Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future

ALFREDO: Active Learning with FeatuRe disEntangelement and DOmain adaptation for medical image classification

State-of-the-art deep learning models often fail to generalize in the presence of distribution shifts between training (source) data and test (target) data. Domain adaptation methods are designed to address this issue using labeled samples (supervised domain adaptation) or unlabeled samples (unsupervised domain adaptation). Active learning is a method to select informative samples to obtain maximum performance from minimum annotations. Selecting informative target domain samples can improve model performance and robustness, and reduce data demands. This paper proposes a novel pipeline called ALFREDO (Active Learning with FeatuRe disEntangelement and DOmain adaptation) that performs active learning under domain shift. We propose a novel feature disentanglement approach to decompose image features into domain specific and task specific components. Domain specific components refer to those features that provide source specific information, e.g., scanners, vendors or hospitals. Task specific components are discriminative features for classification, segmentation or other tasks. Thereafter we define multiple novel cost functions that identify informative samples under domain shift. We test our proposed method for medical image classification using one histopathology dataset and two chest X-ray datasets. Experiments show our method achieves state-of-the-art results compared to other domain adaptation methods, as well as state of the art active domain adaptation methods.

Automated Three-Dimensional Imaging and Pfirrmann Classification of Intervertebral Disc Using a Graphical Neural Network in Sagittal Magnetic Resonance Imaging of the Lumbar Spine

This study aimed to develop a graph neural network (GNN) for automated three-dimensional (3D) magnetic resonance imaging (MRI) visualization and Pfirrmann grading of intervertebral discs (IVDs), and benchmark it against manual classifications. Lumbar IVD MRI data from 300 patients were retrospectively analyzed. Two clinicians assessed the manual segmentation and grading for inter-rater reliability using Cohen's kappa. The IVDs were then processed and classified using an automated convolutional neural network (CNN)-GNN pipeline, and their performance was evaluated using F1 scores. Manual Pfirrmann grading exhibited moderate agreement (κ = 0.455-0.565) among the clinicians, with higher exact match frequencies at lower lumbar levels. Single-grade discrepancies were prevalent except at L5/S1. Automated segmentation of IVDs using a pretrained U-Net model achieved an F1 score of 0.85, with a precision and recall of 0.83 and 0.88, respectively. Following 3D reconstruction of the automatically segmented IVD into a 3D point-cloud representation of the target intervertebral disc, the GNN model demonstrated moderate performance in Pfirrmann classification. The highest precision (0.81) and F1 score (0.71) were observed at L2/3, whereas the overall metrics indicated moderate performance (precision: 0.46, recall: 0.47, and F1 score: 0.46), with variability across spinal levels. The integration of CNN and GNN offers a new perspective for automating IVD analysis in MRI. Although the current performance highlights the need for further refinement, the moderate accuracy of the model, combined with its 3D visualization capabilities, establishes a promising foundation for more advanced grading systems.

Brain-GCN-Net: Graph-Convolutional Neural Network for brain tumor identification

BACKGROUND

The intersection of artificial intelligence and medical image analysis has ushered in a new era of innovation and changed the landscape of brain tumor detection and diagnosis. Correct detection and classification of brain tumors based on medical images is crucial for early diagnosis and effective treatment. Convolutional Neural Network (CNN) models are widely used for disease detection. However, they are sometimes unable to sufficiently recognize the complex features of medical images.

METHODS

This paper proposes a fused Deep Learning (DL) model that combines Graph Neural Networks (GNN), which recognize relational dependencies of image regions, and CNN, which captures spatial features, is proposed to improve brain tumor detection. By integrating these two architectures, our model achieves a more comprehensive representation of brain tumor images and improves classification performance. The proposed model is evaluated on a public dataset of 10847 MRI images. The results show that the proposed model outperforms the existing pre-trained models and traditional CNN architectures.

RESULTS

The fused DL model achieves 93.68% accuracy in brain tumor classification. The results indicate that the proposed model outperforms the existing pre-trained models and traditional CNN architectures.

CONCLUSION

The numerical results suggest that the model should be further investigated for potential use in clinical trials to improve clinical decision-making.

Neuroimage analysis using artificial intelligence approaches: a systematic review

In the contemporary era, artificial intelligence (AI) has undergone a transformative evolution, exerting a profound influence on neuroimaging data analysis. This development has significantly elevated our comprehension of intricate brain functions. This study investigates the ramifications of employing AI techniques on neuroimaging data, with a specific objective to improve diagnostic capabilities and contribute to the overall progress of the field. A systematic search was conducted in prominent scientific databases, including PubMed, IEEE Xplore, and Scopus, meticulously curating 456 relevant articles on AI-driven neuroimaging analysis spanning from 2013 to 2023. To maintain rigor and credibility, stringent inclusion criteria, quality assessments, and precise data extraction protocols were consistently enforced throughout this review. Following a rigorous selection process, 104 studies were selected for review, focusing on diverse neuroimaging modalities with an emphasis on mental and neurological disorders. Among these, 19.2% addressed mental illness, and 80.7% focused on neurological disorders. It is found that the prevailing clinical tasks are disease classification (58.7%) and lesion segmentation (28.9%), whereas image reconstruction constituted 7.3%, and image regression and prediction tasks represented 9.6%. AI-driven neuroimaging analysis holds tremendous potential, transforming both research and clinical applications. Machine learning and deep learning algorithms outperform traditional methods, reshaping the field significantly.

Classification of epileptic seizures in EEG data based on iterative gated graph convolution network

Introduction

The automatic and precise classification of epilepsy types using electroencephalogram (EEG) data promises significant advancements in diagnosing patients with epilepsy. However, the intricate interplay among multiple electrode signals in EEG data poses challenges. Recently, Graph Convolutional Neural Networks (GCN) have shown strength in analyzing EEG data due to their capability to describe complex relationships among different EEG regions. Nevertheless, several challenges remain: (1) GCN typically rely on predefined or prior graph topologies, which may not accurately reflect the complex correlations between brain regions. (2) GCN struggle to capture the long-temporal dependencies inherent in EEG signals, limiting their ability to effectively extract temporal features.

Methods

To address these challenges, we propose an innovative epileptic seizure classification model based on an Iterative Gated Graph Convolutional Network (IGGCN). For the epileptic seizure classification task, the original EEG graph structure is iteratively optimized using a multi-head attention mechanism during training, rather than relying on a static, predefined prior graph. We introduce Gated Graph Neural Networks (GGNN) to enhance the model's capacity to capture long-term dependencies in EEG series between brain regions. Additionally, Focal Loss is employed to alleviate the imbalance caused by the scarcity of epileptic EEG data.

Results

Our model was evaluated on the Temple University Hospital EEG Seizure Corpus (TUSZ) for classifying four types of epileptic seizures. The results are outstanding, achieving an average F1 score of 91.5% and an average Recall of 91.8%, showing a substantial improvement over current state-of-the-art models.

