Multi-Parameter MRI for Evaluating Glymphatic Impairment and White-Matter Abnormalities and Discriminating Refractory Epilepsy in Children

OBJECTIVE

To explore glymphatic impairment in pediatric refractory epilepsy (RE) using multi-parameter magnetic resonance imaging (MRI), assess its relationship with white-matter (WM) abnormalities and clinical indicators, and preliminarily evaluate the performance of multi-parameter MRI in discriminating RE from drug-sensitive epilepsy (DSE).

MATERIALS AND METHODS

We retrospectively included 70 patients with DSE (mean age, 9.7 ± 3.5 years; male:female, 37:33) and 26 patients with RE (9.0 ± 2.9 years; male:female, 12:14). The diffusion tensor imaging analysis along the perivascular space (DTI-ALPS) index as well as fractional anisotropy (FA), mean diffusivity (MD), and nodal efficiency values were measured and compared between patients with RE and DSE. With sex and age as covariables, differences in the FA and MD values were analyzed using tract-based spatial statistics, and nodal efficiency was analyzed using a linear model. Pearson's partial correlation was analyzed. Receiver operating characteristic (ROC) curves were used to evaluate the discrimination performance of the MRI-based machine-learning models through five-fold cross-validation.

RESULTS

In the RE group, FA decreased and MD increased in comparison with the corresponding values in the DSE group, and these differences mainly involved the callosum, right and left corona radiata, inferior and superior longitudinal fasciculus, and posterior thalamic radiation (threshold-free cluster enhancement, P < 0.05). The RE group also showed reduced nodal efficiency, which mainly involved the limbic system, default mode network, and visual network (false discovery rate, P < 0.05), and significantly lower DTI-ALPS index (F = 2.0, P = 0.049). The DTI-ALPS index was positively correlated with FA (0.25 ≤ r ≤ 0.32) and nodal efficiency (0.22 ≤ r ≤ 0.37), and was negatively correlated with the MD (-0.24 ≤ r ≤ -0.34) and seizure frequency (r = -0.47). A machine-learning model combining DTI-ALPS, FA, MD, and nodal efficiency achieved a cross-validated ROC curve area of 0.83 (sensitivity, 78.2%; specificity, 84.8%).

CONCLUSION

Pediatric patients with RE showed impaired glymphatic function in comparison with patients with DSE, which was correlated with WM abnormalities and seizure frequency. Multi-parameter MRI may be feasible for distinguishing RE from DSE.

Fast blood flow index reconstruction of diffuse correlation spectroscopy using a back-propagation-free data-driven algorithm

This study introduces a fast and accurate online training method for blood flow index (BFI) and relative BFI (rBFI) reconstruction in diffuse correlation spectroscopy (DCS). We implement rigorous mathematical models to simulate the auto-correlation functions (g 2) for semi-infinite homogeneous and three-layer human brain models. We implemented a fast online training algorithm known as random vector functional link (RVFL) to reconstruct BFI from noisy g 2. We extensively evaluated RVFL regarding both speed and accuracy for training and inference. Moreover, we compared RVFL with extreme learning machine (ELM) architecture, a conventional convolutional neural network (CNN), and three fitting algorithms. Results from semi-infinite and three-layer models indicate that RVFL achieves higher accuracy than the other algorithms, as evidenced by comprehensive metrics. While RVFL offers comparable accuracy to CNNs, it boosts training speeds that are 3900-fold faster and inference speeds that are 19.8-fold faster, enhancing its generalizability across different experimental settings. We also used g 2 from one- and three-layer Monte Carlo (MC)-based in-silico simulations, as well as from analytical models, to compare the accuracy and consistency of the results obtained from RVFL and ELM. Furthermore, we discuss how RVFL is more suitable for embedded hardware due to its lower computational complexity than ELM and CNN for training and inference.

Comprehensive review of literature on Parkinson's disease diagnosis

PD is one of the neurodegenerative illnesses affects 1-2 individuals per 1000 people over the age of 60 and has a 1 % prevalence rate. It affects both the non-motor and motor aspects of movement, including initiation, execution, and planning. Prior to behavioral and cognitive abnormalities like dementia, movement-related symptoms including stiffness, tremor, and initiation issues may be observed. Patients with PD have substantial reductions in social interactions, quality of life (QoL), and familial ties, as well as significant financial burdens on both the individual and societal levels. The healthcare industry is mostly using ML approaches with the modalities like image, signal, and data as well. Therefore, this survey aims to conduct a review of 50 articles on Parkinson disease diagnosis using different modalities. The survey includes (i) Classifying multimodal articles on Parkinson disease diagnosis (image, signal, data) using various machine learning, deep learning, and other approaches. (ii) Analyzing different datasets, simulation tools used in the existing papers. (iii)Examining certain performance measures, assessing the best performance, and chronological review of reviewed paper. Finally, the review determines the research gaps and obstacles in this research topic.

