201
|
Vieira S, Lopez Pinaya WH, Garcia-Dias R, Mechelli A. Deep neural networks. Mach Learn 2020. [DOI: 10.1016/b978-0-12-815739-8.00009-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
|
202
|
|
203
|
|
204
|
A Long Short-Term Memory neural network for the detection of epileptiform spikes and high frequency oscillations. Sci Rep 2019; 9:19374. [PMID: 31852929 PMCID: PMC6920137 DOI: 10.1038/s41598-019-55861-w] [Citation(s) in RCA: 23] [Impact Index Per Article: 4.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2019] [Accepted: 12/02/2019] [Indexed: 12/02/2022] Open
Abstract
Over the last two decades, the evidence has been growing that in addition to epileptic spikes high frequency oscillations (HFOs) are important biomarkers of epileptogenic tissue. New methods of artificial intelligence such as deep learning neural networks can provide additional tools for automated analysis of EEG. Here we present a Long Short-Term Memory neural network for detection of spikes, ripples and ripples-on-spikes (RonS). We used intracranial EEG (iEEG) from two independent datasets. First dataset (7 patients) was used for network training and testing. The second dataset (5 patients) was used for cross-institutional validation. 1000 events of each class (spike, RonS, ripple and baseline) were selected from the candidates initially found using a novel threshold method. Network training was performed using random selections of 50–500 events (per class) from all patients from the 1st dataset. This ‘global’ network was then tested on other events for each patient from both datasets. The network was able to detect events with a good generalisability namely, with total accuracy and specificity for each class exceeding 90% in all cases, and sensitivity less than 86% in only two cases (82.5% for spikes in one patient and 81.9% for ripples in another patient). The deep learning networks can significantly accelerate the analysis of iEEG data and increase their diagnostic value which may improve surgical outcome in patients with localization-related intractable epilepsy.
Collapse
|
205
|
Santana AN, Cifre I, de Santana CN, Montoya P. Using Deep Learning and Resting-State fMRI to Classify Chronic Pain Conditions. Front Neurosci 2019; 13:1313. [PMID: 31920483 PMCID: PMC6929667 DOI: 10.3389/fnins.2019.01313] [Citation(s) in RCA: 25] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/14/2019] [Accepted: 11/25/2019] [Indexed: 12/11/2022] Open
Abstract
Chronic pain is known as a complex disease due to its comorbidities with other symptoms and the lack of effective treatments. As a consequence, chronic pain seems to be under-diagnosed in more than 75% of patients. At the same time, the advance in brain imaging, the popularization of machine learning techniques and the development of new diagnostic tools based on these technologies have shown that these tools could be an option in supporting decision-making of healthcare professionals. In this study, we computed functional brain connectivity using resting-state fMRI data from one hundred and fifty participants to assess the performance of different machine learning models, including deep learning (DL) neural networks in classifying chronic pain patients and pain-free controls. The best result was obtained by training a convolutional neural network fed with data preprocessed using the MSDL probabilistic atlas and using the dynamic time warping (DTW) as connectivity measure. DL models had a better performance compared to other less costly models such as support vector machine (SVM) and RFC, with balanced accuracy ranged from 69 to 86%, while the area under the curve (ROC) ranged from 0.84 to 0.93. Also, DTW overperformed correlation as connectivity measure. These findings support the notion that resting-state fMRI data could be used as a potential biomarker of chronic pain conditions.
Collapse
Affiliation(s)
- Alex Novaes Santana
- Research Institute of Health Sciences (IUNICS-IdISBa), University of the Balearic Islands, Palma, Spain
| | - Ignacio Cifre
- Facultat de Psicologia, Ciències de l'Educació i de l'Esport, Blanquerna, Universitat Ramon Llull, Barcelona, Spain
| | | | - Pedro Montoya
- Research Institute of Health Sciences (IUNICS-IdISBa), University of the Balearic Islands, Palma, Spain
| |
Collapse
|
206
|
Oh K, Chung YC, Kim KW, Kim WS, Oh IS. Classification and Visualization of Alzheimer's Disease using Volumetric Convolutional Neural Network and Transfer Learning. Sci Rep 2019; 9:18150. [PMID: 31796817 PMCID: PMC6890708 DOI: 10.1038/s41598-019-54548-6] [Citation(s) in RCA: 83] [Impact Index Per Article: 16.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2019] [Accepted: 11/12/2019] [Indexed: 12/21/2022] Open
Abstract
Recently, deep-learning-based approaches have been proposed for the classification of neuroimaging data related to Alzheimer's disease (AD), and significant progress has been made. However, end-to-end learning that is capable of maximizing the impact of deep learning has yet to receive much attention due to the endemic challenge of neuroimaging caused by the scarcity of data. Thus, this study presents an approach meant to encourage the end-to-end learning of a volumetric convolutional neural network (CNN) model for four binary classification tasks (AD vs. normal control (NC), progressive mild cognitive impairment (pMCI) vs. NC, stable mild cognitive impairment (sMCI) vs. NC and pMCI vs. sMCI) based on magnetic resonance imaging (MRI) and visualizes its outcomes in terms of the decision of the CNNs without any human intervention. In the proposed approach, we use convolutional autoencoder (CAE)-based unsupervised learning for the AD vs. NC classification task, and supervised transfer learning is applied to solve the pMCI vs. sMCI classification task. To detect the most important biomarkers related to AD and pMCI, a gradient-based visualization method that approximates the spatial influence of the CNN model's decision was applied. To validate the contributions of this study, we conducted experiments on the ADNI database, and the results demonstrated that the proposed approach achieved the accuracies of 86.60% and 73.95% for the AD and pMCI classification tasks respectively, outperforming other network models. In the visualization results, the temporal and parietal lobes were identified as key regions for classification.