Discussion

Ablation experiments verified the efficacy of iterative graph optimization and gated graph convolution. The optimized graph structure significantly differs from the predefined EEG topology. Gated graph convolutions demonstrate superior performance in capturing the long-term dependencies in EEG series. Additionally, Focal Loss outperforms other commonly used loss functions in the TUSZ classification task.

Admission blood tests predicting survival of SARS-CoV-2 infected patients: a practical implementation of graph convolution network in imbalance dataset

BACKGROUND

Predicting an individual's risk of death from COVID-19 is essential for planning and optimising resources. However, since the real-world mortality rate is relatively low, particularly in places like Hong Kong, this makes building an accurate prediction model difficult due to the imbalanced nature of the dataset. This study introduces an innovative application of graph convolutional networks (GCNs) to predict COVID-19 patient survival using a highly imbalanced dataset. Unlike traditional models, GCNs leverage structural relationships within the data, enhancing predictive accuracy and robustness. By integrating demographic and laboratory data into a GCN framework, our approach addresses class imbalance and demonstrates significant improvements in prediction accuracy.

METHODS

The cohort included all consecutive positive COVID-19 patients fulfilling study criteria admitted to 42 public hospitals in Hong Kong between January 23 and December 31, 2020 (n = 7,606). We proposed the population-based graph convolutional neural network (GCN) model which took blood test results, age and sex as inputs to predict the survival outcomes. Furthermore, we compared our proposed model to the Cox Proportional Hazard (CPH) model, conventional machine learning models, and oversampling machine learning models. Additionally, a subgroup analysis was performed on the test set in order to acquire a deeper understanding of the relationship between each patient node and its neighbours, revealing possible underlying causes of the inaccurate predictions.

RESULTS

The GCN model was the top-performing model, with an AUC of 0.944, considerably outperforming all other models (p < 0.05), including the oversampled CPH model (0.708), linear regression (0.877), Linear Discriminant Analysis (0.860), K-nearest neighbours (0.834), Gaussian predictor (0.745) and support vector machine (0.847). With Kaplan-Meier estimates, the GCN model demonstrated good discriminability between low- and high-risk individuals (p < 0.0001). Based on subanalysis using the weighted-in score, although the GCN model was able to discriminate well between different predicted groups, the separation was inadequate between false negative (FN) and true negative (TN) groups.

CONCLUSION

The GCN model considerably outperformed all other machine learning methods and baseline CPH models. Thus, when applied to this imbalanced COVID survival dataset, adopting a population graph representation may be an approach to achieving good prediction.

Machine learning prediction models for diabetic kidney disease: systematic review and meta-analysis

BACKGROUND

Machine learning is increasingly recognized as a viable approach for identifying risk factors associated with diabetic kidney disease (DKD). However, the current state of real-world research lacks a comprehensive systematic analysis of the predictive performance of machine learning (ML) models for DKD.

OBJECTIVES

The objectives of this study were to systematically summarize the predictive capabilities of various ML methods in forecasting the onset and the advancement of DKD, and to provide a basic outline for ML methods in DKD.

METHODS

We have searched mainstream databases, including PubMed, Web of Science, Embase, and MEDLINE databases to obtain the eligible studies. Subsequently, we categorized various ML techniques and analyzed the differences in their performance in predicting DKD.

RESULTS

Logistic regression (LR) was the prevailing ML method, yielding an overall pooled area under the receiver operating characteristic curve (AUROC) of 0.83. On the other hand, the non-LR models also performed well with an overall pooled AUROC of 0.80. Our t-tests showed no statistically significant difference in predicting ability between LR and non-LR models (t = 1.6767, p > 0.05).

CONCLUSION

All ML predicting models yielded relatively satisfied DKD predicting ability with their AUROCs greater than 0.7. However, we found no evidence that non-LR models outperformed the LR model. LR exhibits high performance or accuracy in practice, while it is known for algorithmic simplicity and computational efficiency compared to others. Thus, LR may be considered a cost-effective ML model in practice.

Improving the Automated Diagnosis of Breast Cancer with Mesh Reconstruction of Ultrasound Images Incorporating 3D Mesh Features and a Graph Attention Network

This study proposes a novel approach for breast tumor classification from ultrasound images into benign and malignant by converting the region of interest (ROI) of a 2D ultrasound image into a 3D representation using the point-e system, allowing for in-depth analysis of underlying characteristics. Instead of relying solely on 2D imaging features, this method extracts 3D mesh features that describe tumor patterns more precisely. Ten informative and medically relevant mesh features are extracted and assessed with two feature selection techniques. Additionally, a feature pattern analysis has been conducted to determine the feature's significance. A feature table with dimensions of 445 × 12 is generated and a graph is constructed, considering the rows as nodes and the relationships among the nodes as edges. The Spearman correlation coefficient method is employed to identify edges between the strongly connected nodes (with a correlation score greater than or equal to 0.7), resulting in a graph containing 56,054 edges and 445 nodes. A graph attention network (GAT) is proposed for the classification task and the model is optimized with an ablation study, resulting in the highest accuracy of 99.34%. The performance of the proposed model is compared with ten machine learning (ML) models and one-dimensional convolutional neural network where the test accuracy of these models ranges from 73 to 91%. Our novel 3D mesh-based approach, coupled with the GAT, yields promising performance for breast tumor classification, outperforming traditional models, and has the potential to reduce time and effort of radiologists providing a reliable diagnostic system.

Identifying autism spectrum disorder from multi-modal data with privacy-preserving

The application of deep learning models to precision medical diagnosis often requires the aggregation of large amounts of medical data to effectively train high-quality models. However, data privacy protection mechanisms make it difficult to perform medical data collection from different medical institutions. In autism spectrum disorder (ASD) diagnosis, automatic diagnosis using multimodal information from heterogeneous data has not yet achieved satisfactory performance. To address the privacy preservation issue as well as to improve ASD diagnosis, we propose a deep learning framework using multimodal feature fusion and hypergraph neural networks for disease prediction in federated learning (FedHNN). By introducing the federated learning strategy, each local model is trained and computed independently in a distributed manner without data sharing, allowing rapid scaling of medical datasets to achieve robust and scalable deep learning predictive models. To further improve the performance with privacy preservation, we improve the hypergraph model for multimodal fusion to make it suitable for autism spectrum disorder (ASD) diagnosis tasks by capturing the complementarity and correlation between modalities through a hypergraph fusion strategy. The results demonstrate that our proposed federated learning-based prediction model is superior to all local models and outperforms other deep learning models. Overall, our proposed FedHNN has good results in the work of using multi-site data to improve the performance of ASD identification.

