bowel syndrome and obesity, further validate the predictive results, and the MAHN model is a trustworthy prediction tool for discovering potential metabolites. Moreover, deep learning models integrating multi-omics data represent the future mainstream direction for predicting disease-related biological entities.

A Systematic Review of Occult Contralateral Neck Metastasis in Tonsillar Squamous Cell Carcinoma.

To determine the prevalence of occult contralateral nodal metastasis in tonsillar squamous cell carcinoma (TSCC) in patients who have undergone bilateral neck dissection. A systematic review of English articles identified from PubMed, Embase, and Web of Science databases. Search terms included "oropharynx," "carcinoma," "lymph node," and "neck dissection." Two reviewers independently screened abstracts, reviewed full texts, and extracted data from all studies that presented the prevalence of contralateral occult nodal metastasis in TSCC. The overall prevalence of occult contralateral nodal metastasis was 10%. The prevalence was 8% for cT1/T2 tumors, 19% for cT3/T4, 1% for N0 in the ipsilateral neck, and 12% for N+. Occult contralateral lymph nodes were most frequently found in neck level II (81%) and level III (19%). No metastatic nodes were found in level I. Elective neck dissection of the contralateral neck in TSCC is controversial due the historic morbidity caused by the surgery. A widely accepted recommendation suggests performing an elective neck dissection when the prevalence of occult metastasis is between 15% and 20%. The results of this study suggest that elective contralateral neck dissection will identify occult positivity in 19% of patients with T3/T4 tonsil cancer. In T1/T2 or N0 tumors, the diagnostic yield would be considerably lower at 8% and 1%, respectively. Contralateral nodal sampling could be considered based on patient preference after adequate counseling on the risks/benefits of occult nodal detection. More research is needed on other nodal features to formulate treatment guidelines. Laryngoscope, 2024.

HTFSMMA: Higher-Order Topological Guided Small Molecule-MicroRNA Associations Prediction.

Small molecules (SMs) play a pivotal role in regulating microRNAs (miRNAs). Existing prediction methods for associations between SM-miRNA have overlooked crucial aspects: the incorporation of local topological features between nodes, which represent either SMs or miRNAs, and the effective fusion of node features with topological features. This study introduces a novel approach, termed high-order topological features for SM-miRNA association prediction (HTFSMMA), which specifically addresses these limitations. Initially, an association graph is formed by integrating SM-miRNA association data, SM similarity, and miRNA similarity. Subsequently, we focus on the local information of links and propose target neighborhood graph convolutional network for extracting local topological features. Then, HTFSMMA employs graph attention networks to amalgamate these local features, thereby establishing a platform for the acquisition of high-order features through random walks. Finally, the extracted features are integrated into the multilayer perceptron to derive the association prediction scores. To demonstrate the performance of HTFSMMA, we conducted comprehensive evaluations including five-fold cross-validation, leave-one-out cross-validation (LOOCV), SM-fixed local LOOCV, and miRNA-fixed local LOOCV. The area under receiver operating characteristic curve values were 0.9958 ± 0.0024 (0.8722 ± 0.0021), 0.9986 (0.9504), 0.9974 (0.9111), and 0.9977 (0.9074), respectively. Our findings demonstrate the superior performance of HTFSMMA over existing approaches. In addition, three case studies and the DeLong test have confirmed the effectiveness of the proposed method. These results collectively underscore the significance of HTFSMMA in facilitating the inference of associations between SMs and miRNAs.

AdpSTGCN: Adaptive spatial–temporal graph convolutional network for traffic forecasting

Traffic flow forecasting plays a crucial role in applications such as intelligent transportation systems. Despite significant research in this field, the current methods have limitations that hinder the realization of highly accurate predictions. Existing GCN-based approaches typically rely on a definite graph structure derived from a physical topology or learned from node features, which is insufficient for building intricate spatial relationships among nodes. To address this challenge, we propose an adaptive spatial–temporal graph convolutional network for traffic forecasting. Our approach exploits a multi-head attention mechanism to construct multi-view feature graphs. We then introduce an adaptive graph convolution method to dynamically aggregate and propagate information from both the topology graph and multi-view feature graphs, which are capable of capturing complex spatial correlations across diverse proximity ranges. Furthermore, we designed a cascaded structural framework that combines temporal information with node features using gated dilated causal convolution to ensure the integrated modeling of spatial–temporal dynamics in traffic flow. Experiments on real-world datasets demonstrate that our proposed method outperforms the current mainstream methods, achieving better performance in traffic flow forecasting. The code is available at https://github.com/dhxdla/AdpSTGCN.git.