PD-ARnet: a deep learning approach for Parkinson's disease diagnosis from resting-state fMRI

Objective. The clinical diagnosis of Parkinson's disease (PD) relying on medical history, clinical symptoms, and signs is subjective and lacks sensitivity. Resting-state fMRI (rs-fMRI) has been demonstrated to be an effective biomarker for diagnosing PD.Approach.This study proposes a deep learning approach for the automatic diagnosis of PD using rs-fMRI, named PD-ARnet. Specifically, PD-ARnet utilizes Amplitude of Low Frequency Fluctuations and Regional Homogeneity extracted from rs-fMRI as inputs. The inputs are then processed through a developed dual-branch 3D feature extractor to perform advanced feature extraction. During this process, a Correlation-Driven weighting module is applied to capture complementary information from both features. Subsequently, the Attention-Enhanced fusion module is developed to effectively merge two types of features, and the fused features are input into a fully connected layer for automatic diagnosis classification.Main results.Using 145 samples from the PPMI dataset to evaluate the detection performance of PD-ARnet, the results indicated an average classification accuracy of 91.6% (95% confidence interval [CI]: 90.9%, 92.4%), precision of 94.7% (95% CI: 94.2%, 95.1%), recall of 86.2% (95% CI: 84.9%, 87.4%), F1 score of 90.2% (95% CI: 89.3%, 91.1%), and AUC of 92.8% (95% CI: 91.1%, 95.0%).Significance.The proposed method has the potential to become a clinical auxiliary diagnostic tool for PD, reducing subjectivity in the diagnostic process, and enhancing diagnostic efficiency and consistency.

Parkinson's severity diagnosis explainable model based on 3D multi-head attention residual network

The severity evaluation of Parkinson's disease (PD) is of great significance for the treatment of PD. However, existing methods either have limitations based on prior knowledge or are invasive methods. To propose a more generalized severity evaluation model, this paper proposes an explainable 3D multi-head attention residual convolution network. First, we introduce the 3D attention-based convolution layer to extract video features. Second, features will be fed into LSTM and residual backbone networks, which can be used to capture the contextual information of the video. Finally, we design a feature compression module to condense the learned contextual features. We develop some interpretable experiments to better explain this black-box model so that it can be better generalized. Experiments show that our model can achieve state-of-the-art diagnosis performance. The proposed lightweight but effective model is expected to serve as a suitable end-to-end deep learning baseline in future research on PD video-based severity evaluation and has the potential for large-scale application in PD telemedicine. The source code is available at https://github.com/JackAILab/MARNet.

Automated detection of MRI-negative temporal lobe epilepsy with ROI-based morphometric features and machine learning

Objective

Temporal lobe epilepsy (TLE) predominantly originates from the anteromedial basal region of the temporal lobe, and its prognosis is generally favorable following surgical intervention. However, TLE often appears negative in magnetic resonance imaging (MRI), making it difficult to quantitatively diagnose the condition solely based on clinical symptoms. There is a pressing need for a quantitative, automated method for detecting TLE.

Methods

This study employed MRI scans and clinical data from 51 retrospective epilepsy cases, dividing them into two groups: 34 patients in TLE group and 17 patients in non-TLE group. The criteria for defining the TLE group were successful surgical removal of the epileptogenic zone in the temporal lobe and a favorable postoperative prognosis. A standard procedure was used for normalization, brain extraction, tissue segmentation, regional brain partitioning, and cortical reconstruction of T1 structural MRI images. Morphometric features such as gray matter volume, cortical thickness, and surface area were extracted from a total of 20 temporal lobe regions in both hemispheres. Support vector machine (SVM), extreme learning machine (ELM), and cmcRVFL+ classifiers were employed for model training and validated using 10-fold cross-validation.

Results

The results demonstrated that employing ELM classifiers in conjunction with specific temporal lobe gray matter volume features led to a better identification of TLE. The classification accuracy was 92.79%, with an area under the curve (AUC) value of 0.8019.

Conclusion

The method proposed in this study can significantly assist in the preoperative identification of TLE patients. By employing this method, TLE can be included in surgical criteria, which could alleviate patient symptoms and improve prognosis, thereby bearing substantial clinical significance.