Acute exacerbation prediction of COPD based on Auto-metric graph neural network with inspiratory and expiratory chest CT images

Chronic obstructive pulmonary disease (COPD) is a widely prevalent disease with significant mortality and disability rates and has become the third leading cause of death globally. Patients with acute exacerbation of COPD (AECOPD) often substantially suffer deterioration and death. Therefore, COPD patients deserve special consideration regarding treatment in this fragile population for pre-clinical health management. Based on the above, this paper proposes an AECOPD prediction model based on the Auto-Metric Graph Neural Network (AMGNN) using inspiratory and expiratory chest low-dose CT images. This study was approved by the ethics committee in the First Affiliated Hospital of Guangzhou Medical University. Subsequently, 202 COPD patients with inspiratory and expiratory chest CT Images and their annual number of AECOPD were collected after the exclusion. First, the inspiratory and expiratory lung parenchyma images of the 202 COPD patients are extracted using a trained ResU-Net. Then, inspiratory and expiratory lung Radiomics and CNN features are extracted from the 202 inspiratory and expiratory lung parenchyma images by Pyradiomics and pre-trained Med3D (a heterogeneous 3D network), respectively. Last, Radiomics and CNN features are combined and then further selected by the Lasso algorithm and generalized linear model for determining node features and risk factors of AMGNN, and then the AECOPD prediction model is established. Compared to related models, the proposed model performs best, achieving an accuracy of 0.944, precision of 0.950, F1-score of 0.944, ad area under the curve of 0.965. Therefore, it is concluded that our model may become an effective tool for AECOPD prediction.

SGT++: Improved Scene Graph-Guided Transformer for Surgical Report Generation

Automatically recording surgical procedures and generating surgical reports are crucial for alleviating surgeons' workload and enabling them to concentrate more on the operations. Despite some achievements, there still exist several issues for the previous works: 1) failure to model the interactive relationship between surgical instruments and tissue; and 2) neglect of fine-grained differences within different surgical images in the same surgery. To address these two issues, we propose an improved scene graph-guided Transformer, also named by SGT++, to generate more accurate surgical report, in which the complex interactions between surgical instruments and tissue are learnt from both explicit and implicit perspectives. Specifically, to facilitate the understanding of the surgical scene graph under a graph learning framework, a simple yet effective approach is proposed for homogenizing the input heterogeneous scene graph. For the homogeneous scene graph that contains explicit structured and fine-grained semantic relationships, we design an attention-induced graph transformer for node aggregation via an explicit relation-aware encoder. In addition, to characterize the implicit relationships about the instrument, tissue, and the interaction between them, the implicit relational attention is proposed to take full advantage of the prior knowledge from the interactional prototype memory. With the learnt explicit and implicit relation-aware representations, they are then coalesced to obtain the fused relation-aware representations contributing to generating reports. Some comprehensive experiments on two surgical datasets show that the proposed STG++ model achieves state-of-the-art results.

A novel spatiotemporal graph convolutional network framework for functional connectivity biomarkers identification of Alzheimer's disease

BACKGROUND

Functional connectivity (FC) biomarkers play a crucial role in the early diagnosis and mechanistic study of Alzheimer's disease (AD). However, the identification of effective FC biomarkers remains challenging. In this study, we introduce a novel approach, the spatiotemporal graph convolutional network (ST-GCN) combined with the gradient-based class activation mapping (Grad-CAM) model (STGC-GCAM), to effectively identify FC biomarkers for AD.

METHODS

This multi-center cross-racial retrospective study involved 2,272 participants, including 1,105 cognitively normal (CN) subjects, 790 mild cognitive impairment (MCI) individuals, and 377 AD patients. All participants underwent functional magnetic resonance imaging (fMRI) and T1-weighted MRI scans. In this study, firstly, we optimized the STGC-GCAM model to enhance classification accuracy. Secondly, we identified novel AD-associated biomarkers using the optimized model. Thirdly, we validated the imaging biomarkers using Kaplan-Meier analysis. Lastly, we performed correlation analysis and causal mediation analysis to confirm the physiological significance of the identified biomarkers.

RESULTS

The STGC-GCAM model demonstrated great classification performance (The average area under the curve (AUC) values for different categories were: CN vs MCI = 0.98, CN vs AD = 0.95, MCI vs AD = 0.96, stable MCI vs progressive MCI = 0.79). Notably, the model identified specific brain regions, including the sensorimotor network (SMN), visual network (VN), and default mode network (DMN), as key differentiators between patients and CN individuals. These brain regions exhibited significant associations with the severity of cognitive impairment (p < 0.05). Moreover, the topological features of important brain regions demonstrated excellent predictive capability for the conversion from MCI to AD (Hazard ratio = 3.885, p < 0.001). Additionally, our findings revealed that the topological features of these brain regions mediated the impact of amyloid beta (Aβ) deposition (bootstrapped average causal mediation effect: β = -0.01 [-0.025, 0.00], p < 0.001) and brain glucose metabolism (bootstrapped average causal mediation effect: β = -0.02 [-0.04, -0.001], p < 0.001) on cognitive status.

CONCLUSIONS

This study presents the STGC-GCAM framework, which identifies FC biomarkers using a large multi-site fMRI dataset.

The optimization of college tennis training and teaching under deep learning

To enhance the integration of deep learning into tennis education and instigate reforms in sports programs, this paper employs deep learning techniques to analyze tennis tactics. The experiments initially introduce the concepts of sports science and backpropagation neural networks. Subsequently, these theories are applied to formulate a comprehensive system of tennis tactical diagnostic indicators, encompassing construction principles, basic requirements, diagnostic indicator content, and evaluation indicator design. Simultaneously, a Back Propagation Neural Network (BPNN) is utilized to construct a tennis tactical diagnostic model. The paper concludes with a series of experiments conducted to validate the effectiveness of the constructed indicator system and diagnostic model. The results indicate the excellent performance of the neural network model when trained on tennis match data, with a mean squared error of 0.00037146 on the validation set and 0.0104 on the training set. This demonstrates the outstanding predictive capability of the model. Additionally, the system proves capable of providing detailed tactical application analysis when employing the tennis tactical diagnostic indicator system for real-time athlete diagnosis. This functionality offers robust support for effective training and coaching during matches. In summary, this paper aims to evaluate athletes' performance by constructing a diagnostic system, providing a solid reference for optimizing tennis training and education. The insights offered by this paper have the potential to drive reforms in sports programs, particularly in the realm of tennis education.

Statistical Methods and Machine Learning Algorithms for Investigating Metabolic Syndrome in Temporomandibular Disorders: A Nationwide Study

The objective of this study was to analyze the associations between temporomandibular disorders (TMDs) and metabolic syndrome (MetS) components, consequences, and related conditions. This research analyzed data from the Dental, Oral, Medical Epidemiological (DOME) records-based study which integrated comprehensive socio-demographic, medical, and dental databases from a nationwide sample of dental attendees aged 18-50 years at military dental clinics for 1 year. Statistical and machine learning models were performed with TMDs as the dependent variable. The independent variables included age, sex, smoking, each of the MetS components, and consequences and related conditions, including hypertension, hyperlipidemia, diabetes, impaired glucose tolerance (IGT), obesity, cardiac disease, obstructive sleep apnea (OSA), nonalcoholic fatty liver disease (NAFLD), transient ischemic attack (TIA), stroke, deep venous thrombosis (DVT), and anemia. The study included 132,529 subjects, of which 1899 (1.43%) had been diagnosed with TMDs. The following parameters retained a statistically significant positive association with TMDs in the multivariable binary logistic regression analysis: female sex [OR = 2.65 (2.41-2.93)], anemia [OR = 1.69 (1.48-1.93)], and age [OR = 1.07 (1.06-1.08)]. Features importance generated by the XGBoost machine learning algorithm ranked the significance of the features with TMDs (the target variable) as follows: sex was ranked first followed by age (second), anemia (third), hypertension (fourth), and smoking (fifth). Metabolic morbidity and anemia should be included in the systemic evaluation of TMD patients.