Backdoor attacks on unsupervised graph representation learning

Unsupervised graph learning techniques have garnered increasing interest among researchers. These methods employ the technique of maximizing mutual information to generate representations of nodes and graphs. We show that these methods are susceptible to backdoor attacks, wherein the adversary can poison a small portion of unlabeled graph data (e.g., node features and graph structure) by introducing triggers into the graph. This tampering disrupts the representations and increases the risk to various downstream applications. Previous backdoor attacks in supervised learning primarily operate directly on the label space and may not be suitable for unlabeled graph data. To tackle this challenge, we introduce GRBA,11https://github.com/fbd3/GRBA.git. a gradient-based first-order backdoor attack method. To the best of our knowledge, this constitutes a pioneering endeavor in investigating backdoor attacks within the domain of unsupervised graph learning. The initiation of this method doesn’t necessitate prior knowledge of downstream tasks, as it directly focuses on representations. Furthermore, it is versatile and can be applied to various downstream tasks, including node classification, node clustering and graph classification. We evaluate GRBA on state-of-the-art unsupervised learning models, and the experimental results substantiate the effectiveness and evasiveness of GRBA in both node-level and graph-level tasks.

Towards Inductive and Efficient Explanations for Graph Neural Networks.

Despite recent progress in Graph Neural Networks (GNNs), explaining predictions made by GNNs remains a challenging and nascent problem. The leading method mainly considers the local explanations, i.e., important subgraph structure and node features, to interpret why a GNN model makes the prediction for a single instance, e.g. a node or a graph. As a result, the explanation generated is painstakingly customized at the instance level. The unique explanation interpreting each instance independently is not sufficient to provide a global understanding of the learned GNN model, leading to the lack of generalizability and hindering it from being used in the inductive setting. Besides, training the explanation model explaining for each instance is time-consuming for large-scale real-life datasets. In this study, we address these key challenges and propose PGExplainer, a parameterized explainer for GNNs. PGExplainer adopts a deep neural network to parameterize the generation process of explanations, which renders PGExplainer a natural approach to multi-instance explanations. Compared to the existing work, PGExplainer has better generalization ability and can be utilized in an inductive setting without training the model for new instances. Thus, PGExplainer is much more efficient than the leading method with significant speed-up. In addition, the explanation networks can also be utilized as a regularizer to improve the generalization power of existing GNNs when jointly trained with downstream tasks. Experiments on both synthetic and real-life datasets show highly competitive performance with up to 24.7% relative improvement in AUC on explaining graph classification over the leading baseline.

Dual Contrastive Learning Network for Graph Clustering.

Graph representation is an important part of graph clustering. Recently, contrastive learning, which maximizes the mutual information between augmented graph views that share the same semantics, has become a popular and powerful paradigm for graph representation. However, in the process of patch contrasting, existing literature tends to learn all features into similar variables, i.e., representation collapse, leading to less discriminative graph representations. To tackle this problem, we propose a novel self-supervised learning method called dual contrastive learning network (DCLN), which aims to reduce the redundant information of learned latent variables in a dual manner. Specifically, the dual curriculum contrastive module (DCCM) is proposed, which approximates the node similarity matrix and feature similarity matrix to a high-order adjacency matrix and an identity matrix, respectively. By doing this, the informative information in high-order neighbors could be well collected and preserved while the irrelevant redundant features among representations could be eliminated, hence improving the discriminative capacity of the graph representation. Moreover, to alleviate the problem of sample imbalance during the contrastive process, we design a curriculum learning strategy, which enables the network to simultaneously learn reliable information from two levels. Extensive experiments on six benchmark datasets have demonstrated the effectiveness and superiority of the proposed algorithm compared with state-of-the-art methods.

Breast Cancer Classification From Digital Pathology Images via Connectivity-Aware Graph Transformer.

