Uncovering Flat and Hierarchical Topics by Community Discovery on Word Co-occurrence Network.

Topic modeling aims to discover latent themes in collections of text documents. It has various applications across fields such as sociology, opinion analysis, and media studies. In such areas, it is essential to have easily interpretable, diverse, and coherent topics. An efficient topic modeling technique should accurately identify flat and hierarchical topics, especially useful in disciplines where topics can be logically arranged into a tree format. In this paper, we propose Community Topic, a novel algorithm that exploits word co-occurrence networks to mine communities and produces topics. We also evaluate the proposed approach using several metrics and compare it with usual baselines, confirming its good performances. Community Topic enables quick identification of flat topics and topic hierarchy, facilitating the on-demand exploration of sub- and super-topics. It also obtains good results on datasets in different languages.

General value functions for fault detection in multivariate time series data.

One of the greatest challenges to the automated production of goods is equipment malfunction. Ideally, machines should be able to automatically predict and detect operational faults in order to minimize downtime and plan for timely maintenance. While traditional condition-based maintenance (CBM) involves costly sensor additions and engineering, machine learning approaches offer the potential to learn from already existing sensors. Implementations of data-driven CBM typically use supervised and semi-supervised learning to classify faults. In addition to a large collection of operation data, records of faulty operation are also necessary, which are often costly to obtain. Instead of classifying faults, we use an approach to detect abnormal behaviour within the machine's operation. This approach is analogous to semi-supervised anomaly detection in machine learning (ML), with important distinctions in experimental design and evaluation specific to the problem of industrial fault detection. We present a novel method of machine fault detection using temporal-difference learning and General Value Functions (GVFs). Using GVFs, we form a predictive model of sensor data to detect faulty behaviour. As sensor data from machines is not i.i.d. but closer to Markovian sampling, temporal-difference learning methods should be well suited for this data. We compare our GVF outlier detection (GVFOD) algorithm to a broad selection of multivariate and temporal outlier detection methods, using datasets collected from a tabletop robot emulating the movement of an industrial actuator. We find that not only does GVFOD achieve the same recall score as other multivariate OD algorithms, it attains significantly higher precision. Furthermore, GVFOD has intuitive hyperparameters which can be selected based upon expert knowledge of the application. Together, these findings allow for a more reliable detection of abnormal machine behaviour to allow ideal timing of maintenance; saving resources, time and cost.

A Collaborative Self-supervised Domain Adaptation for Low-Quality Medical Image Enhancement.

Medical image analysis techniques have been employed in diagnosing and screening clinical diseases. However, both poor medical image quality and illumination style inconsistency increase uncertainty in clinical decision-making, potentially resulting in clinician misdiagnosis. The majority of current image enhancement methods primarily concentrate on enhancing medical image quality by leveraging high-quality reference images, which are challenging to collect in clinical applications. In this study, we address image quality enhancement within a fully self-supervised learning setting, wherein neither high-quality images nor paired images are required. To achieve this goal, we investigate the potential of self-supervised learning combined with domain adaptation to enhance the quality of medical images without the guidance of high-quality medical images. We design a Domain Adaptation Self-supervised Quality Enhancement framework, called DASQE. More specifically, we establish multiple domains at the patch level through a designed rule-based quality assessment scheme and style clustering. To achieve image quality enhancement and maintain style consistency, we formulate the image quality enhancement as a collaborative self-supervised domain adaptation task for disentangling the low-quality factors, medical image content, and illumination style characteristics by exploring intrinsic supervision in the low-quality medical images. Finally, we perform extensive experiments on six benchmark datasets of medical images, and the experimental results demonstrate that DASQE attains state-of-the-art performance. Furthermore, we explore the impact of the proposed method on various clinical tasks, such as retinal fundus vessel/lesion segmentation, nerve fiber segmentation, polyp segmentation, skin lesion segmentation, and disease classification. The results demonstrate that DASQE is advantageous for diverse downstream image analysis tasks.

Label correlation guided discriminative label feature learning for multi-label chest image classification.