Collapse
Affiliation(s)
- Kanghan Oh
- Jeonbuk National University, Department of Computer Science and Engineering, Jeonju, 54896, Korea
| | - Young-Chul Chung
- Research Institute of Clinical Medicine of Jeonbuk National University-Biomedical Research Institute of Jeonbuk National University Hospital, Jeonju, 54907, Korea
- Jeonbuk National University Medical School, Department of Psychiatry, Jeonju, 54907, Korea
| | - Ko Woon Kim
- Jeonbuk National University Medical School, Department of Neurology, Jeonju, 54907, Korea
| | - Woo-Sung Kim
- Research Institute of Clinical Medicine of Jeonbuk National University-Biomedical Research Institute of Jeonbuk National University Hospital, Jeonju, 54907, Korea
- Jeonbuk National University Medical School, Department of Psychiatry, Jeonju, 54907, Korea
| | - Il-Seok Oh
- Jeonbuk National University, Department of Computer Science and Engineering, Jeonju, 54896, Korea.
| |
Collapse
|
207
|
Fernandez-Maloigne C, Guillevin R. L’intelligence artificielle au service de l’imagerie et de la santé des femmes. IMAGERIE DE LA FEMME 2019. [DOI: 10.1016/j.femme.2019.09.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
208
|
Nielsen AN, Barch DM, Petersen SE, Schlaggar BL, Greene DJ. Machine Learning With Neuroimaging: Evaluating Its Applications in Psychiatry. BIOLOGICAL PSYCHIATRY: COGNITIVE NEUROSCIENCE AND NEUROIMAGING 2019; 5:791-798. [PMID: 31982357 DOI: 10.1016/j.bpsc.2019.11.007] [Citation(s) in RCA: 38] [Impact Index Per Article: 7.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/05/2019] [Revised: 10/29/2019] [Accepted: 11/17/2019] [Indexed: 01/08/2023]
Abstract
Psychiatric disorders are complex, involving heterogeneous symptomatology and neurobiology that rarely involves the disruption of single, isolated brain structures. In an attempt to better describe and understand the complexities of psychiatric disorders, investigators have increasingly applied multivariate pattern classification approaches to neuroimaging data and in particular supervised machine learning methods. However, supervised machine learning approaches also come with unique challenges and trade-offs, requiring additional study design and interpretation considerations. The goal of this review is to provide a set of best practices for evaluating machine learning applications to psychiatric disorders. We discuss how to evaluate two common efforts: 1) making predictions that have the potential to aid in diagnosis, prognosis, and treatment and 2) interrogating the complex neurophysiological mechanisms underlying psychopathology. We focus here on machine learning as applied to functional connectivity with magnetic resonance imaging, as an example to ground discussion. We argue that for machine learning classification to have translational utility for individual-level predictions, investigators must ensure that the classification is clinically informative, independent of confounding variables, and appropriately assessed for both performance and generalizability. We contend that shedding light on the complex mechanisms underlying psychiatric disorders will require consideration of the unique utility, interpretability, and reliability of the neuroimaging features (e.g., regions, networks, connections) identified from machine learning approaches. Finally, we discuss how the rise of large, multisite, publicly available datasets may contribute to the utility of machine learning approaches in psychiatry.
Collapse
Affiliation(s)
- Ashley N Nielsen
- Institute for Innovations in Developmental Sciences, Northwestern University, Chicago, Illinois; Department of Medical Social Sciences, Northwestern University, Chicago, Illinois.
| | - Deanna M Barch
- Department of Psychological and Brain Sciences, Washington University in St. Louis, St. Louis, Missouri; Department of Psychiatry, Washington University School of Medicine, St. Louis, Missouri
| | - Steven E Petersen
- Department of Neurology, Washington University School of Medicine, St. Louis, Missouri; Department of Neuroscience, Washington University School of Medicine, St. Louis, Missouri; Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, Missouri
| | - Bradley L Schlaggar
- Kennedy Krieger Institute, Baltimore, Maryland; Department of Neurology, Johns Hopkins University School of Medicine, Baltimore, Maryland; Department of Pediatrics, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Deanna J Greene
- Department of Psychiatry, Washington University School of Medicine, St. Louis, Missouri; Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, Missouri
| |
Collapse
|
209
|
Lei D, Pinaya WHL, Young J, van Amelsvoort T, Marcelis M, Donohoe G, Mothersill DO, Corvin A, Vieira S, Huang X, Lui S, Scarpazza C, Arango C, Bullmore E, Gong Q, McGuire P, Mechelli A. Integrating machining learning and multimodal neuroimaging to detect schizophrenia at the level of the individual. Hum Brain Mapp 2019; 41:1119-1135. [PMID: 31737978 PMCID: PMC7268084 DOI: 10.1002/hbm.24863] [Citation(s) in RCA: 50] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/15/2019] [Revised: 10/23/2019] [Accepted: 10/31/2019] [Indexed: 02/05/2023] Open
Abstract
Schizophrenia is a severe psychiatric disorder associated with both structural and functional brain abnormalities. In the past few years, there has been growing interest in the application of machine learning techniques to neuroimaging data for the diagnostic and prognostic assessment of this disorder. However, the vast majority of studies published so far have used either structural or functional neuroimaging data, without accounting for the multimodal nature of the disorder. Structural MRI and resting‐state functional MRI data were acquired from a total of 295 patients with schizophrenia and 452 healthy controls at five research centers. We extracted features from the data including gray matter volume, white matter volume, amplitude of low‐frequency fluctuation, regional homogeneity and two connectome‐wide based metrics: structural covariance matrices and functional connectivity matrices. A support vector machine classifier was trained on each dataset separately to distinguish the subjects at individual level using each of the single feature as well as their combination, and 10‐fold cross‐validation was used to assess the performance of the model. Functional data allow higher accuracy of classification than structural data (mean 82.75% vs. 75.84%). Within each modality, the combination of images and matrices improves performance, resulting in mean accuracies of 81.63% for structural data and 87.59% for functional data. The use of all combined structural and functional measures allows the highest accuracy of classification (90.83%). We conclude that combining multimodal measures within a single model is a promising direction for developing biologically informed diagnostic tools in schizophrenia.