Multi-Dimensional Validation of the Integration of Syntactic and Semantic Distance Measures for Clustering Fibromyalgia Patients in the Rheumatic Monitor Big Data Study

This study primarily aimed at developing a novel multi-dimensional methodology to discover and validate the optimal number of clusters. The secondary objective was to deploy it for the task of clustering fibromyalgia patients. We present a comprehensive methodology that includes the use of several different clustering algorithms, quality assessment using several syntactic distance measures (the Silhouette Index (SI), Calinski-Harabasz index (CHI), and Davies-Bouldin index (DBI)), stability assessment using the adjusted Rand index (ARI), and the validation of the internal semantic consistency of each clustering option via the performance of multiple clustering iterations after the repeated bagging of the data to select multiple partial data sets. Then, we perform a statistical analysis of the (clinical) semantics of the most stable clustering options using the full data set. Finally, the results are validated through a supervised machine learning (ML) model that classifies the patients back into the discovered clusters and is interpreted by calculating the Shapley additive explanations (SHAP) values of the model. Thus, we refer to our methodology as the clustering, distance measures and iterative statistical and semantic validation (CDI-SSV) methodology. We applied our method to the analysis of a comprehensive data set acquired from 1370 fibromyalgia patients. The results demonstrate that the K-means was highly robust in the syntactic and the internal consistent semantics analysis phases and was therefore followed by a semantic assessment to determine the optimal number of clusters (k), which suggested k = 3 as a more clinically meaningful solution, representing three distinct severity levels. the random forest model validated the results by classification into the discovered clusters with high accuracy (AUC: 0.994; accuracy: 0.946). SHAP analysis emphasized the clinical relevance of "functional problems" in distinguishing the most severe condition. In conclusion, the CDI-SSV methodology offers significant potential for improving the classification of complex patients. Our findings suggest a classification system for different profiles of fibromyalgia patients, which has the potential to improve clinical care, by providing clinical markers for the evidence-based personalized diagnosis, management, and prognosis of fibromyalgia patients.

Functional division of the dorsal striatum based on a graph neural network

The dorsal striatum, an essential nucleus in subcortical areas, has a crucial role in controlling a variety of complex cognitive behaviors; however, few studies have been conducted in recent years to explore the functional subregions of the dorsal striatum that are significantly activated when performing multiple tasks. To explore the differences and connections between the functional subregions of the dorsal striatum that are significantly activated when performing different tasks, we propose a framework for functional division of the dorsal striatum based on a graph neural network model. First, time series information for each voxel in the dorsal striatum is extracted from acquired functional magnetic resonance imaging data and used to calculate the connection strength between voxels. Then, a graph is constructed using the voxels as nodes and the connection strengths between voxels as edges. Finally, the graph data are analyzed using the graph neural network model to functionally divide the dorsal striatum. The framework was used to divide functional subregions related to the four tasks including olfactory reward, "0-back" working memory, emotional picture stimulation, and capital investment decision-making. The results were further subjected to conjunction analysis to obtain 15 functional subregions in the dorsal striatum. The 15 different functional subregions divided based on the graph neural network model indicate that there is functional differentiation in the dorsal striatum when the brain performs different cognitive tasks. The spatial localization of the functional subregions contributes to a clear understanding of the differences and connections between functional subregions.

Explaining graph convolutional network predictions for clinicians-An explainable AI approach to Alzheimer's disease classification

Introduction

Graph-based representations are becoming more common in the medical domain, where each node defines a patient, and the edges signify associations between patients, relating individuals with disease and symptoms in a node classification task. In this study, a Graph Convolutional Networks (GCN) model was utilized to capture differences in neurocognitive, genetic, and brain atrophy patterns that can predict cognitive status, ranging from Normal Cognition (NC) to Mild Cognitive Impairment (MCI) and Alzheimer's Disease (AD), on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Elucidating model predictions is vital in medical applications to promote clinical adoption and establish physician trust. Therefore, we introduce a decomposition-based explanation method for individual patient classification.

Methods

Our method involves analyzing the output variations resulting from decomposing input values, which allows us to determine the degree of impact on the prediction. Through this process, we gain insight into how each feature from various modalities, both at the individual and group levels, contributes to the diagnostic result. Given that graph data contains critical information in edges, we studied relational data by silencing all the edges of a particular class, thereby obtaining explanations at the neighborhood level.

Results

Our functional evaluation showed that the explanations remain stable with minor changes in input values, specifically for edge weights exceeding 0.80. Additionally, our comparative analysis against SHAP values yielded comparable results with significantly reduced computational time. To further validate the model's explanations, we conducted a survey study with 11 domain experts. The majority (71%) of the responses confirmed the correctness of the explanations, with a rating of above six on a 10-point scale for the understandability of the explanations.

Discussion

Strategies to overcome perceived limitations, such as the GCN's overreliance on demographic information, were discussed to facilitate future adoption into clinical practice and gain clinicians' trust as a diagnostic decision support system.

Reduced reverse degree-based topological indices of graphyne and graphdiyne nanoribbons with applications in chemical analysis

Graphyne and Graphdiyne Nanoribbons reveal significant prospective with diverse applications. In electronics, they propose unique electronic properties for high-performance nanoscale devices, while in catalysis, their excellent surface area and reactivity sort them valuable catalyst supports for numerous chemical reactions, contributing to progresses in sustainable energy and environmental remediation. The topological indices (TIs) are numerical invariants that provide important information about the molecular topology of a given molecular graph. These indices are essential in QSAR/QSPR analysis and play a significant role in predicting various physico-chemical characteristics. In this article, we present a formula for computing reduced reverse (RR) degree-based topological indices for graphyne and graphdiyne nanoribbons, including the RR Zagreb indices, RR hyper-Zagreb indices, RR forgotten index, RR atom bond connectivity index, and RR Geometric-arithmetic index. We also execute a graph-theoretical analysis and comparison to demonstrate the critical significance and validate the acquired results. Our findings provide insights into the structural and chemical properties of these nanoribbons and contribute to the development of new materials for various applications.