BACKGROUND AND OBJECTIVE: Multi-label Chest X-ray (CXR) images often contain rich label relationship information, which is beneficial to improve classification performance. However, because of the intricate relationships among labels, most existing works fail to effectively learn and make full use of the label correlations, resulting in limited classification performance. In this study, we propose a multi-label learning framework that learns and leverages the label correlations to improve multi-label CXR image classification. METHODS: In this paper, we capture the global label correlations through the self-attention mechanism. Meanwhile, to better utilize label correlations for guiding feature learning, we decompose the image-level features into label-level features. Furthermore, we enhance label-level feature learning in an end-to-end manner by a consistency constraint between global and local label correlations, and a label correlation guided multi-label supervised contrastive loss. RESULTS: To demonstrate the superior performance of our proposed approach, we conduct three times 5-fold cross-validation experiments on the CheXpert dataset. Our approach obtains an average F1 score of 44.6% and an AUC of 76.5%, achieving a 7.7% and 1.3% improvement compared to the state-of-the-art results. CONCLUSION: More accurate label correlations and full utilization of the learned label correlations help learn more discriminative label-level features. Experimental results demonstrate that our approach achieves exceptionally competitive performance compared to the state-of-the-art algorithms.

Graph Self-Supervised Learning With Application to Brain Networks Analysis.

The less training data and insufficient supervision limit the performance of the deep supervised models for brain disease diagnosis. It is significant to construct a learning framework that can capture more information in limited data and insufficient supervision. To address these issues, we focus on self-supervised learning and aim to generalize the self-supervised learning to the brain networks, which are non-Euclidean graph data. More specifically, we propose an ensemble masked graph self-supervised framework named BrainGSLs, which incorporates 1) a local topological-aware encoder that takes the partially visible nodes as input and learns these latent representations, 2) a node-edge bi-decoder that reconstructs the masked edges by the representations of both the masked and visible nodes, 3) a signal representation learning module for capturing temporal representations from BOLD signals and 4) a classifier used for the classification. We evaluate our model on three real medical clinical applications: diagnosis of Autism Spectrum Disorder (ASD), diagnosis of Bipolar Disorder (BD) and diagnosis of Major Depressive Disorder (MDD). The results suggest that the proposed self-supervised training has led to remarkable improvement and outperforms state-of-the-art methods. Moreover, our method is able to identify the biomarkers associated with the diseases, which is consistent with the previous studies. We also explore the correlation of these three diseases and find the strong association between ASD and BD. To the best of our knowledge, our work is the first attempt of applying the idea of self-supervised learning with masked autoencoder on the brain network analysis.

MCA-UNet: multi-scale cross co-attentional U-Net for automatic medical image segmentation.

Medical image segmentation is a challenging task due to the high variation in shape, size and position of infections or lesions in medical images. It is necessary to construct multi-scale representations to capture image contents from different scales. However, it is still challenging for U-Net with a simple skip connection to model the global multi-scale context. To overcome it, we proposed a dense skip-connection with cross co-attention in U-Net to solve the semantic gaps for an accurate automatic medical image segmentation. We name our method MCA-UNet, which enjoys two benefits: (1) it has a strong ability to model the multi-scale features, and (2) it jointly explores the spatial and channel attentions. The experimental results on the COVID-19 and IDRiD datasets suggest that our MCA-UNet produces more precise segmentation performance for the consolidation, ground-glass opacity (GGO), microaneurysms (MA) and hard exudates (EX). The source code of this work will be released via https://github.com/McGregorWwww/MCA-UNet/.

Developing a triage predictive model for access to a spinal surgeon using clinical variables and natural language processing of radiology reports.

PURPOSE: To utilize natural language processing (NLP) of MRI reports and various clinical variables to develop a preliminary model predictive of the need for surgery in patients with low back and neck pain. Such a model would be beneficial for informing clinical practice decisions and help reduce the number of unnecessary surgical referrals, streamlining the surgical process. METHODS: A historical cohort study was conducted using de-identified data from patients referred to a spine assessment clinic. Various demographic, clinical, and radiological variables were included as potential predictors. Full-text radiology reports of patients' MRI findings were vectorized using NLP before applying machine learning algorithms to develop models predicting who underwent surgery. Outputs from these models were then entered into a logistic regression model with clinical variables to develop a preliminary model predictive of surgical recommendations. RESULTS: Of the 398 patients assessed, 71 underwent spine surgery. NLP variables were significant predictors in univariate analysis but did not remain in the final logistic regression model. An outcome of receiving surgery was predicted by a primary symptom of low back and leg pain (adjusted odds ratio 2.81), distal pain indicated by a pain diagram (adjusted odds ratio 2.49) and self-reported difficulties walking (adjusted odds ratio 2.73). CONCLUSION: A logistic regression model was created to predict which patients may require spine surgery. Simple clinical variables appeared more predictive than variables created using NLP. However, additional research with more data samples is needed to validate this model and fully evaluate the usefulness of NLP for this task.