Collapse
Affiliation(s)
- Du Lei
- Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital of Sichuan University, Chengdu, China.,Department of Psychosis Studies, Institute of Psychiatry, Psychology & Neuroscience, King's College London, De Crespigny Park, London, UK
| | - Walter H L Pinaya
- Department of Psychosis Studies, Institute of Psychiatry, Psychology & Neuroscience, King's College London, De Crespigny Park, London, UK
| | - Jonathan Young
- Department of Neuroimaging, Institute of Psychiatry, Psychology, and Neuroscience, King's College London, London, UK
| | - Therese van Amelsvoort
- Department of Psychiatry and Neuropsychology, School of Mental Health and Neuroscience, Maastricht University Medical Center, Maastricht, The Netherlands
| | - Machteld Marcelis
- Department of Psychiatry and Neuropsychology, School of Mental Health and Neuroscience, Maastricht University Medical Center, Maastricht, The Netherlands.,Mental Health Care Institute Eindhoven (GGzE), Eindhoven, The Netherlands
| | - Gary Donohoe
- School of Psychology & Center for neuroimaging and Cognitive Genomics, NUI Galway University, Galway, Ireland
| | - David O Mothersill
- School of Psychology & Center for neuroimaging and Cognitive Genomics, NUI Galway University, Galway, Ireland
| | - Aiden Corvin
- Department of Psychiatry, School of Medicine, Trinity College Dublin, Dublin, Ireland
| | - Sandra Vieira
- Department of Psychosis Studies, Institute of Psychiatry, Psychology & Neuroscience, King's College London, De Crespigny Park, London, UK
| | - Xiaoqi Huang
- Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital of Sichuan University, Chengdu, China
| | - Su Lui
- Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital of Sichuan University, Chengdu, China
| | - Cristina Scarpazza
- Department of Psychosis Studies, Institute of Psychiatry, Psychology & Neuroscience, King's College London, De Crespigny Park, London, UK.,Department of General Psychology, University of Padua, Padua, Italy
| | - Celso Arango
- Child and Adolescent Department of Psychiatry, Hospital General Universitario Gregorio Marañon, School of Medicine, Universidad Complutense Madrid, IiSGM, CIBERSAM, Madrid, Spain
| | - Ed Bullmore
- Brain Mapping Unit, Department of Psychiatry, University of Cambridge, Cambridge, UK
| | - Qiyong Gong
- Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital of Sichuan University, Chengdu, China.,Psychoradiology Research Unit of Chinese Academy of Medical Sciences, West China Hospital of Sichuan University, Chengdu, Sichuan, China.,Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, Liaoning, China
| | - Philip McGuire
- Department of Psychosis Studies, Institute of Psychiatry, Psychology & Neuroscience, King's College London, De Crespigny Park, London, UK
| | - Andrea Mechelli
- Department of Psychosis Studies, Institute of Psychiatry, Psychology & Neuroscience, King's College London, De Crespigny Park, London, UK
| |
Collapse
|
210
|
Girault JB, Piven J. The Neurodevelopment of Autism from Infancy Through Toddlerhood. Neuroimaging Clin N Am 2019; 30:97-114. [PMID: 31759576 DOI: 10.1016/j.nic.2019.09.009] [Citation(s) in RCA: 28] [Impact Index Per Article: 5.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/21/2022]
Abstract
Autism spectrum disorder (ASD) emerges during early childhood and is marked by a relatively narrow window in which infants transition from exhibiting normative behavioral profiles to displaying the defining features of the ASD phenotype in toddlerhood. Prospective brain imaging studies in infants at high familial risk for autism have revealed important insights into the neurobiology and developmental unfolding of ASD. In this article, we review neuroimaging studies of brain development in ASD from birth through toddlerhood, relate these findings to candidate neurobiological mechanisms, and discuss implications for future research and translation to clinical practice.
Collapse
Affiliation(s)
- Jessica B Girault
- Carolina Institute for Developmental Disabilities, The University of North Carolina at Chapel Hill School of Medicine, 101 Renee Lynne Court, Chapel Hill, NC 27599, USA.
| | - Joseph Piven
- Carolina Institute for Developmental Disabilities, The University of North Carolina at Chapel Hill School of Medicine, 101 Renee Lynne Court, Chapel Hill, NC 27599, USA
| |
Collapse
|
211
|
A robust swarm intelligence-based feature selection model for neuro-fuzzy recognition of mild cognitive impairment from resting-state fMRI. Inf Sci (N Y) 2019. [DOI: 10.1016/j.ins.2019.07.026] [Citation(s) in RCA: 22] [Impact Index Per Article: 4.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|
212
|
Durstewitz D, Koppe G, Meyer-Lindenberg A. Deep neural networks in psychiatry. Mol Psychiatry 2019; 24:1583-1598. [PMID: 30770893 DOI: 10.1038/s41380-019-0365-9] [Citation(s) in RCA: 108] [Impact Index Per Article: 21.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/05/2018] [Revised: 01/02/2019] [Accepted: 01/24/2019] [Indexed: 01/03/2023]
Abstract
Machine and deep learning methods, today's core of artificial intelligence, have been applied with increasing success and impact in many commercial and research settings. They are powerful tools for large scale data analysis, prediction and classification, especially in very data-rich environments ("big data"), and have started to find their way into medical applications. Here we will first give an overview of machine learning methods, with a focus on deep and recurrent neural networks, their relation to statistics, and the core principles behind them. We will then discuss and review directions along which (deep) neural networks can be, or already have been, applied in the context of psychiatry, and will try to delineate their future potential in this area. We will also comment on an emerging area that so far has been much less well explored: by embedding semantically interpretable computational models of brain dynamics or behavior into a statistical machine learning context, insights into dysfunction beyond mere prediction and classification may be gained. Especially this marriage of computational models with statistical inference may offer insights into neural and behavioral mechanisms that could open completely novel avenues for psychiatric treatment.
Collapse
Affiliation(s)
- Daniel Durstewitz
- Department of Theoretical Neuroscience, Central Institute of Mental Health, Medical Faculty Mannheim/Heidelberg University, 68159, Mannheim, Germany.
| | - Georgia Koppe
- Department of Theoretical Neuroscience, Central Institute of Mental Health, Medical Faculty Mannheim/Heidelberg University, 68159, Mannheim, Germany.,Department of Psychiatry and Psychotherapy, Central Institute of Mental Health, Medical Faculty Mannheim/Heidelberg University, 68159, Mannheim, Germany
| | - Andreas Meyer-Lindenberg
- Department of Psychiatry and Psychotherapy, Central Institute of Mental Health, Medical Faculty Mannheim/Heidelberg University, 68159, Mannheim, Germany
| |
Collapse
|
213
|
Clinical-learning versus machine-learning for transdiagnostic prediction of psychosis onset in individuals at-risk. Transl Psychiatry 2019; 9:259. [PMID: 31624229 PMCID: PMC6797779 DOI: 10.1038/s41398-019-0600-9] [Citation(s) in RCA: 20] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/09/2019] [Revised: 05/03/2019] [Accepted: 05/31/2019] [Indexed: 02/08/2023] Open
Abstract
Predicting the onset of psychosis in individuals at-risk is based on robust prognostic model building methods including a priori clinical knowledge (also termed clinical-learning) to preselect predictors or machine-learning methods to select predictors automatically. To date, there is no empirical research comparing the prognostic accuracy of these two methods for the prediction of psychosis onset. In a first experiment, no improved performance was observed when machine-learning methods (LASSO and RIDGE) were applied-using the same predictors-to an individualised, transdiagnostic, clinically based, risk calculator previously developed on the basis of clinical-learning (predictors: age, gender, age by gender, ethnicity, ICD-10 diagnostic spectrum), and externally validated twice. In a second experiment, two refined versions of the published model which expanded the granularity of the ICD-10 diagnosis were introduced: ICD-10 diagnostic categories and ICD-10 diagnostic subdivisions. Although these refined versions showed an increase in apparent performance, their external performance was similar to the original model. In a third experiment, the three refined models were analysed under machine-learning and clinical-learning with a variable event per variable ratio (EPV). The best performing model under low EPVs was obtained through machine-learning approaches. The development of prognostic models on the basis of a priori clinical knowledge, large samples and adequate events per variable is a robust clinical prediction method to forecast psychosis onset in patients at-risk, and is comparable to machine-learning methods, which are more difficult to interpret and implement. Machine-learning methods should be preferred for high dimensional data when no a priori knowledge is available.