Frequency-Dependent Microstate Characteristics for Mild Cognitive Impairment in Parkinson's Disease

Cognitive impairment is typically reflected in the time and frequency variations of electroencephalography (EEG). Integrating time-domain and frequency-domain analysis methods is essential to better understand and assess cognitive ability. Timely identification of cognitive levels in early Parkinson's disease (ePD) patients can help mitigate the risk of future dementia. For the investigation of the brain activity and states related to cognitive levels, this study recruited forty ePD patients for EEG microstate analysis, including 13 with mild cognitive impairment (MCI) and 27 without MCI (control group). To determine the specific frequency band on which the microstate analysis relies, a deep learning framework was employed to discern the frequency dependence of the cognitive level in ePD patients. The input to the convolutional neural network consisted of the power spectral density of multi-channel multi-point EEG signals. The visualization technique of gradient-weighted class activation mapping was utilized to extract the optimal frequency band for identifying MCI samples. Within this frequency band, microstate analysis was conducted and correlated with the Montreal Cognitive Assessment (MoCA) Scale. The deep neural network revealed significant differences in the 1-11.5Hz spectrum of the ePD-MCI group compared to the control group. In this characteristic frequency band, ePD-MCI patients exhibited a pattern of global microstate disorder. The coverage rate and occurrence frequency of microstate A and D increased significantly and were both negatively correlated with the MoCA scale. Meanwhile, the coverage, frequency and duration of microstate C decreased significantly and were positively correlated with the MoCA scale. Our work unveils abnormal microstate characteristics in ePD-MCI based on time-frequency fusion, enhancing our understanding of cognitively related brain dynamics and providing electrophysiological markers for ePD-MCI recognition.

B-mode ultrasound based CAD for liver cancers via multi-view privileged information learning

B-mode ultrasound-based computer-aided diagnosis model can help sonologists improve the diagnostic performance for liver cancers, but it generally suffers from the bottleneck due to the limited structure and internal echogenicity information in B-mode ultrasound images. Contrast-enhanced ultrasound images provide additional diagnostic information on dynamic blood perfusion of liver lesions for B-mode ultrasound images with improved diagnostic accuracy. Since transfer learning has indicated its effectiveness in promoting the performance of target computer-aided diagnosis model by transferring knowledge from related imaging modalities, a multi-view privileged information learning framework is proposed to improve the diagnostic accuracy of the single-modal B-mode ultrasound-based diagnosis for liver cancers. This framework can make full use of the shared label information between the paired B-mode ultrasound images and contrast-enhanced ultrasound images to guide knowledge transfer It consists of a novel supervised dual-view deep Boltzmann machine and a new deep multi-view SVM algorithm. The former is developed to implement knowledge transfer from the multi-phase contrast-enhanced ultrasound images to the B-mode ultrasound-based diagnosis model via a feature-level learning using privileged information paradigm, which is totally different from the existing learning using privileged information paradigm that performs knowledge transfer in the classifier. The latter further fuses and enhances feature representation learned from three pre-trained supervised dual-view deep Boltzmann machine networks for the classification task. An experiment is conducted on a bimodal ultrasound liver cancer dataset. The experimental results show that the proposed framework outperforms all the compared algorithms with the best classification accuracy of 88.91 ± 1.52%, sensitivity of 88.31 ± 2.02%, and specificity of 89.50 ± 3.12%. It suggests the effectiveness of our proposed MPIL framework for the BUS-based CAD of liver cancers.

Multi-View Feature Transformation Based SVM+ for Computer-Aided Diagnosis of Liver Cancers With Ultrasound Images

It is feasible to improve the performance of B-mode ultrasound (BUS) based computer-aided diagnosis (CAD) for liver cancers by transferring knowledge from contrast-enhanced ultrasound (CEUS) images. In this work, we propose a novel feature transformation based support vector machine plus (SVM+) algorithm for this transfer learning task by introducing feature transformation into the SVM+ framework (named FSVM+). Specifically, the transformation matrix in FSVM+ is learned to minimize the radius of the enclosing ball of all samples, while the SVM+ is used to maximize the margin between two classes. Moreover, to capture more transferable information from multiple CEUS phase images, a multi-view FSVM+ (MFSVM+) is further developed, which transfers knowledge from three CEUS images from three phases, i.e., arterial phase, portal venous phase, and delayed phase, to the BUS-based CAD model. MFSVM+ innovatively assigns appropriate weights for each CEUS image by calculating the maximum mean discrepancy between a pair of BUS and CEUS images, which can capture the relationship between source and target domains. The experimental results on a bi-modal ultrasound liver cancer dataset demonstrate that MFSVM+ achieves the best classification accuracy of 88.24±1.28%, sensitivity of 88.32±2.88%, specificity of 88.17±2.91%, suggesting its effectiveness in promoting the diagnostic accuracy of BUS-based CAD.