BrainTGL: A dynamic graph representation learning model for brain network analysis.

Modeling the dynamics characteristics in functional brain networks (FBNs) is important for understanding the functional mechanism of the human brain. However, the current works do not fully consider the potential complex spatial and temporal correlations in human brain. To solve this problem, we propose a temporal graph representation learning framework for brain networks (BrainTGL). The framework involves a temporal graph pooling for eliminating the noisy edges as well as data inconsistency, and a dual temporal graph learning for capturing the spatio-temporal features of the temporal graphs. The proposed method has been evaluated in both tasks of brain disease (ASD, MDD and BD) diagnosis/gender classification (classification task) and subtype identification (clustering task) on the four datasets: Human Connectome Project (HCP), Autism Brain Imaging Data Exchange (ABIDE), NMU-MDD and NMU-BD. A large improvement is achieved for the ASD diagnosis. Specifically, our model outperforms the GroupINN and ST-GCN by an average increase of 4.2% and 8.6% on accuracy, respectively, demonstrating its advantages in comparison to the state-of-the-art methods based on functional connectivity features or learned spatio-temporal features. The results demonstrate that learning the spatial-temporal brain network representation for modeling dynamics characteristics in FBNs can improve the model's performance on both disease diagnosis and subtype identification tasks for multiple disorders. Apart from performance, the improvements of computational efficiency and convergence speed reduce training costs.

WS-LungNet: A two-stage weakly-supervised lung cancer detection and diagnosis network.

Computer-aided lung cancer diagnosis (CAD) system on computed tomography (CT) helps radiologists guide preoperative planning and prognosis assessment. The flexibility and scalability of deep learning methods are limited in lung CAD. In essence, two significant challenges to be solved are (1) Label scarcity due to cost annotations of CT images by experienced domain experts, and (2) Label inconsistency between the observed nodule malignancy and the patients' pathology evaluation. These two issues can be considered weak label problems. We address these issues in this paper by introducing a weakly-supervised lung cancer detection and diagnosis network (WS-LungNet), consisting of a semi-supervised computer-aided detection (Semi-CADe) that can segment 3D pulmonary nodules based on unlabeled data through adversarial learning to reduce label scarcity, as well as a cross-nodule attention computer-aided diagnosis (CNA-CADx) for evaluating malignancy at the patient level by modeling correlations between nodules via cross-attention mechanisms and thereby eliminating label inconsistency. Through extensive evaluations on the LIDC-IDRI public database, we show that our proposed method achieves 82.99% competition performance metric (CPM) on pulmonary nodule detection and 88.63% area under the curve (AUC) on lung cancer diagnosis. Extensive experiments demonstrate the advantage of WS-LungNet on nodule detection and malignancy evaluation tasks. Our promising results demonstrate the benefits and flexibility of the semi-supervised segmentation with adversarial learning and the nodule instance correlation learning with the attention mechanism. The results also suggest that making use of the unlabeled data and taking the relationship among nodules in a case into account are essential for lung cancer detection and diagnosis.

Exploiting task relationships for Alzheimer's disease cognitive score prediction via multi-task learning.