Collapse
|
214
|
Dang S, Chaudhury S. Novel relative relevance score for estimating brain connectivity from fMRI data using an explainable neural network approach. J Neurosci Methods 2019; 326:108371. [PMID: 31344374 DOI: 10.1016/j.jneumeth.2019.108371] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2019] [Revised: 07/14/2019] [Accepted: 07/19/2019] [Indexed: 11/15/2022]
Abstract
BACKGROUND Functional integration or connectivity in brain is directional, non-linear as well as variable in time-lagged dependence. Deep neural networks (DNN) have become an indispensable tool everywhere, by learning higher levels of abstract and complex patterns from raw data. However, in neuroscientific community they generally work as black-boxes, leading to the explanation of results difficult and less intuitive. We aim to propose a brain-connectivity measure based on an explainable NN (xNN) approach. NEW METHOD We build a NN-based predictor for regression problem. Since we aim to determine the contribution/relevance of past data-point from one region i in the prediction of current data-point from another region j, i.e. the higher-order connectivity between two brain-regions, we employ layer-wise relevance propagation (Bach et al., 2015) (LRP, a method for explaining DNN predictions), which has not been done before to the best of our knowledge. Specifically, we propose a novel score depending on weights as a quantitative measure of connectivity, called as relative relevance score (xNN-RRS). The RRS is an intuitive and transparent score. We provide an interpretation of the trained NN weights with-respect-to the brain-connectivity. RESULTS Face validity of our approach is demonstrated with experiments on simulated data, over existing methods. We also demonstrate construct validity of xNN-RRS in a resting-state fMRI experiment. COMPARISON Our approach shows superior performance, in terms of accuracy and computational complexity, over existing state-of-the-art methods for brain-connectivity estimation. CONCLUSION The proposed method is promising to serve as a first post-hoc explainable NN-approach for brain-connectivity analysis in clinical applications.
Collapse
Affiliation(s)
- Shilpa Dang
- Electrical Engineering Department, Indian Institute of Technology, Delhi, New Delhi, 110016, India.
| | - Santanu Chaudhury
- Electrical Engineering Department, Indian Institute of Technology, Delhi, New Delhi, 110016, India; Indian Institute of Technology Jodhpur, Jodhpur, 342037, India
| |
Collapse
|
215
|
Zhang J, Li X, Li Y, Wang M, Huang B, Yao S, Shen L. Three dimensional convolutional neural network-based classification of conduct disorder with structural MRI. Brain Imaging Behav 2019; 14:2333-2340. [PMID: 31538277 DOI: 10.1007/s11682-019-00186-5] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/21/2022]
Abstract
Conduct disorder (CD) is a common child and adolescent psychiatric disorder with various representative symptoms, and may cause long-term burden to patients and society. Recently, an increasing number of studies have used deep learning-based approaches, such as convolutional neural network (CNN), to analyze neuroimaging data and to identify biomarkers. In this study, we applied an optimized 3D AlexNet CNN model to automatically extract multi-layer high dimensional features of structural magnetic resonance imaging (sMRI), and to classify CD from healthy controls (HCs). We acquired high-resolution sMRI from 60 CD and 60 age- and gender-matched HCs. All subjects were male, and the age (mean ± std. dev) of participants in the CD and HC groups was 15.3 ± 1.0 and 15.5 ± 0.7, respectively. Five-fold cross validation (CV) was used to train and test this model. The receiver operating characteristic (ROC) curve for this model and that for support vector machine (SVM) model were compared. Feature visualization was performed to obtain intuition about the sMRI features learned by our AlexNet model. Our proposed AlexNet model achieved high classification performance with accuracy of 0.85, specificity of 0.82 and sensitivity of 0.87. The area under the ROC curve (AUC) of AlexNet was 0.86, significantly higher than that of SVM (AUC = 0.78; p = 0.046). The saliency maps for each convolutional layer highlighted the different brain regions in sMRI of CD, mainly including the frontal lobe, superior temporal gyrus, parietal lobe and occipital lobe. The classification results indicated that deep learning-based method is able to explore the hidden features from the sMRI of CD and might assist clinicians in the diagnosis of CD.
Collapse
Affiliation(s)
- Jianing Zhang
- School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, People's Republic of China
| | - Xuechen Li
- Computer Vision Institute, School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, People's Republic of China
| | - Yuexiang Li
- Computer Vision Institute, School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, People's Republic of China
| | - Mingyu Wang
- School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, People's Republic of China
| | - Bingsheng Huang
- School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, People's Republic of China
- Medical Psychological Center, Second Xiangya Hospital, Central South University, Changsha, People's Republic of China
| | - Shuqiao Yao
- Medical Psychological Center, Second Xiangya Hospital, Central South University, Changsha, People's Republic of China.
| | - Linlin Shen
- Computer Vision Institute, School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, People's Republic of China.