Artificially intelligent differential diagnosis of enlarged lymph nodes with random vector functional link network plus

Differential diagnosis of enlarged lymph nodes (ELNs) is essential for the treatment of related patients. Though multi-modal ultrasound including B-mode, Doppler ultrasound, elastography and contrast-enhanced ultrasound (CEUS) can enhance diagnostic performance for ELNs, the scenario of having only single or dual modal data is often encountered. In this study, an artificially intelligent diagnosis model based on the learning using privileged information was proposed to aid in differential diagnosis of ELNs in the case of single or dual modal images. In our model, B-mode, or combined with another modality, was used as the standard information (SI) and other modalities were used as the privileged information (PI). The model was constructed through the combination of the SI and PI in the training stage. By learning from the training samples, a random vector functional link network with privileged information (RVFL+) was obtained, which was used to classify the testing samples of solely the SI. Results showed that the accuracy, precision and Youden's index of the RVFL+ model, using B-mode with elastography as the SI and CEUS as the PI, reached 78.4%, 92.4% and 54.9%, increased by 14.0%, 8.4% and 24.5% compared with the model using B-mode as the SI without the PI. The method based on the LUPI can improve the diagnostic performance for ELNs.

Tensor based stacked fuzzy neural network for efficient data regression

Random vector functional link and extreme learning machine have been extended by the type-2 fuzzy sets with vector stacked methods, this extension leads to a new way to use tensor to construct learning structure for the type-2 fuzzy sets-based learning framework. In this paper, type-2 fuzzy sets-based random vector functional link, type-2 fuzzy sets-based extreme learning machine and Tikhonov-regularized extreme learning machine are fused into one network, a tensor way of stacking data is used to incorporate the nonlinear mappings when using type-2 fuzzy sets. In this way, the network could learn the sub-structure by three sub-structures' algorithms, which are merged into one tensor structure via the type-2 fuzzy mapping results. To the stacked single fuzzy neural network, the consequent part parameters learning is implemented by unfolding tensor-based matrix regression. The newly proposed stacked single fuzzy neural network shows a new way to design the hybrid fuzzy neural network with the higher order fuzzy sets and higher order data structure. The effective of the proposed stacked single fuzzy neural network are verified by the classical testing benchmarks and several statistical testing methods.

Doubly Supervised Transfer Classifier for Computer-Aided Diagnosis With Imbalanced Modalities

Transfer learning (TL) can effectively improve diagnosis accuracy of single-modal-imaging-based computer-aided diagnosis (CAD) by transferring knowledge from other related imaging modalities, which offers a way to alleviate the small-sample-size problem. However, medical imaging data generally have the following characteristics for the TL-based CAD: 1) The source domain generally has limited data, which increases the difficulty to explore transferable information for the target domain; 2) Samples in both domains often have been labeled for training the CAD model, but the existing TL methods cannot make full use of label information to improve knowledge transfer. In this work, we propose a novel doubly supervised transfer classifier (DSTC) algorithm. In particular, DSTC integrates the support vector machine plus (SVM+) classifier and the low-rank representation (LRR) into a unified framework. The former makes full use of the shared labels to guide the knowledge transfer between the paired data, while the latter adopts the block-diagonal low-rank (BLR) to perform supervised TL between the unpaired data. Furthermore, we introduce the Schatten-p norm for BLR to obtain a tighter approximation to the rank function. The proposed DSTC algorithm is evaluated on the Alzheimer's disease neuroimaging initiative (ADNI) dataset and the bimodal breast ultrasound image (BBUI) dataset. The experimental results verify the effectiveness of the proposed DSTC algorithm.

Parkinson's Disease Classification and Clinical Score Regression via United Embedding and Sparse Learning From Longitudinal Data

Parkinson's disease (PD) is known as an irreversible neurodegenerative disease that mainly affects the patient's motor system. Early classification and regression of PD are essential to slow down this degenerative process from its onset. In this article, a novel adaptive unsupervised feature selection approach is proposed by exploiting manifold learning from longitudinal multimodal data. Classification and clinical score prediction are performed jointly to facilitate early PD diagnosis. Specifically, the proposed approach performs united embedding and sparse regression, which can determine the similarity matrices and discriminative features adaptively. Meanwhile, we constrain the similarity matrix among subjects and exploit the l_2,p norm to conduct sparse adaptive control for obtaining the intrinsic information of the multimodal data structure. An effective iterative optimization algorithm is proposed to solve this problem. We perform abundant experiments on the Parkinson's Progression Markers Initiative (PPMI) data set to verify the validity of the proposed approach. The results show that our approach boosts the performance on the classification and clinical score regression of longitudinal data and surpasses the state-of-the-art approaches.