Alzheimer's disease (AD) is highly prevalent and a significant cause of dementia and death in elderly individuals. Motivated by breakthroughs of multi-task learning (MTL), efforts have been made to extend MTL to improve the Alzheimer's disease cognitive score prediction by exploiting structure correlation. Though important and well-studied, three key aspects are yet to be fully handled in an unified framework: (i) appropriately modeling the inherent task relationship; (ii) fully exploiting the task relatedness by considering the underlying feature structure. (iii) automatically determining the weight of each task. To this end, we present the Bi-Graph guided self-Paced Multi-Task Feature Learning (BGP-MTFL) framework for exploring the relationship among multiple tasks to improve overall learning performance of cognitive score prediction. The framework consists of the two correlation regularization for features and tasks, ℓ2,1 regularization and self-paced learning scheme. Moreover, we design an efficient optimization method to solve the non-smooth objective function of our approach based on the Alternating Direction Method of Multipliers (ADMM) combined with accelerated proximal gradient (APG). The proposed model is comprehensively evaluated on the Alzheimer's disease neuroimaging initiative (ADNI) datasets. Overall, the proposed algorithm achieves an nMSE (normalized Mean Squared Error) of 3.923 and an wR (weighted R-value) of 0.416 for predicting eighteen cognitive scores, respectively. The empirical study demonstrates that the proposed BGP-MTFL model outperforms the state-of-the-art AD prediction approaches and enables identifying more stable biomarkers.

Exploring interpretable graph convolutional networks for autism spectrum disorder diagnosis.

PURPOSE: Finding the biomarkers associated with autism spectrum disorder (ASD) is helpful for understanding the underlying roots of the disorder and can lead to earlier diagnosis and more targeted treatments. In essence, we are faced with two challenges (i) how to learn a node representation and a clean graph structure from original graph data with high dimensionality and (ii) how to jointly model the procedure of node representation learning, structure learning and graph classification. METHODS: We propose FSL-BrainNet, an interpretable graph convolution network (GCN) model for jointly Learning of node Features and clean Structures in brain networks for automatic brain network classification and interpretation. We formulate an end-to-end trainable and interpretable framework for graph classification and biomarkers (salient brain regions and potential subnetworks) identification. RESULTS: The experimental results on the ABIDE dataset show that our proposed methods not only achieve improved prediction performance compared with the state-of-the-art methods, but also find a compact set of highly suggestive biomarkers including relevant brain regions and subnetworks to ASD. CONCLUSION: Through node feature learning and structure learning, our model can simultaneously select important brain regions and identify subnetworks.

Identifying Potential Gamification Elements for A New Chatbot for Families With Neurodevelopmental Disorders: User-Centered Design Approach.

BACKGROUND: Chatbots have been increasingly considered for applications in the health care field. However, it remains unclear how a chatbot can assist users with complex health needs, such as parents of children with neurodevelopmental disorders (NDDs) who need ongoing support. Often, this population must deal with complex and overwhelming health information, which can make parents less likely to use a software that may be very helpful. An approach to enhance user engagement is incorporating game elements in nongame contexts, known as gamification. Gamification needs to be tailored to users; however, there has been no previous assessment of gamification use in chatbots for NDDs. OBJECTIVE: We sought to examine how gamification elements are perceived and whether their implementation in chatbots will be well received among parents of children with NDDs. We have discussed some elements in detail as the initial step of the project. METHODS: We performed a narrative literature review of gamification elements, specifically those used in health and education. Among the elements identified in the literature, our health and social science experts in NDDs prioritized five elements for in-depth discussion: goal setting, customization, rewards, social networking, and unlockable content. We used a qualitative approach, which included focus groups and interviews with parents of children with NDDs (N=21), to assess the acceptability of the potential implementation of these elements in an NDD-focused chatbot. Parents were asked about their opinions on the 5 elements and to rate them. Video and audio recordings were transcribed and summarized for emerging themes, using deductive and inductive thematic approaches. RESULTS: From the responses obtained from 21 participants, we identified three main themes: parents of children with NDDs were familiar with and had positive experiences with gamification; a specific element (goal setting) was important to all parents, whereas others (customization, rewards, and unlockable content) received mixed opinions; and the social networking element received positive feedback, but concerns about information accuracy were raised. CONCLUSIONS: We showed for the first time that parents of children with NDDs support gamification use in a chatbot for NDDs. Our study illustrates the need for a user-centered design in the medical domain and provides a foundation for researchers interested in developing chatbots for populations that are medically vulnerable. Future studies exploring wide range of gamification elements with large number of potential users are needed to understand the impact of gamification elements in enhancing knowledge mobilization.

Developing, Implementing, and Evaluating an Artificial Intelligence-Guided Mental Health Resource Navigation Chatbot for Health Care Workers and Their Families During and Following the COVID-19 Pandemic: Protocol for a Cross-sectional Study.