| |
Collapse
|
216
|
Eitel F, Soehler E, Bellmann-Strobl J, Brandt AU, Ruprecht K, Giess RM, Kuchling J, Asseyer S, Weygandt M, Haynes JD, Scheel M, Paul F, Ritter K. Uncovering convolutional neural network decisions for diagnosing multiple sclerosis on conventional MRI using layer-wise relevance propagation. Neuroimage Clin 2019; 24:102003. [PMID: 31634822 PMCID: PMC6807560 DOI: 10.1016/j.nicl.2019.102003] [Citation(s) in RCA: 65] [Impact Index Per Article: 13.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/24/2019] [Revised: 08/29/2019] [Accepted: 09/04/2019] [Indexed: 12/21/2022]
Abstract
Machine learning-based imaging diagnostics has recently reached or even surpassed the level of clinical experts in several clinical domains. However, classification decisions of a trained machine learning system are typically non-transparent, a major hindrance for clinical integration, error tracking or knowledge discovery. In this study, we present a transparent deep learning framework relying on 3D convolutional neural networks (CNNs) and layer-wise relevance propagation (LRP) for diagnosing multiple sclerosis (MS), the most widespread autoimmune neuroinflammatory disease. MS is commonly diagnosed utilizing a combination of clinical presentation and conventional magnetic resonance imaging (MRI), specifically the occurrence and presentation of white matter lesions in T2-weighted images. We hypothesized that using LRP in a naive predictive model would enable us to uncover relevant image features that a trained CNN uses for decision-making. Since imaging markers in MS are well-established this would enable us to validate the respective CNN model. First, we pre-trained a CNN on MRI data from the Alzheimer's Disease Neuroimaging Initiative (n = 921), afterwards specializing the CNN to discriminate between MS patients (n = 76) and healthy controls (n = 71). Using LRP, we then produced a heatmap for each subject in the holdout set depicting the voxel-wise relevance for a particular classification decision. The resulting CNN model resulted in a balanced accuracy of 87.04% and an area under the curve of 96.08% in a receiver operating characteristic curve. The subsequent LRP visualization revealed that the CNN model focuses indeed on individual lesions, but also incorporates additional information such as lesion location, non-lesional white matter or gray matter areas such as the thalamus, which are established conventional and advanced MRI markers in MS. We conclude that LRP and the proposed framework have the capability to make diagnostic decisions of CNN models transparent, which could serve to justify classification decisions for clinical review, verify diagnosis-relevant features and potentially gather new disease knowledge.
Collapse
Affiliation(s)
- Fabian Eitel
- Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), Department of Psychiatry and Psychotherapy, 10117 Berlin, Germany; Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), Berlin Center for Advanced Neuroimaging, Bernstein Center for Computational Neuroscience, 10117 Berlin, Germany
| | - Emily Soehler
- Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), Department of Psychiatry and Psychotherapy, 10117 Berlin, Germany; Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), Berlin Center for Advanced Neuroimaging, Bernstein Center for Computational Neuroscience, 10117 Berlin, Germany
| | - Judith Bellmann-Strobl
- Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), NeuroCure Clinical Research Center, 10117 Berlin, Germany; Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universitt zu Berlin, Berlin Institute of Health (BIH), Experimental and Clinical Research Center, Max Delbrück Center for Molecular Medicine, 10117 Berlin, Germany
| | - Alexander U Brandt
- Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), Department of Neurology, 10117 Berlin, Germany; Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), NeuroCure Clinical Research Center, 10117 Berlin, Germany; Department of Neurology, University of California, Irvine, CA, USA
| | - Klemens Ruprecht
- Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), Department of Neurology, 10117 Berlin, Germany
| | - René M Giess
- Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), Department of Neurology, 10117 Berlin, Germany; Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), NeuroCure Clinical Research Center, 10117 Berlin, Germany
| | - Joseph Kuchling
- Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), Department of Neurology, 10117 Berlin, Germany; Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), NeuroCure Clinical Research Center, 10117 Berlin, Germany; Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universitt zu Berlin, Berlin Institute of Health (BIH), Experimental and Clinical Research Center, Max Delbrück Center for Molecular Medicine, 10117 Berlin, Germany
| | - Susanna Asseyer
- Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), Department of Neurology, 10117 Berlin, Germany; Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), NeuroCure Clinical Research Center, 10117 Berlin, Germany; Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universitt zu Berlin, Berlin Institute of Health (BIH), Experimental and Clinical Research Center, Max Delbrück Center for Molecular Medicine, 10117 Berlin, Germany
| | - Martin Weygandt
- Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), Department of Neurology, 10117 Berlin, Germany; Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), NeuroCure Clinical Research Center, 10117 Berlin, Germany
| | - John-Dylan Haynes
- Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), Berlin Center for Advanced Neuroimaging, Bernstein Center for Computational Neuroscience, 10117 Berlin, Germany; Einstein Center for Digital Future Berlin, Germany
| | - Michael Scheel
- Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), Department of Neurology, 10117 Berlin, Germany; Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), NeuroCure Clinical Research Center, 10117 Berlin, Germany; Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universitt zu Berlin, Berlin Institute of Health (BIH), Department of Neuroradiology, 10117 Berlin, Germany
| | - Friedemann Paul
- Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), Department of Neurology, 10117 Berlin, Germany; Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), NeuroCure Clinical Research Center, 10117 Berlin, Germany; Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universitt zu Berlin, Berlin Institute of Health (BIH), Experimental and Clinical Research Center, Max Delbrück Center for Molecular Medicine, 10117 Berlin, Germany; Einstein Center for Digital Future Berlin, Germany
| | - Kerstin Ritter
- Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), Department of Psychiatry and Psychotherapy, 10117 Berlin, Germany; Charité - Universitätsmedizin Berlin, Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of Health (BIH), Berlin Center for Advanced Neuroimaging, Bernstein Center for Computational Neuroscience, 10117 Berlin, Germany.
| |
Collapse
|
217
|
Wolfers T, Floris DL, Dinga R, van Rooij D, Isakoglou C, Kia SM, Zabihi M, Llera A, Chowdanayaka R, Kumar VJ, Peng H, Laidi C, Batalle D, Dimitrova R, Charman T, Loth E, Lai MC, Jones E, Baumeister S, Moessnang C, Banaschewski T, Ecker C, Dumas G, O’Muircheartaigh J, Murphy D, Buitelaar JK, Marquand AF, Beckmann CF. From pattern classification to stratification: towards conceptualizing the heterogeneity of Autism Spectrum Disorder. Neurosci Biobehav Rev 2019; 104:240-254. [DOI: 10.1016/j.neubiorev.2019.07.010] [Citation(s) in RCA: 54] [Impact Index Per Article: 10.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/15/2019] [Revised: 07/10/2019] [Accepted: 07/15/2019] [Indexed: 11/17/2022]
|
218
|
Huang X, Gong Q, Sweeney JA, Biswal BB. Progress in psychoradiology, the clinical application of psychiatric neuroimaging. Br J Radiol 2019; 92:20181000. [PMID: 31170803 PMCID: PMC6732936 DOI: 10.1259/bjr.20181000] [Citation(s) in RCA: 42] [Impact Index Per Article: 8.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/26/2018] [Revised: 05/09/2019] [Accepted: 05/21/2019] [Indexed: 02/05/2023] Open
Abstract
Psychoradiology is an emerging field that applies radiological imaging technologies to psychiatric conditions. In the past three decades, brain imaging techniques have rapidly advanced understanding of illness and treatment effects in psychiatry. Based on these advances, radiologists have become increasingly interested in applying these advances for differential diagnosis and individualized patient care selection for common psychiatric illnesses. This shift from research to clinical practice represents the beginning evolution of psychoradiology. In this review, we provide a summary of recent progress relevant to this field based on their clinical functions, namely the (1) classification and subtyping; (2) prediction and monitoring of treatment outcomes; and (3) treatment selection. In addition, we provide guidelines for the practice of psychoradiology in clinical settings and suggestions for future research to validate broader clinical applications. Given the high prevalence of psychiatric disorders and the importance of increased participation of radiologists in this field, a guide regarding advances in this field and a description of relevant clinical work flow patterns help radiologists contribute to this fast-evolving field.