Adaptive Multimodal Neuroimage Integration for Major Depression Disorder Detection

Major depressive disorder (MDD) is one of the most common mental health disorders that can affect sleep, mood, appetite, and behavior of people. Multimodal neuroimaging data, such as functional and structural magnetic resonance imaging (MRI) scans, have been widely used in computer-aided detection of MDD. However, previous studies usually treat these two modalities separately, without considering their potentially complementary information. Even though a few studies propose integrating these two modalities, they usually suffer from significant inter-modality data heterogeneity. In this paper, we propose an adaptive multimodal neuroimage integration (AMNI) framework for automated MDD detection based on functional and structural MRIs. The AMNI framework consists of four major components: (1) a graph convolutional network to learn feature representations of functional connectivity networks derived from functional MRIs, (2) a convolutional neural network to learn features of T1-weighted structural MRIs, (3) a feature adaptation module to alleviate inter-modality difference, and (4) a feature fusion module to integrate feature representations extracted from two modalities for classification. To the best of our knowledge, this is among the first attempts to adaptively integrate functional and structural MRIs for neuroimaging-based MDD analysis by explicitly alleviating inter-modality heterogeneity. Extensive evaluations are performed on 533 subjects with resting-state functional MRI and T1-weighted MRI, with results suggesting the efficacy of the proposed method.

Self-paced learning and privileged information based KRR classification algorithm for diagnosis of Parkinson's disease

Computer aided diagnosis (CAD) methods for Parkinson's disease (PD) can assist clinicians in diagnosis and treatment. Magnetic resonance imaging (MRI) based CAD methods can help reveal structural changes in brain. Classifier is a key component in CAD system, which directly affects the classification performance. Privileged information (PI) can assist to train the classifier by providing additional information, which makes test samples have less error and improves the classification accuracy. In this paper, we proposed a PI based kernel ridge regression plus (KRR+) in diagnosis of PD. Specifically, morphometric features and brain network features are extracted from MRI. Then, empirical kernel mapping feature expression method is used to make the data separable in high-dimensional space. Besides, we introduce self-paced learning that can adaptively select the sample in training of the model, which can further improve the classification performance. The experimental results show that the proposed method is effective for PD diagnosis, its performance is superior to existing classification model. This method is helpful to assist clinicians to find out possible neuroimaging biomarkers in the diagnosis of PD.

Self-Paced Learning and Privileged Information based Cascaded Multi-column Classification algorithm for ASD diagnosis

Autism spectrum disorder (ASD) is one of the most serious mental disorder in children. Machine learning based computer aided diagnosis (CAD) on resting-state functional magnetic resonance imaging (rs-fMRI) for ASD has attracted widespread attention. In recent years, learning using privileged information (LUPI), a supervised transfer learning method, has been generally used on multi-modality cases, which can transfer knowledge from source domain to target domain in order to improve the prediction capability on the target domain. However, multi-modality data is difficult to collect in clinical cases. LUPI method without introducing additional imaging modality images is worth further study. Random vector function link network plus (RVFL+) is a LUPI diagnosis algorithm, which has been proven to be effective for classification tasks. In this work, we proposed a self-paced learning based cascaded multi-column RVFL+ algorithm (SPL-cmcRVFL+) for ASD diagnosis. Initial classification model is trained using RVFL on the single-modal data (e.g. rs-fMRI). The output of the initial layer is then sent as privileged information (PI) to train the next layer of classification model. During this process, samples are selected using self-paced learning (SPL), which can adaptively select simple to difficult samples according to the loss value. The procedure is repeated until all samples are included. Experimental results show that our proposed method can accurately identify ASD and normal control, and outperforms other methods by a relatively higher classification accuracy.