BACKGROUND: Approximately 1 in 3 Canadians will experience an addiction or mental health challenge at some point in their lifetime. Unfortunately, there are multiple barriers to accessing mental health care, including system fragmentation, episodic care, long wait times, and insufficient support for health system navigation. In addition, stigma may further reduce an individual's likelihood of seeking support. Digital technologies present new and exciting opportunities to bridge significant gaps in mental health care service provision, reduce barriers pertaining to stigma, and improve health outcomes for patients and mental health system integration and efficiency. Chatbots (ie, software systems that use artificial intelligence to carry out conversations with people) may be explored to support those in need of information or access to services and present the opportunity to address gaps in traditional, fragmented, or episodic mental health system structures on demand with personalized attention. The recent COVID-19 pandemic has exacerbated even further the need for mental health support among Canadians and called attention to the inefficiencies of our system. As health care workers and their families are at an even greater risk of mental illness and psychological distress during the COVID-19 pandemic, this technology will be first piloted with the goal of supporting this vulnerable group. OBJECTIVE: This pilot study seeks to evaluate the effectiveness of the Mental Health Intelligent Information Resource Assistant in supporting health care workers and their families in the Canadian provinces of Alberta and Nova Scotia with the provision of appropriate information on mental health issues, services, and programs based on personalized needs. METHODS: The effectiveness of the technology will be assessed via voluntary follow-up surveys and an analysis of client interactions and engagement with the chatbot. Client satisfaction with the chatbot will also be assessed. RESULTS: This project was initiated on April 1, 2021. Ethics approval was granted on August 12, 2021, by the University of Alberta Health Research Board (PRO00109148) and on April 21, 2022, by the Nova Scotia Health Authority Research Ethics Board (1027474). Data collection is anticipated to take place from May 2, 2022, to May 2, 2023. Publication of preliminary results will be sought in spring or summer 2022, with a more comprehensive evaluation completed by spring 2023 following the collection of a larger data set. CONCLUSIONS: Our findings can be incorporated into public policy and planning around mental health system navigation by Canadian mental health care providers-from large public health authorities to small community-based, not-for-profit organizations. This may serve to support the development of an additional touch point, or point of entry, for individuals to access the appropriate services or care when they need them, wherever they are. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/33717.

Modeling global and local label correlation with graph convolutional networks for multi-label chest X-ray image classification.

The diagnosis of chest diseases is a challenging task for assessing thousands of radiology subjects. Their diagnosis decisions heavily rely on the expert radiologists' manual annotations. It is important to develop automated analysis methods for the computer-aided diagnosis of chest diseases on chest radiography. To explore the label relationship and improve the diagnosis performance, we present an end-to-end multi-label learning framework for jointly modeling the global and local label correlation, called GL-MLL that (1) explores the label correlation from a globally static view and a locally adaptive view, (2) considers the imbalanced class distribution, and (3) focuses on capturing label-specific features in image-level representation. We validate the performance of the proposed framework on the CheXpert dataset. The results demonstrate that the proposed GL-MLL outperforms state-of-the-art approaches. The code is available at https://github.com/llt1836/GL-MLL.

Modeling the dynamic brain network representation for autism spectrum disorder diagnosis.

The dynamic functional connectivity analysis provides valuable information for understanding functional brain activity underlying different cognitive processes. Modeling spatio-temporal dynamics in functional brain networks is critical for underlying the functional mechanism of autism spectrum disorder (ASD). In our study, we propose a machine learning approach for the classification of neurological disorders while providing an interpretable framework, which thoroughly captures spatio-temporal features in resting-state functional magnetic resonance imaging (rs-fMRI) data. Specifically, we first transform rs-fMRI time-series into temporal multi-graph using the sliding window technique. A temporal multi-graph clustering is then designed to eliminate the inconsistency of the temporal multi-graph series. Then, a graph structure-aware LSTM (GSA-LSTM) is further proposed to capture the spatio-temporal embedding for temporal graphs. Furthermore, The proposed GSA-LSTM can not only capture discriminative features for prediction but also impute the incomplete graphs for the temporal multi-graph series. Extensive experiments on the autism brain imaging data exchange (ABIDE) dataset demonstrate that the proposed dynamic brain network embedding learning outperforms the state-of-the-art brain network classification models. Furthermore, the obtained clustering results are consistent with the previous neuroimaging-derived evidence of biomarkers for autism spectrum disorder (ASD).