Meta Transfer of Self-Supervised Knowledge: Foundation Model in Action for Post-Traumatic Epilepsy Prediction

Despite the impressive advancements achieved using deep-learning for functional brain activity analysis, the heterogeneity of functional patterns and scarcity of imaging data still pose challenges in tasks such as prediction of future onset of Post-Traumatic Epilepsy (PTE) from data acquired shortly after traumatic brain injury (TBI). Foundation models pre-trained on separate large-scale datasets can improve the performance from scarce and heterogeneous datasets. For functional Magnetic Resonance Imaging (fMRI), while data may be abundantly available from healthy controls, clinical data is often scarce, limiting the ability of foundation models to identify clinically-relevant features. We overcome this limitation by introducing a novel training strategy for our foundation model by integrating meta-learning with self-supervised learning to improve the generalization from normal to clinical features. In this way we enable generalization to other downstream clinical tasks, in our case prediction of PTE. To achieve this, we perform self-supervised training on the control dataset to focus on inherent features that are not limited to a particular supervised task while applying meta-learning, which strongly improves the model's generalizability using bi-level optimization. Through experiments on neurological disorder classification tasks, we demonstrate that the proposed strategy significantly improves task performance on small-scale clinical datasets. To explore the generalizability of the foundation model in downstream applications, we then apply the model to an unseen TBI dataset for prediction of PTE using zero-shot learning. Results further demonstrated the enhanced generalizability of our foundation model.

Spatio-Temporal Anomaly Detection with Graph Networks for Data Quality Monitoring of the Hadron Calorimeter

The Compact Muon Solenoid (CMS) experiment is a general-purpose detector for high-energy collision at the Large Hadron Collider (LHC) at CERN. It employs an online data quality monitoring (DQM) system to promptly spot and diagnose particle data acquisition problems to avoid data quality loss. In this study, we present a semi-supervised spatio-temporal anomaly detection (AD) monitoring system for the physics particle reading channels of the Hadron Calorimeter (HCAL) of the CMS using three-dimensional digi-occupancy map data of the DQM. We propose the GraphSTAD system, which employs convolutional and graph neural networks to learn local spatial characteristics induced by particles traversing the detector and the global behavior owing to shared backend circuit connections and housing boxes of the channels, respectively. Recurrent neural networks capture the temporal evolution of the extracted spatial features. We validate the accuracy of the proposed AD system in capturing diverse channel fault types using the LHC collision data sets. The GraphSTAD system achieves production-level accuracy and is being integrated into the CMS core production system for real-time monitoring of the HCAL. We provide a quantitative performance comparison with alternative benchmark models to demonstrate the promising leverage of the presented system.

TaG-Net: Topology-Aware Graph Network for Centerline-Based Vessel Labeling

Anatomical labeling of head and neck vessels is a vital step for cerebrovascular disease diagnosis. However, it remains challenging to automatically and accurately label vessels in computed tomography angiography (CTA) since head and neck vessels are tortuous, branched, and often spatially close to nearby vasculature. To address these challenges, we propose a novel topology-aware graph network (TaG-Net) for vessel labeling. It combines the advantages of volumetric image segmentation in the voxel space and centerline labeling in the line space, wherein the voxel space provides detailed local appearance information, and line space offers high-level anatomical and topological information of vessels through the vascular graph constructed from centerlines. First, we extract centerlines from the initial vessel segmentation and construct a vascular graph from them. Then, we conduct vascular graph labeling using TaG-Net, in which techniques of topology-preserving sampling, topology-aware feature grouping, and multi-scale vascular graph are designed. After that, the labeled vascular graph is utilized to improve volumetric segmentation via vessel completion. Finally, the head and neck vessels of 18 segments are labeled by assigning centerline labels to the refined segmentation. We have conducted experiments on CTA images of 401 subjects, and experimental results show superior vessel segmentation and labeling of our method compared to other state-of-the-art methods.

Opportunities and challenges of 5G network technology toward precision medicine

Moving away from traditional "one-size-fits-all" treatment to precision-based medicine has tremendously improved disease prognosis, accuracy of diagnosis, disease progression prediction, and targeted-treatment. The current cutting-edge of 5G network technology is enabling a growing trend in precision medicine to extend its utility and value to the smart healthcare system. The 5G network technology will bring together big data, artificial intelligence, and machine learning to provide essential levels of connectivity to enable a new health ecosystem toward precision medicine. In the 5G-enabled health ecosystem, its applications involve predictive and preventative measurements which enable advances in patient personalization. This review aims to discuss the opportunities, challenges, and prospects posed to 5G network technology in moving forward to deliver personalized treatments and patient-centric care via a precision medicine approach.

Using artificial intelligence to improve public health: a narrative review

Artificial intelligence (AI) is a rapidly evolving tool revolutionizing many aspects of healthcare. AI has been predominantly employed in medicine and healthcare administration. However, in public health, the widespread employment of AI only began recently, with the advent of COVID-19. This review examines the advances of AI in public health and the potential challenges that lie ahead. Some of the ways AI has aided public health delivery are via spatial modeling, risk prediction, misinformation control, public health surveillance, disease forecasting, pandemic/epidemic modeling, and health diagnosis. However, the implementation of AI in public health is not universal due to factors including limited infrastructure, lack of technical understanding, data paucity, and ethical/privacy issues.

The Combination of a Graph Neural Network Technique and Brain Imaging to Diagnose Neurological Disorders: A Review and Outlook

Neurological disorders (NDs), such as Alzheimer's disease, have been a threat to human health all over the world. It is of great importance to diagnose ND through combining artificial intelligence technology and brain imaging. A graph neural network (GNN) can model and analyze the brain, imaging from morphology, anatomical structure, function features, and other aspects, thus becoming one of the best deep learning models in the diagnosis of ND. Some researchers have investigated the application of GNN in the medical field, but the scope is broad, and its application to NDs is less frequent and not detailed enough. This review focuses on the research progress of GNNs in the diagnosis of ND. Firstly, we systematically investigated the GNN framework of ND, including graph construction, graph convolution, graph pooling, and graph prediction. Secondly, we investigated common NDs using the GNN diagnostic model in terms of data modality, number of subjects, and diagnostic accuracy. Thirdly, we discussed some research challenges and future research directions. The results of this review may be a valuable contribution to the ongoing intersection of artificial intelligence technology and brain imaging.

Classification of recurrent major depressive disorder using a new time series feature extraction method through multisite rs-fMRI data

BACKGROUND

Major depressive disorder (MDD) has a high rate of recurrence. Identifying patients with recurrent MDD is advantageous in adopting prevention strategies to reduce the disabling effects of depression.

METHOD

We propose a novel feature extraction method that includes dynamic temporal information, and inputs the extracted features into a graph convolutional network (GCN) to achieve classification of recurrent MDD. We extract the average time series using an atlas from resting-state functional magnetic resonance imaging (fMRI) data. Pearson correlation was calculated between brain region sequences at each time point, representing the functional connectivity at each time point. The connectivity is used as the adjacency matrix and the brain region sequences as node features for a GCN model to classify recurrent MDD. Gradient-weighted Class Activation Mapping (Grad-CAM) was used to analyze the contribution of different brain regions to the model. Brain regions making greater contribution to classification were considered to be the regions with altered brain function in recurrent MDD.

RESULT

We achieved a classification accuracy of 75.8 % for recurrent MDD on the multi-site dataset, the Rest-meta-MDD. The brain regions closely related to recurrent MDD have been identified.