Automated classification of breast cancer subtypes from digital pathology images has been an extremely challenging task due to the complicated spatial patterns of cells in the tissue micro-environment. While newly proposed graph transformers are able to capture more long-range dependencies to enhance accuracy, they largely ignore the topological connectivity between graph nodes, which is nevertheless critical to extract more representative features to address this difficult task. In this paper, we propose a novel connectivity-aware graph transformer (CGT) for phenotyping the topology connectivity of the tissue graph constructed from digital pathology images for breast cancer classification. Our CGT seamlessly integrates connectivity embedding to node feature at every graph transformer layer by using local connectivity aggregation, in order to yield more comprehensive graph representations to distinguish different breast cancer subtypes. In light of the realistic intercellular communication mode, we then encode the spatial distance between two arbitrary nodes as connectivity bias in self-attention calculation, thereby allowing the CGT to distinctively harness the connectivity embedding based on the distance of two nodes. We extensively evaluate the proposed CGT on a large cohort of breast carcinoma digital pathology images stained by Haematoxylin & Eosin. Experimental results demonstrate the effectiveness of our CGT, which outperforms state-of-the-art methods by a large margin. Codes are released on https://github.com/wang-kang-6/CGT.

Research on group decision optimization and influence analysis in social network based on machine learning

With the rapid development of online social networks, the research on group decision-making in social networks has attracted extensive attention. Social networks facilitate interaction and behavior between individuals, businesses, and organizations. However, traditional group decision-making methods often ignore the social relationships between group members and fail to fully consider the impact of these relationships on subgroup division. In this work, we propose a novel model approach that combines graph neural networks and deep learning techniques to capture and analyze complex relational structures in social networks. The model uses node features and edge features to optimize the group decision-making process and effectively evaluate the influence between individuals through multi-layer network embedding and aggregation operations. Experimental analysis results show that the proposed method performs well in improving the accuracy and efficiency of decision-making, and significantly improves the quality of decision-making.

A Hybrid GNN Approach for Improved Molecular Property Prediction.

The development of new drugs is a vital effort that has the potential to improve human health, well-being and life expectancy. Molecular property prediction is a crucial step in drug discovery, as it helps to identify potential therapeutic compounds. However, experimental methods for drug development can often be time-consuming and resource-intensive, with a low probability of success. To address such limitations, deep learning (DL) methods have emerged as a viable alternative due to their ability to identify high-discriminating patterns in molecular data. In particular, graph neural networks (GNNs) operate on graph-structured data to identify promising drug candidates with desirable molecular properties. These methods represent molecules as a set of node (atoms) and edge (chemical bonds) features to aggregate local information for molecular graph representation learning. Despite the availability of several GNN frameworks, each approach has its own shortcomings. Although, some GNNs may excel in certain tasks, they may not perform as well in others. In this work, we propose a hybrid approach that incorporates different graph-based methods to combine their strengths and mitigate their limitations to accurately predict molecular properties. The proposed approach consists in a multi-layered hybrid GNN architecture that integrates multiple GNN frameworks to compute graph embeddings for molecular property prediction. Furthermore, we conduct extensive experiments on multiple benchmark datasets to demonstrate that our hybrid approach significantly outperforms the state-of-the-art graph-based models. The data and code scripts to reproduce the results are available in the repository, https://github.com/pedro-quesado/HybridGNN.

Reconstruction and Generation of Porous Metamaterial Units via Variational Graph Autoencoder and Large Language Model

Abstract In this paper, we propose and compare two novel deep generative model-based approaches for the design representation, reconstruction, and generation of porous metamaterials characterized by complex and fully connected solid and pore networks. A highly diverse porous metamaterial database is curated, with each sample represented by solid and pore phase graphs and a voxel image. All metamaterial samples adhere to the requirement of complete connectivity in both pore and solid phases. The first approach employs a Dual Decoder Variational Graph Autoencoder to generate both solid phase and pore phase graphs. The second approach employs a Variational Graph Autoencoder for reconstructing/generating the nodes in the solid phase and pore phase graphs and a Transformer-based Large Language Model (LLM) for reconstructing/generating the connections, i.e., the edges among the nodes. A comparative study is conducted, and we found that both approaches achieved high accuracy in reconstructing node features, while the LLM exhibited superior performance in reconstructing edge features. Reconstruction accuracy is also validated by voxel-to-voxel comparison between the reconstructions and the original images in the test set. Additionally, discussions on the advantages and limitations of using LLMs in metamaterial design generation, along with the rationale behind their utilization, are provided.

Predicting lncRNA-Disease Associations Based on a Dual-Path Feature Extraction Network with Multiple Sources of Information Integration.