Multi-Source Transfer Learning Via Multi-Kernel Support Vector Machine Plus for B-Mode Ultrasound-Based Computer-Aided Diagnosis of Liver Cancers

B-mode ultrasound (BUS) imaging is a routine tool for diagnosis of liver cancers, while contrast-enhanced ultrasound (CEUS) provides additional information to BUS on the local tissue vascularization and perfusion to promote diagnostic accuracy. In this work, we propose to improve the BUS-based computer aided diagnosis for liver cancers by transferring knowledge from the multi-view CEUS images, including the arterial phase, portal venous phase, and delayed phase, respectively. To make full use of the shared labels of paired of BUS and CEUS images to guide knowledge transfer, support vector machine plus (SVM+), a specifically designed transfer learning (TL) classifier for paired data with shared labels, is adopted for this supervised TL. A nonparallel hyperplane based SVM+ (NHSVM+) is first proposed to improve the TL performance by transferring the per-class knowledge from source domain to the corresponding target domain. Moreover, to handle the issue of multi-source TL, a multi-kernel learning based NHSVM+ (MKL-NHSVM+) algorithm is further developed to effectively transfer multi-source knowledge from multi-view CEUS images. The experimental results indicate that the proposed MKL-NHSVM+ outperforms all the compared algorithms for diagnosis of liver cancers, whose mean classification accuracy, sensitivity, and specificity are 88.18 ± 3.16 %, 86.98 ± 4.77 %, and 89.42±3.77%, respectively.

An ensemble learning framework for potential miRNA-disease association prediction with positive-unlabeled data

To explore the pathogenic mechanisms of MicroRNA (miRNA) on diverse diseases, many researchers have concentrated on discovering the potential associations between miRNA and disease using machine learning methods. However, the prediction accuracy of supervised machine learning methods is limited by lacking of experimentally-validated uncorrelated miRNA-disease pairs. Without these negative samples, training a highly accurate model is much more difficult. Different from traditional miRNA-disease prediction models using randomly selected unknown samples as negative training samples, we propose an ensemble learning framework to solve this positive-unlabeled (PU) learning problem. The framework incorporates two steps, i.e., a novel semi-supervised Kmeans (SS-Kmeans) to extract reliable negative samples from unknown miRNA-disease pairs and subagging method to generate diverse training sample sets to make full use of those reliable negative samples for ensemble learning. Combined with effective random vector functional link (RVFL) network as prediction model, the proposed framework showed superior prediction accuracy comparing with other popular approaches. A case study on lung and gastric neoplasms further confirms the framework's efficacy at identifying miRNA disease associations.

Diagnosis of early Alzheimer's disease based on dynamic high order networks

Machine learning methods have been widely used for early diagnosis of Alzheimer's disease (AD) via functional connectivity networks (FCNs) analysis from neuroimaging data. The conventional low-order FCNs are obtained by time-series correlation of the whole brain based on resting-state functional magnetic resonance imaging (R-fMRI). However, FCNs overlook inter-region interactions, which limits application to brain disease diagnosis. To overcome this drawback, we develop a novel framework to exploit the high-level dynamic interactions among brain regions for early AD diagnosis. Specifically, a sliding window approach is employed to generate some R-fMRI sub-series. The correlations among these sub-series are then used to construct a series of dynamic FCNs. High-order FCNs based on the topographical similarity between each pair of the dynamic FCNs are then constructed. Afterward, a local weight clustering method is used to extract effective features of the network, and the least absolute shrinkage and selection operation method is chosen for feature selection. A support vector machine is employed for classification, and the dynamic high-order network approach is evaluated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Our experimental results demonstrate that the proposed approach not only achieves promising results for AD classification, but also successfully recognizes disease-related biomarkers.

Shear wave elastography characteristics of upper limb muscle in rigidity-dominant Parkinson's disease

BACKGROUND

Rigidity is one of the major manifestations of Parkinson's disease (PD), but no quantitative and objective imaging method has been developed to measure rigidity. Ultrasound shear wave elastography (SWE) can reflect the stiffness of tissue by providing a quantitative index. Thus, we conducted this study to evaluate the potential clinical value of SWE in assessing rigidity in PD.

METHODS

A total of 63 subjects (44 patients with rigidity-dominant PD and 19 right-dominant-hand normal controls with matched age) were enrolled, and each underwent ultrasound SWE testing. The tests were conducted on the brachioradialis (BR) and biceps brachii (BB) on the more affected side in patients with PD and on the right side in normal controls. Differences in quantitative shear wave velocity (SWV) between patients with PD and normal controls were determined. The relationship of muscle SWV with joint rigidity, UPDRSIII, disease duration, sex, and age in patients with PD was analyzed. The intraclass correlation coefficient (ICC) was used to evaluate the reliability of SWE in assessing muscle stiffness in patients with PD.