LIMITATION

The pre-processing stage may affect the final classification performance and harmonizing site differences may improve the classification performance.

CONCLUSION

The experimental results demonstrate that the proposed method can effectively classify recurrent MDD and extract dynamic changes of brain activity patterns in recurrent depression.

IA-GCN: Interpretable Attention based Graph Convolutional Network for Disease Prediction

Interpretability in Graph Convolutional Networks (GCNs) has been explored to some extent in general in computer vision; yet, in the medical domain, it requires further examination. Most of the interpretability approaches for GCNs, especially in the medical domain, focus on interpreting the output of the model in a post-hoc fashion. In this paper, we propose an interpretable attention module (IAM) that explains the relevance of the input features to the classification task on a GNN Model. The model uses these interpretations to improve its performance. In a clinical scenario, such a model can assist the clinical experts in better decision-making for diagnosis and treatment planning. The main novelty lies in the IAM, which directly operates on input features. IAM learns the attention for each feature based on the unique interpretability-specific losses. We show the application of our model on two publicly available datasets, Tadpole and the UK Biobank (UKBB). For Tadpole we choose the task of disease classification, and for UKBB, age, and sex prediction. The proposed model achieves an increase in an average accuracy of 3.2% for Tadpole and 1.6% for UKBB sex and 2% for the UKBB age prediction task compared to the state-of-the-art. Further, we show exhaustive validation and clinical interpretation of our results.

Unsupervised pre-training of graph transformers on patient population graphs

Pre-training has shown success in different areas of machine learning, such as Computer Vision, Natural Language Processing (NLP), and medical imaging. However, it has not been fully explored for clinical data analysis. An immense amount of clinical records are recorded, but still, data and labels can be scarce for data collected in small hospitals or dealing with rare diseases. In such scenarios, pre-training on a larger set of unlabeled clinical data could improve performance. In this paper, we propose novel unsupervised pre-training techniques designed for heterogeneous, multi-modal clinical data for patient outcome prediction inspired by masked language modeling (MLM), by leveraging graph deep learning over population graphs. To this end, we further propose a graph-transformer-based network, designed to handle heterogeneous clinical data. By combining masking-based pre-training with a transformer-based network, we translate the success of masking-based pre-training in other domains to heterogeneous clinical data. We show the benefit of our pre-training method in a self-supervised and a transfer learning setting, utilizing three medical datasets TADPOLE, MIMIC-III, and a Sepsis Prediction Dataset. We find that our proposed pre-training methods help in modeling the data at a patient and population level and improve performance in different fine-tuning tasks on all datasets.

The radiomic biomarker in non-small cell lung cancer: 18F-FDG PET/CT characterisation of programmed death-ligand 1 status

AIM

To present an integrated 2-[18F]-fluoro-2-deoxy-d-glucose (18F-FDG) positron-emission tomography (PET)/computed tomography (CT) radiomic characterisation of programmed death-ligand 1 (PD-L1) status in non-small-cell lung cancer (NSCLC).

MATERIALS AND METHODS

In this retrospective study, 18F-FDG PET/CT images and clinical data of 394 eligible patients were divided into training (n=275) and test sets (n=119). Next, the corresponding nodule of interest was segmented manually on the axial CT images by radiologists. After which, the spatial position matching method was used to match the image positions of CT and PET, and radiomic features of the CT and PET images were extracted. Radiomic models were built using five different machine-learning classifiers and the performance of the radiomic models were further evaluated. Finally, a radiomic signature was established to predict the PD-L1 status in patients with NSCLC using the features in the best performing radiomic model.

RESULTS

The radiomic model based on the PET intranodular region determined using the logistic regression classifier preformed best, yielding an area under the receiver operating characteristics curve (AUC) of 0.813 (95% CI: 0.812, 0.821) on the test set. The clinical features did not improve the test set AUC (0.806, 95% CI: 0.801, 0.810). The final radiomic signature for PD-L1 status was consisted of three PET radiomic features.

CONCLUSION

This study showed that an 18F-FDG PET/CT-based radiomic signature could be used as a non-invasive biomarker to discriminate PD-L1-positive from PD-L1-negative in patients with NSCLC.

A multi-head residual connection GCN for EEG emotion recognition

Electroencephalography (EEG) emotion recognition is a crucial aspect of human-computer interaction. However, conventional neural networks have limitations in extracting profound EEG emotional features. This paper introduces a novel multi-head residual graph convolutional neural network (MRGCN) model that incorporates complex brain networks and graph convolution networks. The decomposition of multi-band differential entropy (DE) features exposes the temporal intricacy of emotion-linked brain activity, and the combination of short and long-distance brain networks can explore complex topological characteristics. Moreover, the residual-based architecture not only enhances performance but also augments classification stability across subjects. The visualization of brain network connectivity offers a practical technique for investigating emotional regulation mechanisms. The MRGCN model exhibits average classification accuracies of 95.8% and 98.9% for the DEAP and SEED datasets, respectively, highlighting its excellent performance and robustness.

The importance of graph databases and graph learning for clinical applications

The increasing amount and complexity of clinical data require an appropriate way of storing and analyzing those data. Traditional approaches use a tabular structure (relational databases) for storing data and thereby complicate storing and retrieving interlinked data from the clinical domain. Graph databases provide a great solution for this by storing data in a graph as nodes (vertices) that are connected by edges (links). The underlying graph structure can be used for the subsequent data analysis (graph learning). Graph learning consists of two parts: graph representation learning and graph analytics. Graph representation learning aims to reduce high-dimensional input graphs to low-dimensional representations. Then, graph analytics uses the obtained representations for analytical tasks like visualization, classification, link prediction and clustering which can be used to solve domain-specific problems. In this survey, we review current state-of-the-art graph database management systems, graph learning algorithms and a variety of graph applications in the clinical domain. Furthermore, we provide a comprehensive use case for a clearer understanding of complex graph learning algorithms. Graphical abstract.

Brain age prediction using the graph neural network based on resting-state functional MRI in Alzheimer's disease

Introduction

Alzheimer's disease (AD) is a neurodegenerative disease that significantly impacts the quality of life of patients and their families. Neuroimaging-driven brain age prediction has been proposed as a potential biomarker to detect mental disorders, such as AD, aiding in studying its effects on functional brain networks. Previous studies have shown that individuals with AD display impaired resting-state functional connections. However, most studies on brain age prediction have used structural magnetic resonance imaging (MRI), with limited studies based on resting-state functional MRI (rs-fMRI).

Methods

In this study, we applied a graph neural network (GNN) model on controls to predict brain ages using rs-fMRI in patients with AD. We compared the performance of the GNN model with traditional machine learning models. Finally, the post hoc model was also used to identify the critical brain regions in AD.

Results

The experimental results demonstrate that our GNN model can predict brain ages of normal controls using rs-fMRI data from the ADNI database. Moreover the differences between brain ages and chronological ages were more significant in AD patients than in normal controls. Our results also suggest that AD is associated with accelerated brain aging and that the GNN model based on resting-state functional connectivity is an effective tool for predicting brain age.