Collaborative learning of graph generation, clustering and classification for brain networks diagnosis.

PURPOSE: Accurate diagnosis of autism spectrum disorder (ASD) plays a key role in improving the condition and quality of life for patients. In this study, we mainly focus on ASD diagnosis with functional brain networks (FBNs). The major challenge for brain networks modeling is the high dimensional connectivity in brain networks and limited number of subjects, which hinders the classification capability of graph convolutional networks (GCNs). METHOD: To alleviate the influence of the limited data and high dimensional connectivity, we introduce a unified three-stage graph learning framework for brain network classification, involving multi-graph clustering, graph generation and graph classification. The framework combining Graph Generation, Clustering and Classification Networks (GraphCGC-Net) enhances the critical connections by multi-graph clustering (MGC) with a supervision scheme, and generates realistic brain networks by simultaneously preserving the global consistent distribution and local topology properties. RESULTS: To demonstrate the effectiveness of our approach, we evaluate the performance of the proposed method on the Autism Brain Imaging Data Exchange (ABIDE) dataset and conduct extensive experiments on the ASD classification problem. Our proposed method achieves an average accuracy of 70.45% and an AUC of 72.76% on ABIDE. Compared with the traditional GCN model, the proposed GraphCGC-Net obtains 9.3%, and 10.64% improvement in terms of accuracy and AUC metrics, respectively. CONCLUSION: The comprehensive experiments demonstrate that our GraphCGC-Net is effective for graph classification in brain disorders diagnosis. Moreover, we find that MGC can generate biologically meaningful subnetworks, which is highly consistent with the previous neuroimaging-derived biomarker evidence of ASD. More importantly, the promising results suggest that applying generative adversarial networks (GANs) in brain networks to improve the classification performance is worth further investigation.

Collaborative learning of weakly-supervised domain adaptation for diabetic retinopathy grading on retinal images.

Early detection and treatment of diabetic retinopathy (DR) can significantly reduce the risk of vision loss in patients. In essence, we are faced with two challenges: (i) how to simultaneously achieve domain adaptation from the different domains and (ii) how to build an interpretable multi-instance learning (MIL) on the target domain in an end-to-end framework. In this paper, we address these issues and propose a unified weakly-supervised domain adaptation framework, which consists of three components: domain adaptation, instance progressive discriminator and multi-instance learning with attention. The method models the relationship between the patches and images in the target domain with a multi-instance learning scheme and an attention mechanism. Meanwhile, it incorporates all available information from both source and target domains for a jointly learning strategy. We validate the performance of the proposed framework for DR grading on the Messidor dataset and the large-scale Eyepacs dataset. The experimental results demonstrate that it achieves an average accuracy of 0.949 (95% CI 0.931-0.958)/0.764 (95% CI 0.755-0.772) and an average AUC value of 0.958 (95% CI 0.945-0.962)/0.749 (95% CI 0.732-0.761) for binary-class/multi-class classification tasks on the Messidor dataset. Moreover, the proposed method achieves an accuracy of 0.887 and a quadratic weighted kappa score value of 0.860 on the Eyepacs dataset, outperforming the state-of-the-art approaches. Comprehensive experiments confirm the effectiveness of the approach in terms of both grading performance and interpretability. The source code is available at https://github.com/HouQingshan/WAD-Net.

MVS-GCN: A prior brain structure learning-guided multi-view graph convolution network for autism spectrum disorder diagnosis.