RESULTS

The mean SWVs of the BB and BR were higher in the PD group (3.65±0.46 and 4.62±0.89 m/s, respectively) than in normal controls (2.79±0.37 and 3.26±0.40 m/s, respectively). Stiffness in BR and BB was correlated with the upper-limb joint rigidity, UPDRSIII, and disease duration but not with sex or age in the PD group. The intraobserver correlation coefficients (ICCs) for interobserver and intraobserver variations in measuring SWV were 0.85 (95% confidence interval 0.56-0.95) and 0.85 (95% confidence interval 0.58-0.95), respectively, for BR and 0.90 (95% confidence interval 0.73-0.97) and 0.86 (95% confidence interval 0.61-0.95), respectively, for BB.

CONCLUSIONS

SWV is associated with joint rigidity and disease duration, indicating that SWE can be potentially used as an objective and quantitative tool for evaluating rigidity.

Improving prediction for medical institution with limited patient data: Leveraging hospital-specific data based on multicenter collaborative research network

BACKGROUND AND OBJECTIVE

Clinical decision support assisted by prediction models usually faces the challenges of limited clinical data and a lack of labels when the model is developed with data from a single medical institution. Accordingly, research on multicenter clinical collaborative networks, which can provide external medical data, has received increasing attention. With the increasing availability of machine learning techniques such as transfer learning, leveraging large-scale patient data from multiple hospitals to build data-driven predictive models with clinical application potential provides an alternative solution to address the problem of limited patient data.

METHODS

A multicenter hybrid semi-supervised transfer learning model (MHSTL) is proposed in this study on the basis of unified common data model to ensure multicenter data standardized representation. Then the hospital-specific features, along with the co-occurrence features across domains, are aligned through a representation learning architecture that is built based on deep neural networks and the newly proposed neural decision forest model. In this process, limited patient data from the target hospital, both labeled and unlabeled, are incorporated during the feature adaptation process, thereby contributing to better model performance. Without patient-level data sharing, the proposed model learning strategy which overcomes feature misalignment and distribution divergence, enables the multi-source transfer learning process in the case of insufficient and unlabeled patient data at target hospital.

RESULTS

The effectiveness of the proposed transfer learning model was evaluated on a collaborative research network of colorectal cancer patients in the US and China. The results demonstrate that the proposed model can achieve much better performance for predicting target risk with limited resources on patient data than baseline models      . Better discrimination and calibration ability are also observed when sufficient labeled data are not available in the target hospital for prognosis prediction tasks      . Further exploratory experiments show that the proposed approach exhibits good model generalizability regardless of the data heterogeneity. With the help of the SHapley Additive exPlanations for model interpretation, the effectiveness of incorporating hospital-specific features in the transfer learning model is shown.

CONCLUSIONS

In this study, the proposed method can develop prediction models from multiple source hospitals and exhibit good performance by leveraging cross-domain hospital-specific feature information, therefore enhancing the model prediction when applied to single medical institution with limited patient data.

A Survey on Deep Learning for Neuroimaging-Based Brain Disorder Analysis

Deep learning has recently been used for the analysis of neuroimages, such as structural magnetic resonance imaging (MRI), functional MRI, and positron emission tomography (PET), and it has achieved significant performance improvements over traditional machine learning in computer-aided diagnosis of brain disorders. This paper reviews the applications of deep learning methods for neuroimaging-based brain disorder analysis. We first provide a comprehensive overview of deep learning techniques and popular network architectures by introducing various types of deep neural networks and recent developments. We then review deep learning methods for computer-aided analysis of four typical brain disorders, including Alzheimer's disease, Parkinson's disease, Autism spectrum disorder, and Schizophrenia, where the first two diseases are neurodegenerative disorders and the last two are neurodevelopmental and psychiatric disorders, respectively. More importantly, we discuss the limitations of existing studies and present possible future directions.

A novel semi-supervised multi-view clustering framework for screening Parkinson's disease

In recent years, there are many research cases for the diagnosis of Parkinson's disease (PD) with the brain magnetic resonance imaging (MRI) by utilizing the traditional unsupervised machine learning methods and the supervised deep learning models. However, unsupervised learning methods are not good at extracting accurate features among MRIs and it is difficult to collect enough data in the field of PD to satisfy the need of training deep learning models. Moreover, most of the existing studies are based on single-view MRI data, of which data characteristics are not sufficient enough. In this paper, therefore, in order to tackle the drawbacks mentioned above, we propose a novel semi-supervised learning framework called Semi-supervised Multi-view learning Clustering architecture technology (SMC). The model firstly introduces the sliding window method to grasp different features, and then uses the dimensionality reduction algorithms of Linear Discriminant Analysis (LDA) to process the data with different features. Finally, the traditional single-view clustering and multi-view clustering methods are employed on multiple feature views to obtain the results. Experiments show that our proposed method is superior to the state-of-art unsupervised learning models on the clustering effect. As a result, it may be noted that, our work could contribute to improving the effectiveness of identifying PD by previous labeled and subsequent unlabeled medical MRI data in the realistic medical environment.