Identifying the associations between long noncoding RNAs (lncRNAs) and disease is critical for disease prevention, diagnosis and treatment. However, conducting wet experiments to discover these associations is time-consuming and costly. Therefore, computational modeling for predicting lncRNA-disease associations (LDAs) has become an important alternative. To enhance the accuracy of LDAs prediction and alleviate the issue of node feature oversmoothing when exploring the potential features of nodes using graph neural networks, we introduce DPFELDA, a dual-path feature extraction network that leverages the integration of information from multiple sources to predict LDA. Initially, we establish a dual-view structure of lncRNAs and disease and a heterogeneous network of lncRNA-disease-microRNA (miRNA) interactions. Subsequently, features are extracted using a dual-path feature extraction network. In particular, we employ a combination of a graph convolutional network, a convolutional block attention module, and a node aggregation layer to perform multilayer topology feature extraction for the dual-view structure of lncRNAs and diseases. Additionally, we utilize a Transformer model to construct the node topology feature residual network for obtaining node-specific features in heterogeneous networks. Finally, XGBoost is employed for LDA prediction. The experimental results demonstrate that DPFELDA outperforms the benchmark model on various benchmark data sets. In the course of model exploration, it becomes evident that DPFELDA successfully alleviates the issue of node feature oversmoothing induced by graph-based learning. Ablation experiments confirm the effectiveness of the innovative module, and a case study substantiates the accuracy of DPFELDA model in predicting novel LDAs for characteristic diseases.

Intra-Frame Graph Structure and Inter-Frame Bipartite Graph Matching with ReID-Based Occlusion Resilience for Point Cloud Multi-Object Tracking

Three-dimensional multi-object tracking (MOT) using lidar point cloud data is crucial for applications in autonomous driving, smart cities, and robotic navigation. It involves identifying objects in point cloud sequence data and consistently assigning unique identities to them throughout the sequence. Occlusions can lead to missed detections, resulting in incorrect data associations and ID switches. To address these challenges, we propose a novel point cloud multi-object tracker called GBRTracker. Our method integrates an intra-frame graph structure into the backbone to extract and aggregate spatial neighborhood node features, significantly reducing detection misses. We construct an inter-frame bipartite graph for data association and design a sophisticated cost matrix based on the center, box size, velocity, and heading angle. Using a minimum-cost flow algorithm to achieve globally optimal matching, thereby reducing ID switches. For unmatched detections, we design a motion-based re-identification (ReID) feature embedding module, which uses velocity and the heading angle to calculate similarity and association probability, reconnecting them with their corresponding trajectory IDs or initializing new tracks. Our method maintains high accuracy and reliability, significantly reducing ID switches and trajectory fragmentation, even in challenging scenarios. We validate the effectiveness of GBRTracker through comparative and ablation experiments on the NuScenes and Waymo Open Datasets, demonstrating its superiority over state-of-the-art methods.

Signed Curvature Graph Representation Learning of Brain Networks for Brain Age Estimation.

Graph Neural Networks (GNNs) play a pivotal role in learning representations of brain networks for estimating brain age. However, the over-squashing impedes interactions between long-range nodes, hindering the ability of message-passing mechanism-based GNNs to learn the topological structure of brain networks. Graph rewiring methods and curvature GNNs have been proposed to alleviate over-squashing. However, most graph rewiring methods overlook node features and curvature GNNs neglect the geometric properties of signed curvature. In this study, a Signed Curvature GNN (SCGNN) was proposed to rewire the graph based on node features and curvature, and learn the representation of signed curvature. First, a Mutual Information Ollivier-Ricci Flow (MORF) was proposed to add connections in the neighborhood of edge with the minimal negative curvature based on the maximum mutual information between node features, improving the efficiency of information interaction between nodes. Then, a Signed Curvature Convolution (SCC) was proposed to aggregate node features based on positive and negative curvature, facilitating the model's ability to capture the complex topological structures of brain networks. Additionally, an Ollivier-Ricci Gradient Pooling (ORG-Pooling) was proposed to select the key nodes and topology structures by curvature gradient and attention mechanism, accurately obtaining the global representation for brain age estimation. Experiments conducted on six public datasets with structural magnetic resonance imaging (sMRI), spanning ages from 18 to 91 years, validate that our method achieves promising performance compared with existing methods. Furthermore, we employed the gaps between brain age and chronological age for identifying Alzheimer's Disease (AD), yielding the best classification performance.