Collapse
Affiliation(s)
| | | | - John A. Sweeney
- Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati, Cincinnati, USA
| | | |
Collapse
|
219
|
Duong MT, Rudie JD, Wang J, Xie L, Mohan S, Gee JC, Rauschecker AM. Convolutional Neural Network for Automated FLAIR Lesion Segmentation on Clinical Brain MR Imaging. AJNR Am J Neuroradiol 2019; 40:1282-1290. [PMID: 31345943 PMCID: PMC6697209 DOI: 10.3174/ajnr.a6138] [Citation(s) in RCA: 39] [Impact Index Per Article: 7.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2019] [Accepted: 06/17/2019] [Indexed: 12/17/2022]
Abstract
BACKGROUND AND PURPOSE Most brain lesions are characterized by hyperintense signal on FLAIR. We sought to develop an automated deep learning-based method for segmentation of abnormalities on FLAIR and volumetric quantification on clinical brain MRIs across many pathologic entities and scanning parameters. We evaluated the performance of the algorithm compared with manual segmentation and existing automated methods. MATERIALS AND METHODS We adapted a U-Net convolutional neural network architecture for brain MRIs using 3D volumes. This network was retrospectively trained on 295 brain MRIs to perform automated FLAIR lesion segmentation. Performance was evaluated on 92 validation cases using Dice scores and voxelwise sensitivity and specificity, compared with radiologists' manual segmentations. The algorithm was also evaluated on measuring total lesion volume. RESULTS Our model demonstrated accurate FLAIR lesion segmentation performance (median Dice score, 0.79) on the validation dataset across a large range of lesion characteristics. Across 19 neurologic diseases, performance was significantly higher than existing methods (Dice, 0.56 and 0.41) and approached human performance (Dice, 0.81). There was a strong correlation between the predictions of lesion volume of the algorithm compared with true lesion volume (ρ = 0.99). Lesion segmentations were accurate across a large range of image-acquisition parameters on >30 different MR imaging scanners. CONCLUSIONS A 3D convolutional neural network adapted from a U-Net architecture can achieve high automated FLAIR segmentation performance on clinical brain MR imaging across a variety of underlying pathologies and image acquisition parameters. The method provides accurate volumetric lesion data that can be incorporated into assessments of disease burden or into radiologic reports.
Collapse
Affiliation(s)
- M T Duong
- From the Department of Radiology, Hospital of the University of Pennsylvania, Philadelphia, Pennsylvania
| | - J D Rudie
- From the Department of Radiology, Hospital of the University of Pennsylvania, Philadelphia, Pennsylvania
| | - J Wang
- From the Department of Radiology, Hospital of the University of Pennsylvania, Philadelphia, Pennsylvania
| | - L Xie
- From the Department of Radiology, Hospital of the University of Pennsylvania, Philadelphia, Pennsylvania
| | - S Mohan
- From the Department of Radiology, Hospital of the University of Pennsylvania, Philadelphia, Pennsylvania
| | - J C Gee
- From the Department of Radiology, Hospital of the University of Pennsylvania, Philadelphia, Pennsylvania
| | - A M Rauschecker
- From the Department of Radiology, Hospital of the University of Pennsylvania, Philadelphia, Pennsylvania.
| |
Collapse
|
220
|
Chauhan S, Vig L, De Filippo De Grazia M, Corbetta M, Ahmad S, Zorzi M. A Comparison of Shallow and Deep Learning Methods for Predicting Cognitive Performance of Stroke Patients From MRI Lesion Images. Front Neuroinform 2019; 13:53. [PMID: 31417388 PMCID: PMC6684739 DOI: 10.3389/fninf.2019.00053] [Citation(s) in RCA: 29] [Impact Index Per Article: 5.8] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2019] [Accepted: 07/04/2019] [Indexed: 01/17/2023] Open
Abstract
Stroke causes behavioral deficits in multiple cognitive domains and there is a growing interest in predicting patient performance from neuroimaging data using machine learning techniques. Here, we investigated a deep learning approach based on convolutional neural networks (CNNs) for predicting the severity of language disorder from 3D lesion images from magnetic resonance imaging (MRI) in a heterogeneous sample of stroke patients. CNN performance was compared to that of conventional (shallow) machine learning methods, including ridge regression (RR) on the images' principal components and support vector regression. We also devised a hybrid method based on re-using CNN's high-level features as additional input to the RR model. Predictive accuracy of the four different methods was further investigated in relation to the size of the training set and the level of redundancy across lesion images in the dataset, which was evaluated in terms of location and topological properties of the lesions. The Hybrid model achieved the best performance in most cases, thereby suggesting that the high-level features extracted by CNNs are complementary to principal component analysis features and improve the model's predictive accuracy. Moreover, our analyses indicate that both the size of training data and image redundancy are critical factors in determining the accuracy of a computational model in predicting behavioral outcome from the structural brain imaging data of stroke patients.