Discussion

Our study provides evidence that rs-fMRI is a promising modality for brain age prediction in AD research, and the GNN model proves to be effective in predicting brain age. Furthermore, the effects of the hippocampus, parahippocampal gyrus, and amygdala on brain age prediction are verified.

Disease Prediction Using Graph Machine Learning Based on Electronic Health Data: A Review of Approaches and Trends

Graph machine-learning (ML) methods have recently attracted great attention and have made significant progress in graph applications. To date, most graph ML approaches have been evaluated on social networks, but they have not been comprehensively reviewed in the health informatics domain. Herein, a review of graph ML methods and their applications in the disease prediction domain based on electronic health data is presented in this study from two levels: node classification and link prediction. Commonly used graph ML approaches for these two levels are shallow embedding and graph neural networks (GNN). This study performs comprehensive research to identify articles that applied or proposed graph ML models on disease prediction using electronic health data. We considered journals and conferences from four digital library databases (i.e., PubMed, Scopus, ACM digital library, and IEEEXplore). Based on the identified articles, we review the present status of and trends in graph ML approaches for disease prediction using electronic health data. Even though GNN-based models have achieved outstanding results compared with the traditional ML methods in a wide range of disease prediction tasks, they still confront interpretability and dynamic graph challenges. Though the disease prediction field using ML techniques is still emerging, GNN-based models have the potential to be an excellent approach for disease prediction, which can be used in medical diagnosis, treatment, and the prognosis of diseases.

Predicting Physiological Response in Heart Failure Management: A Graph Representation Learning Approach using Electronic Health Records

Heart failure management is challenging due to the complex and heterogenous nature of its pathophysiology which makes the conventional treatments based on the "one size fits all" ideology not suitable. Coupling the longitudinal medical data with novel deep learning and network-based analytics will enable identifying the distinct patient phenotypic characteristics to help individualize the treatment regimen through the accurate prediction of the physiological response. In this study, we develop a graph representation learning framework that integrates the heterogeneous clinical events in the electronic health records (EHR) as graph format data, in which the patient-specific patterns and features are naturally infused for personalized predictions of lab test response. The framework includes a novel Graph Transformer Network that is equipped with a self-attention mechanism to model the underlying spatial interdependencies among the clinical events characterizing the cardiac physiological interactions in the heart failure treatment and a graph neural network (GNN) layer to incorporate the explicit temporality of each clinical event, that would help summarize the therapeutic effects induced on the physiological variables, and subsequently on the patient's health status as the heart failure condition progresses over time. We introduce a global attention mask that is computed based on event co-occurrences and is aggregated across all patient records to enhance the guidance of neighbor selection in graph representation learning. We test the feasibility of our model through detailed quantitative and qualitative evaluations on observational EHR data.

Structural Attention Graph Neural Network for Diagnosis and Prediction of COVID-19 Severity

With rapid worldwide spread of Coronavirus Disease 2019 (COVID-19), jointly identifying severe COVID-19 cases from mild ones and predicting the conversion time (from mild to severe) is essential to optimize the workflow and reduce the clinician's workload. In this study, we propose a novel framework for COVID-19 diagnosis, termed as Structural Attention Graph Neural Network (SAGNN), which can combine the multi-source information including features extracted from chest CT, latent lung structural distribution, and non-imaging patient information to conduct diagnosis of COVID-19 severity and predict the conversion time from mild to severe. Specifically, we first construct a graph to incorporate structural information of the lung and adopt graph attention network to iteratively update representations of lung segments. To distinguish different infection degrees of left and right lungs, we further introduce a structural attention mechanism. Finally, we introduce demographic information and develop a multi-task learning framework to jointly perform both tasks of classification and regression. Experiments are conducted on a real dataset with 1687 chest CT scans, which includes 1328 mild cases and 359 severe cases. Experimental results show that our method achieves the best classification (e.g., 86.86% in terms of Area Under Curve) and regression (e.g., 0.58 in terms of Correlation Coefficient) performance, compared with other comparison methods.

Focal Boundary Dice: Improved Breast Tumor Segmentation from MRI Scan

Focal Boundary Dice, a new segmentation evaluation measure, was hereby presented, with the focus on boundary quality and class imbalance. Extensive analysis was carried out across different error types with varied object sizes of imaged tumors from Magnetic Resonance Imaging (MRI) scans, and the results show that Focal Boundary Dice is significantly more adaptive than the standard Focal and Dice measures to boundary errors for imaged tumors from MRI scans and does not over-penalize errors on the division of the boundary, including smaller imaged objects. Based on Boundary Dice, the standard evaluation protocols for tumor segmentation tasks were updated by proposing the Focal Boundary Dice. The contradiction between the target and the background area, and the conflict between the importance and the attention of boundary features were mainly solved. Meanwhile, a boundary attention module was introduced to further extract the tumor edge features. The new quality measure presents several desirable characteristics, including higher accuracy in the selection of hard samples, prediction/ground-truth pairs, and balanced responsiveness with across scales, which jointly make it more suitable for segmentation evaluation than other classification-focused measures such as combined Intersection-over-Union and Boundary binary cross-entropy loss, Boundary binary cross-entropy loss and Shape-aware Loss. The experiments show that the new evaluation metrics allow boundary quality improvements and image segmentation accuracy that are generally overlooked by current Dice-based evaluation metrics and deep learning models. It is expected that the adoption of the new boundary-adaptive evaluation metrics will facilitate the rapid progress in segmentation methods, and further contribute to the improvement of classification accuracy.

Artificial intelligence techniques for neuropathological diagnostics and research

Artificial intelligence (AI) research began in theoretical neurophysiology, and the resulting classical paper on the McCulloch-Pitts mathematical neuron was written in a psychiatry department almost 80 years ago. However, the application of AI in digital neuropathology is still in its infancy. Rapid progress is now being made, which prompted this article. Human brain diseases represent distinct system states that fall outside the normal spectrum. Many differ not only in functional but also in structural terms, and the morphology of abnormal nervous tissue forms the traditional basis of neuropathological disease classifications. However, only a few countries have the medical specialty of neuropathology, and, given the sheer number of newly developed histological tools that can be applied to the study of brain diseases, a tremendous shortage of qualified hands and eyes at the microscope is obvious. Similarly, in neuroanatomy, human observers no longer have the capacity to process the vast amounts of connectomics data. Therefore, it is reasonable to assume that advances in AI technology and, especially, whole-slide image (WSI) analysis will greatly aid neuropathological practice. In this paper, we discuss machine learning (ML) techniques that are important for understanding WSI analysis, such as traditional ML and deep learning, introduce a recently developed neuropathological AI termed PathoFusion, and present thoughts on some of the challenges that must be overcome before the full potential of AI in digital neuropathology can be realized.