Ultrasound-Based Diagnosis of Breast Tumor with Parameter Transfer Multilayer Kernel Extreme Learning Machine

B-mode ultrasound (BUS) imaging is widely used for diagnosis of breast tumors. In recent years, another ultrasound modality, namely ultrasound elastography (UE), has also been successfully applied in clinical practice. Although the combination of bimodal ultrasound imaging can improve the diagnosis accuracy for breast tumors, the single-modal ultrasound-based diagnosis is more popular in clinical practice, especially in the rural areas. Since transfer learning (TL) can transfer knowledge from a source domain to a target domain to help train more effective model, we propose to develop a single-modal ultrasound-based computer-aided diagnosis (CAD) with the transferred information from an additional modality in this work. We propose a projective model (PM) based multilayer kernel extreme learning machine (ML-KELM-PM) algorithm, which performs the parameter transfer approach in classifier to perform TL in CAD. The experimental results on a bimodal ultrasound image dataset show that the proposed ML-KELM-PM algorithm outperforms all the compared algorithms for the single-modal ultrasound-based CAD for breast tumors.

Neuroimaging modality fusion in Alzheimer's classification using convolutional neural networks

Automated methods for Alzheimer’s disease (AD) classification have the potential for great clinical benefits and may provide insight for combating the disease. Machine learning, and more specifically deep neural networks, have been shown to have great efficacy in this domain. These algorithms often use neurological imaging data such as MRI and FDG PET, but a comprehensive and balanced comparison of the MRI and amyloid PET modalities has not been performed. In order to accurately determine the relative strength of each imaging variant, this work performs a comparison study in the context of Alzheimer’s dementia classification using the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset with identical neural network architectures. Furthermore, this work analyzes the benefits of using both modalities in a fusion setting and discusses how these data types may be leveraged in future AD studies using deep learning.

Multi-task learning for quality assessment of fetal head ultrasound images

It is essential to measure anatomical parameters in prenatal ultrasound images for the growth and development of the fetus, which is highly relied on obtaining a standard plane. However, the acquisition of a standard plane is, in turn, highly subjective and depends on the clinical experience of sonographers. In order to deal with this challenge, we propose a new multi-task learning framework using a faster regional convolutional neural network (MF R-CNN) architecture for standard plane detection and quality assessment. MF R-CNN can identify the critical anatomical structure of the fetal head and analyze whether the magnification of the ultrasound image is appropriate, and then performs quality assessment of ultrasound images based on clinical protocols. Specifically, the first five convolution blocks of the MF R-CNN learn the features shared within the input data, which can be associated with the detection and classification tasks, and then extend to the task-specific output streams. In training, in order to speed up the different convergence of different tasks, we devise a section train method based on transfer learning. In addition, our proposed method also uses prior clinical and statistical knowledge to reduce the false detection rate. By identifying the key anatomical structure and magnification of the ultrasound image, we score the ultrasonic plane of fetal head to judge whether it is a standard image or not. Experimental results on our own-collected dataset show that our method can accurately make a quality assessment of an ultrasound plane within half a second. Our method achieves promising performance compared with state-of-the-art methods, which can improve the examination effectiveness and alleviate the measurement error caused by improper ultrasound scanning.

Learning using privileged information improves neuroimaging-based CAD of Alzheimer's disease: a comparative study

The neuroimaging-based computer-aided diagnosis (CAD) for Alzheimer's disease (AD) has shown its effectiveness in recent years. In general, the multimodal neuroimaging-based CAD always outperforms the approaches based on a single modality. However, single-modal neuroimaging is more favored in clinical practice for diagnosis due to the limitations of imaging devices, especially in rural hospitals. Learning using privileged information (LUPI) is a new learning paradigm that adopts additional privileged information (PI) modality to help to train a more effective learning model during the training stage, but PI itself is not available in the testing stage. Since PI is generally related to the training samples, it is then transferred to the learned model. In this work, a LUPI-based CAD framework for AD is proposed. It can flexibly perform a classifier- or feature-level LUPI, in which the information is transferred from the additional PI modality to the diagnosis modality. A thorough comparison has been made among three classifier-level algorithms and five feature-level LUPI algorithms. The experimental results on the ADNI dataset show that all classifier-level and deep learning based feature-level LUPI algorithms can improve the performance of a single-modal neuroimaging-based CAD for AD by transferring PI. Graphical abstract Graphical abstract for the framework of the LUPI-based CAD for AD.