Collapse
Affiliation(s)
- Sucheta Chauhan
- School of Computational and Integrative Sciences, Jawaharlal Nehru University, New Delhi, India
| | | | | | - Maurizio Corbetta
- Department of Neurosciences, Padova Neuroscience Center, University of Padova, Padua, Italy
- Department of Neurology, Washington University School of Medicine, St. Louis, MO, United States
| | - Shandar Ahmad
- School of Computational and Integrative Sciences, Jawaharlal Nehru University, New Delhi, India
| | - Marco Zorzi
- Department of General Psychology, Padova Neuroscience Center, University of Padova, Padua, Italy
- IRCCS San Camillo Hospital, Venice, Italy
| |
Collapse
|
221
|
Böhle M, Eitel F, Weygandt M, Ritter K. Layer-Wise Relevance Propagation for Explaining Deep Neural Network Decisions in MRI-Based Alzheimer's Disease Classification. Front Aging Neurosci 2019; 11:194. [PMID: 31417397 PMCID: PMC6685087 DOI: 10.3389/fnagi.2019.00194] [Citation(s) in RCA: 79] [Impact Index Per Article: 15.8] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2019] [Accepted: 07/15/2019] [Indexed: 12/16/2022] Open
Abstract
Deep neural networks have led to state-of-the-art results in many medical imaging tasks including Alzheimer's disease (AD) detection based on structural magnetic resonance imaging (MRI) data. However, the network decisions are often perceived as being highly non-transparent, making it difficult to apply these algorithms in clinical routine. In this study, we propose using layer-wise relevance propagation (LRP) to visualize convolutional neural network decisions for AD based on MRI data. Similarly to other visualization methods, LRP produces a heatmap in the input space indicating the importance/relevance of each voxel contributing to the final classification outcome. In contrast to susceptibility maps produced by guided backpropagation ("Which change in voxels would change the outcome most?"), the LRP method is able to directly highlight positive contributions to the network classification in the input space. In particular, we show that (1) the LRP method is very specific for individuals ("Why does this person have AD?") with high inter-patient variability, (2) there is very little relevance for AD in healthy controls and (3) areas that exhibit a lot of relevance correlate well with what is known from literature. To quantify the latter, we compute size-corrected metrics of the summed relevance per brain area, e.g., relevance density or relevance gain. Although these metrics produce very individual "fingerprints" of relevance patterns for AD patients, a lot of importance is put on areas in the temporal lobe including the hippocampus. After discussing several limitations such as sensitivity toward the underlying model and computation parameters, we conclude that LRP might have a high potential to assist clinicians in explaining neural network decisions for diagnosing AD (and potentially other diseases) based on structural MRI data.
Collapse
Affiliation(s)
- Moritz Böhle
- Berlin Institute of Health, Charité—Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany
- Department of Psychiatry and Psychotherapy, Bernstein Center for Computational Neuroscience, Berlin, Germany
| | - Fabian Eitel
- Berlin Institute of Health, Charité—Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany
- Department of Psychiatry and Psychotherapy, Bernstein Center for Computational Neuroscience, Berlin, Germany
| | - Martin Weygandt
- Berlin Institute of Health, Charité—Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany
- Excellence Cluster NeuroCure Berlin, Berlin, Germany
| | - Kerstin Ritter
- Berlin Institute of Health, Charité—Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany
- Department of Psychiatry and Psychotherapy, Bernstein Center for Computational Neuroscience, Berlin, Germany
| |
Collapse
|
222
|
Duong MT, Rauschecker AM, Rudie JD, Chen PH, Cook TS, Bryan RN, Mohan S. Artificial intelligence for precision education in radiology. Br J Radiol 2019; 92:20190389. [PMID: 31322909 DOI: 10.1259/bjr.20190389] [Citation(s) in RCA: 80] [Impact Index Per Article: 16.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/07/2023] Open
Abstract
In the era of personalized medicine, the emphasis of health care is shifting from populations to individuals. Artificial intelligence (AI) is capable of learning without explicit instruction and has emerging applications in medicine, particularly radiology. Whereas much attention has focused on teaching radiology trainees about AI, here our goal is to instead focus on how AI might be developed to better teach radiology trainees. While the idea of using AI to improve education is not new, the application of AI to medical and radiological education remains very limited. Based on the current educational foundation, we highlight an AI-integrated framework to augment radiology education and provide use case examples informed by our own institution's practice. The coming age of "AI-augmented radiology" may enable not only "precision medicine" but also what we describe as "precision medical education," where instruction is tailored to individual trainees based on their learning styles and needs.
Collapse
Affiliation(s)
- Michael Tran Duong
- Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.,Department of Radiology, University of Pennsylvania, Philadelphia, PA, USA
| | - Andreas M Rauschecker
- Department of Radiology, University of Pennsylvania, Philadelphia, PA, USA.,Department of Radiology & Biomedical Imaging, University of California San Francisco, San Francisco, CA, USA
| | - Jeffrey D Rudie
- Department of Radiology, University of Pennsylvania, Philadelphia, PA, USA.,Department of Radiology & Biomedical Imaging, University of California San Francisco, San Francisco, CA, USA
| | - Po-Hao Chen
- Imaging Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Tessa S Cook
- Department of Radiology, University of Pennsylvania, Philadelphia, PA, USA
| | - R Nick Bryan
- Department of Radiology, University of Pennsylvania, Philadelphia, PA, USA.,Department of Diagnostic Medicine, Dell Medical School, University of Texas at Austin, Austin, TX, USA
| | - Suyash Mohan
- Department of Radiology, University of Pennsylvania, Philadelphia, PA, USA.,Department of Neurosurgery, University of Pennsylvania, Philadelphia, PA, USA
| |
Collapse
|
223
|
Wee CY, Liu C, Lee A, Poh JS, Ji H, Qiu A. Cortical graph neural network for AD and MCI diagnosis and transfer learning across populations. Neuroimage Clin 2019; 23:101929. [PMID: 31491832 PMCID: PMC6627731 DOI: 10.1016/j.nicl.2019.101929] [Citation(s) in RCA: 44] [Impact Index Per Article: 8.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/15/2019] [Revised: 06/02/2019] [Accepted: 07/02/2019] [Indexed: 01/18/2023]
Abstract
Combining machine learning with neuroimaging data has a great potential for early diagnosis of mild cognitive impairment (MCI) and Alzheimer's disease (AD). However, it remains unclear how well the classifiers built on one population can predict MCI/AD diagnosis of other populations. This study aimed to employ a spectral graph convolutional neural network (graph-CNN), that incorporated cortical thickness and geometry, to identify MCI and AD based on 3089 T1-weighted MRI data of the ADNI-2 cohort, and to evaluate its feasibility to predict AD in the ADNI-1 cohort (n = 3602) and an Asian cohort (n = 347). For the ADNI-2 cohort, the graph-CNN showed classification accuracy of controls (CN) vs. AD at 85.8% and early MCI (EMCI) vs. AD at 79.2%, followed by CN vs. late MCI (LMCI) (69.3%), LMCI vs. AD (65.2%), EMCI vs. LMCI (60.9%), and CN vs. EMCI (51.8%). We demonstrated the robustness of the graph-CNN among the existing deep learning approaches, such as Euclidean-domain-based multilayer network and 1D CNN on cortical thickness, and 2D and 3D CNNs on T1-weighted MR images of the ADNI-2 cohort. The graph-CNN also achieved the prediction on the conversion of EMCI to AD at 75% and that of LMCI to AD at 92%. The find-tuned graph-CNN further provided a promising CN vs. AD classification accuracy of 89.4% on the ADNI-1 cohort and >90% on the Asian cohort. Our study demonstrated the feasibility to transfer AD/MCI classifiers learned from one population to the other. Notably, incorporating cortical geometry in CNN has the potential to improve classification performance.