A fused biometrics information graph convolutional neural network for effective classification of patellofemoral pain syndrome

Patellofemoral pain syndrome (PFPS) is a common, yet misunderstood, knee pathology. Early accurate diagnosis can help avoid the deterioration of the disease. However, the existing intelligent auxiliary diagnosis methods of PFPS mainly focused on the biosignal of individuals but neglected the common biometrics of patients. In this paper, we propose a PFPS classification method based on the fused biometrics information Graph Convolution Neural Networks (FBI-GCN) which focuses on both the biosignal information of individuals and the common characteristics of patients. The method first constructs a graph which uses each subject as a node and fuses the biometrics information (demographics and gait biosignal) of different subjects as edges. Then, the graph and node information [biosignal information, including the joint kinematics and surface electromyography (sEMG)] are used as the inputs to the GCN for diagnosis and classification of PFPS. The method is tested on a public dataset which contain walking and running data from 26 PFPS patients and 15 pain-free controls. The results suggest that our method can classify PFPS and pain-free with higher accuracy (mean accuracy = 0.8531 ± 0.047) than other methods with the biosignal information of individuals as input (mean accuracy = 0.813 ± 0.048). After optimal selection of input variables, the highest classification accuracy (mean accuracy = 0.9245 ± 0.034) can be obtained, and a high accuracy can still be obtained with a 40% reduction in test variables (mean accuracy = 0.8802 ± 0.035). Accordingly, the method effectively reflects the association between subjects, provides a simple and effective aid for physicians to diagnose PFPS, and gives new ideas for studying and validating risk factors related to PFPS.

Graph deep network for optic disc and optic cup segmentation for glaucoma disease using retinal imaging

The fundus imaging method of eye screening detects eye diseases by segmenting the optic disc (OD) and optic cup (OC). OD and OC are still challenging to segment accurately. This work proposes three-layer graph-based deep architecture with an enhanced fusion method for OD and OC segmentation. CNN encoder-decoder architecture, extended graph network, and approximation via fusion-based rule are explored for connecting local and global information. A graph-based model is developed for combining local and overall knowledge. By extending feature masking, regularization of repetitive features with fusion for combining channels has been done. The performance of the proposed network is evaluated through the analysis of different metric parameters such as dice similarity coefficient (DSC), intersection of union (IOU), accuracy, specificity, sensitivity. Experimental verification of this methodology has been done using the four benchmarks publicly available datasets DRISHTI-GS, RIM-ONE for OD, and OC segmentation. In addition, DRIONS-DB and HRF fundus imaging datasets were analyzed for optimizing the model's performance based on OD segmentation. DSC metric of methodology achieved 0.97 and 0.96 for DRISHTI-GS and RIM-ONE, respectively. Similarly, IOU measures for DRISHTI-GS and RIM-ONE datasets were 0.96 and 0.93, respectively, for OD measurement. For OC segmentation, DSC and IOU were measured as 0.93 and 0.90 respectively for DRISHTI-GS and 0.83 and 0.82 for RIM-ONE data. The proposed technique improved value of metrics with most of the existing methods in terms of DSC and IOU of the results metric of the experiments for OD and OC segmentation.

PD-ResNet for Classification of Parkinson's Disease From Gait

OBJECTIVE

To develop an objective and efficient method to automatically identify Parkinson's disease (PD) and healthy control (HC).

METHODS

We design a novel model based on residual network (ResNet) architecture, named PD-ResNet, to learn the gait differences between PD and HC and between PD with different severity levels. Specifically, a polynomial elevated dimensions technique is applied to increase the dimensions of the input gait features; then, the processed data is transformed into a 3-dimensional picture as the input of PD-ResNet. The synthetic minority over-sampling technique (SMOTE), data augmentation, and early stopping technologies are adopted to improve the generalization ability. To further enhance the classification performance, a new loss function, named improved focal loss function, is developed to focus on the train of PD-ResNet on the hard samples and to discard the abnormal samples.

RESULTS

The experiments on the clinical gait dataset show that our proposed model achieves excellent performance with an accuracy of 95.51%, a precision of 94.44%, a recall of 96.59%, a specificity of 94.44%, and an F1-score of 95.50%. Moreover, the accuracy, precision, recall, specificity, and F1-score for the classification of early PD and HC are 92.03%, 94.20%, 90.28%, 93.94%, and 92.20%, respectively. Furthermore, the accuracy, precision, recall, specificity, and F1-score for the classification of PD with different severity levels are 92.03%, 94.29%, 90.41%, 93.85%, and 92.31%, respectively.

CONCLUSION

Our proposed method shows better performance than the traditional machine learning and deep learning methods.

CLINICAL IMPACT

The experimental results show that the proposed method is clinically meaningful for the objective assessment of gait motor impairment for PD patients.

PercolationDF: A percolation-based medical diagnosis framework

Goal: With the continuing shortage and unequal distribution of medical resources, our objective is to develop a general diagnosis framework that utilizes a smaller amount of electronic medical records (EMRs) to alleviate the problem that the data volume requirement of prevailing models is too vast for medical institutions to afford. Methods: The framework proposed contains network construction, network expansion, and disease diagnosis methods. In the first two stages above, the knowledge extracted from EMRs is utilized to build and expense an EMR-based medical knowledge network (EMKN) to model and represent the medical knowledge. Then, percolation theory is modified to diagnose EMKN. Result: Facing the lack of data, our framework outperforms naïve Bayes networks, neural networks and logistic regression, especially in the top-10 recall. Out of 207 test cases, 51.7% achieved 100% in the top-10 recall, 21% better than what was achieved in one of our previous studies. Conclusion: The experimental results show that the proposed framework may be useful for medical knowledge representation and diagnosis. The framework effectively alleviates the lack of data volume by inferring the knowledge modeled in EMKN. Significance: The proposed framework not only has applications for diagnosis but also may be extended to other domains to represent and model the knowledge and inference on the representation.

Neonatal Jaundice Diagnosis Using a Smartphone Camera Based on Eye, Skin, and Fused Features with Transfer Learning

Neonatal jaundice is a common condition worldwide. Failure of timely diagnosis and treatment can lead to death or brain injury. Current diagnostic approaches include a painful and time-consuming invasive blood test and non-invasive tests using costly transcutaneous bilirubinometers. Since periodic monitoring is crucial, multiple efforts have been made to develop non-invasive diagnostic tools using a smartphone camera. However, existing works rely either on skin or eye images using statistical or traditional machine learning methods. In this paper, we adopt a deep transfer learning approach based on eye, skin, and fused images. We also trained well-known traditional machine learning models, including multi-layer perceptron (MLP), support vector machine (SVM), decision tree (DT), and random forest (RF), and compared their performance with that of the transfer learning model. We collected our dataset using a smartphone camera. Moreover, unlike most of the existing contributions, we report accuracy, precision, recall, f-score, and area under the curve (AUC) for all the experiments and analyzed their significance statistically. Our results indicate that the transfer learning model performed the best with skin images, while traditional models achieved the best performance with eyes and fused features. Further, we found that the transfer learning model with skin features performed comparably to the MLP model with eye features.