Global-local manifold embedding broad graph convolutional network for hyperspectral image classification

Graph convolutional neural networks (GCNs) with domain-specific feature aggregation capabilities have unique advantages in hyperspectral image (HSI) classification. However, current GCN-based approaches frequently encounter the issue of node characteristics being over-smoothed while aggregating in higher-order domains. Furthermore, GCN linear classifiers focus solely on sample separability and ignore the potential manifold information of graph features, resulting in a failure to fully investigate extracted features. To address these problems, we propose a global-local manifold embedding broad graph convolutional network (GLMBG) for HSI classification. In GLMBG, we designed two modules from feature extraction and classification perspectives: The graph convolutional edge feature fusion extractor (GEFF) and the broad classifier of global-local manifold embedding (BGLME). GEFF is designed to learn graph node and local edge features from HSI through GCN and recursive filtering, combining them in a weighted manner to construct fused graph features. BGLME is designed to replace traditional linear classifiers with broad learning classifiers through manifold regularized embedding, fully utilizing the global and local manifold discriminant information of graph node features. The combination of GEFF and BGLME effectively reduces over-smoothing of graph node features while maximizing the utilization of manifold discriminant information, hence improving model feature discriminative ability. Experimental evaluations of three commonly used hyperspectral datasets show that our method surpasses state-of-the-art methods.

Tumor morphology evaluation using 3D-morphometric features of renal masses.

To assess the correlation between the general (gender, age, and maximum tumor size) and 3D morphotopometric features of the renal tumor node, following the MSCT data post-processing, and the tumor histological structure; to propose an equation allowing for kidney malignancy assessment based on general and morphometric features. In total, 304 patients with unilateral solitary renal neoplasms underwent laparoscopic (retroperitoneoscopic) or robotic partial or radical nephrectomy. Before the procedure, kidney contrast-enhanced MSCT followed by the tumor 3D-modeling was performed. 3D model of the kidney tumor, and its morphotopometric features, and histological structure were analyzed. The morphotopometric ones include the side of the lesion, location by segments, the surface where the tumor, the depth of the tumor invasion into the kidney, and the shape of tumor. Out of 304 patients, 254 (83.6%) had malignant kidney tumors and 50 (16.4%) benign kidney tumors. In total, 231 patients, out of 254 (90.9%) were assessed for the degree of malignant tumor differentiation. Malignant tumors were more frequent in men than in women (p < 0.001). Mushroom-shaped tumors were the most common shapes among benign renal masses (35.2%). The most common malignant kidney tumors had spherical with a partially uneven surface (27.6%), multinodular (tuberous (27.2%)), and spherical with a conical base (24.8%) shapes. Logistic regression model enabled the development of prognostic equation for tumor malignancy prediction ("low" or "high"). The univariate analysis revealed the correlation only between high differentiation (G1) and a spherical tumor with a conical base (p = 0.029). The resulting logistic model, based on the analysis of such predictors as gender and form of kidney lesions, demonstrated a large share (87.6%) of correct predictions of the kidney tumor malignancy.

Biparametric MRI of the prostate radiomics model for prediction of pelvic lymph node metastasis in prostate cancers : a two-centre study

ObjectivesExploring the value of adding correlation analysis (radiomic features (RFs) of pelvic metastatic lymph nodes and primary lesions) to screen RFs of primary lesions in the feature selection process of establishing prediction model.MethodsA total of 394 prostate cancer (PCa) patients (263 in the training group, 74 in the internal validation group and 57 in the external validation group) from two tertiary hospitals were included in the study. The cases with pelvic lymph node metastasis (PLNM) positive in the training group were diagnosed by biopsy or MRI with a short-axis diameter ≥ 1.5 cm, PLNM-negative cases in the training group and all cases in validation group were underwent both radical prostatectomy (RP) and extended pelvic lymph node dissection (ePLND). The RFs of PLNM-negative lesion and PLNM-positive tissues including primary lesions and their metastatic lymph nodes (MLNs) in the training group were extracted from T2WI and apparent diffusion coefficient (ADC) map to build the following two models by fivefold cross-validation: the lesion model, established according to the primary lesion RFs selected by t tests and absolute shrinkage and selection operator (LASSO); the lesion-correlation model, established according to the primary lesion RFs selected by Pearson correlation analysis (RFs of primary lesions and their MLNs, correlation coefficient > 0.9), t test and LASSO. Finally, we compared the performance of these two models in predicting PLNM.ResultsThe AUC and the DeLong test of AUC in the lesion model and lesion-correlation model were as follows: training groups (0.8053, 0.8466, p = 0.0002), internal validation group (0.7321, 0.8268, p = 0.0429), and external validation group (0.6445, 0.7874, p = 0.0431), respectively.ConclusionThe lesion-correlation model established by features of primary tumors correlated with MLNs has more advantages than the lesion model in predicting PLNM.