PURPOSE: Recently, functional brain networks (FBN) have been used for the classification of neurological disorders, such as Autism Spectrum Disorders (ASD). Neurological disorder diagnosis with FBN is a challenging task due to the high heterogeneity in subjects and the noise correlations in brain networks. Meanwhile, it is challenging for the existing deep learning models to provide interpretable insights into the brain network. We propose a machine learning approach for the classification of neurological disorders while providing an interpretable framework. METHOD: In this paper, we build upon graph neural network in order to learn effective representations for brain networks in an end-to-end fashion. Specifically, we present a prior brain structure learning-guided multi-view graph convolutional neural network (MVS-GCN), which collaborates the graph structure learning and multi-task graph embedding learning to improve the classification performance and identify the potential functional subnetworks. RESULTS: To demonstrate the effectiveness of our approach, we evaluate the performance of the proposed method on the Autism Brain Imaging Data Exchange (ABIDE) dataset and Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. The experimental results indicate that our MVS-GCN can achieve enhanced performance compared with state-of-the-art methods. Notably, MVS-GCN achieves an average accuracy/AUC of 69.38%/69.01% on the ABIDE dataset. Moreover, the obtained results from our model show high consistency with the previous neuroimaging derived evidence of within and between-networks biomarkers for ASD. The discovered subnetworks are used as evidence for the proposed MVS-GCN model. CONCLUSION: The proposed MVS-GCN method performs a graph embedding learning from the multi-views graph embedding learning perspective while considering eliminating the heterogeneity in brain networks and enhancing the feature representation of functional subnetworks, which can capture the essential embeddings to improve the classification performance of brain disorder diagnosis. The code is available at https://github.com/GuangqiWen/MVS-GCN.

Image Quality Assessment Guided Collaborative Learning of Image Enhancement and Classification for Diabetic Retinopathy Grading.

Diabetic retinopathy (DR) is one of the most serious complications of diabetes and is a prominent cause of permanent blindness. However, the low-quality fundus images increase the uncertainty of clinical diagnosis, resulting in a significant decrease on the grading performance of the fundus images. Therefore, enhancing the image quality is essential for predicting the grade level in DR diagnosis. In essence, we are faced with three challenges: (I) How to appropriately evaluate the quality of fundus images; (II) How to effectively enhance low-quality fundus images for providing reliable fundus images to ophthalmologists or automated analysis systems; (III) How to jointly train the quality assessment and enhancement for improving the DR grading performance. Considering the importance of image quality assessment and enhancement for DR grading, we propose a collaborative learning framework to jointly train the subnetworks of the image quality assessment as well as enhancement, and DR disease grading in a unified framework. The key contribution of the proposed framework lies in modelling the potential correlation of these tasks and the joint training of these subnetworks, which significantly improves the fundus image quality and DR grading performance. Our framework is a general learning model, which may be useful in other medical images with low-quality data. Extensive experimental results have shown that our method outperforms state-of-the-art DR grading methods by a considerable 73.6% ACC/71.2% Kappa and 88.5% ACC/86.3% Kappa on Messidor and EyeQ benchmark datasets, respectively. In addition, our method significantly enhances the low-quality fundus images while preserving fundus structure features and lesion information. To make the framework more general, we also evaluate the enhancement results in more downstream tasks, such as vessel segmentation.

TE-HI-GCN: An Ensemble of Transfer Hierarchical Graph Convolutional Networks for Disorder Diagnosis.

Accurate diagnosis of psychiatric disorders plays a critical role in improving the quality of life for patients and potentially supports the development of new treatments. Graph convolutional networks (GCNs) are shown to be successful in modeling applications with graph structures. However, training an accurate GCNs model for brain networks faces several challenges, including high dimensional and noisy correlation in the brain networks, limited labeled training data, and depth limitation of GCN learning. Generalization and interpretability are important in developing predictive models for clinical diagnosis. To address these challenges, we proposed an ensemble framework involving hierarchical GCN and transfer learning for sparse brain networks, which allows GCN to capture the intrinsic correlation among the subjects and domains, to improve the network embedding learning for disease diagnosis. Extensive experiments on two real medical clinical applications: diagnosis of Autism spectrum disorder (ASD) and diagnosis of Alzheimer's disease (AD) on both the ADNI and ABIDE databases, showing the effectiveness of the proposed framework. We achieved state-of-the-art accuracy and AUC for AD/MCI and ASD/NC (Normal control) classification in comparison with studies that used functional connectivity as features or GCN models. The proposed TE-HI-GCN model achieves the best classification performance, leading to about 27.93% (31.38%) improvement for ASD and 16.86% (44.50%) for AD in terms of accuracy and AUC compared with the traditional GCN model. Moreover, the obtained clustering results show high correspondence with the previous neuroimaging derived evidence of within and between-networks biomarkers for ASD. The discovered subnetworks are used as evidence for the proposed TE-HI-GCN model. Furthermore, this work is the first attempt of transfer learning on the two related disorder domains to uncover the correlation among the two diseases with a transfer learning scheme.