Collapse
Affiliation(s)
- Chong-Yaw Wee
- Department of Biomedical Engineering and Clinical Research Center, National University of Singapore, Singapore
| | - Chaoqiang Liu
- Department of Biomedical Engineering and Clinical Research Center, National University of Singapore, Singapore
| | - Annie Lee
- Department of Biomedical Engineering and Clinical Research Center, National University of Singapore, Singapore
| | - Joann S Poh
- Department of Biomedical Engineering and Clinical Research Center, National University of Singapore, Singapore
| | - Hui Ji
- Department of Mathematics, National University of Singapore, Singapore
| | - Anqi Qiu
- Department of Biomedical Engineering and Clinical Research Center, National University of Singapore, Singapore.
| |
Collapse
|
224
|
Martinez-Murcia FJ, Ortiz A, Gorriz JM, Ramirez J, Castillo-Barnes D. Studying the Manifold Structure of Alzheimer's Disease: A Deep Learning Approach Using Convolutional Autoencoders. IEEE J Biomed Health Inform 2019; 24:17-26. [PMID: 31217131 DOI: 10.1109/jbhi.2019.2914970] [Citation(s) in RCA: 67] [Impact Index Per Article: 13.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
Abstract
Many classical machine learning techniques have been used to explore Alzheimer's disease (AD), evolving from image decomposition techniques such as principal component analysis toward higher complexity, non-linear decomposition algorithms. With the arrival of the deep learning paradigm, it has become possible to extract high-level abstract features directly from MRI images that internally describe the distribution of data in low-dimensional manifolds. In this work, we try a new exploratory data analysis of AD based on deep convolutional autoencoders. We aim at finding links between cognitive symptoms and the underlying neurodegeneration process by fusing the information of neuropsychological test outcomes, diagnoses, and other clinical data with the imaging features extracted solely via a data-driven decomposition of MRI. The distribution of the extracted features in different combinations is then analyzed and visualized using regression and classification analysis, and the influence of each coordinate of the autoencoder manifold over the brain is estimated. The imaging-derived markers could then predict clinical variables with correlations above 0.6 in the case of neuropsychological evaluation variables such as the MMSE or the ADAS11 scores, achieving a classification accuracy over 80% for the diagnosis of AD.
Collapse
|
225
|
Bouts MJRJ, van der Grond J, Vernooij MW, Koini M, Schouten TM, de Vos F, Feis RA, Cremers LGM, Lechner A, Schmidt R, de Rooij M, Niessen WJ, Ikram MA, Rombouts SARB. Detection of mild cognitive impairment in a community-dwelling population using quantitative, multiparametric MRI-based classification. Hum Brain Mapp 2019; 40:2711-2722. [PMID: 30803110 PMCID: PMC6563478 DOI: 10.1002/hbm.24554] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2018] [Revised: 01/30/2019] [Accepted: 02/09/2019] [Indexed: 01/18/2023] Open
Abstract
Early and accurate mild cognitive impairment (MCI) detection within a heterogeneous, nonclinical population is needed to improve care for persons at risk of developing dementia. Magnetic resonance imaging (MRI)-based classification may aid early diagnosis of MCI, but has only been applied within clinical cohorts. We aimed to determine the generalizability of MRI-based classification probability scores to detect MCI on an individual basis within a general population. To determine classification probability scores, an AD, mild-AD, and moderate-AD detection model were created with anatomical and diffusion MRI measures calculated from a clinical Alzheimer's Disease (AD) cohort and subsequently applied to a population-based cohort with 48 MCI and 617 normal aging subjects. Each model's ability to detect MCI was quantified using area under the receiver operating characteristic curve (AUC) and compared with an MCI detection model trained and applied to the population-based cohort. The AD-model and mild-AD identified MCI from controls better than chance level (AUC = 0.600, p = 0.025; AUC = 0.619, p = 0.008). In contrast, the moderate-AD-model was not able to separate MCI from normal aging (AUC = 0.567, p = 0.147). The MCI-model was able to separate MCI from controls better than chance (p = 0.014) with mean AUC values comparable with the AD-model (AUC = 0.611, p = 1.0). Within our population-based cohort, classification models detected MCI better than chance. Nevertheless, classification performance rates were moderate and may be insufficient to facilitate robust MRI-based MCI detection on an individual basis. Our data indicate that multiparametric MRI-based classification algorithms, that are effective in clinical cohorts, may not straightforwardly translate to applications in a general population.
Collapse
Affiliation(s)
- Mark J. R. J. Bouts
- Institute of PsychologyLeiden UniversityLeidenthe Netherlands
- Department of RadiologyLeiden University Medical CenterLeidenthe Netherlands
- Leiden Institute for Brain and CognitionLeiden UniversityLeidenthe Netherlands
| | | | - Meike W. Vernooij
- Department of EpidemiologyErasmus MC University Medical CenterRotterdamthe Netherlands
- Department of Radiology and Nuclear MedicineErasmus MC University Medical CenterRotterdamthe Netherlands
| | - Marisa Koini
- Department of NeurologyMedical University of GrazAustria
| | - Tijn M. Schouten
- Institute of PsychologyLeiden UniversityLeidenthe Netherlands
- Department of RadiologyLeiden University Medical CenterLeidenthe Netherlands
- Leiden Institute for Brain and CognitionLeiden UniversityLeidenthe Netherlands
| | - Frank de Vos
- Institute of PsychologyLeiden UniversityLeidenthe Netherlands
- Department of RadiologyLeiden University Medical CenterLeidenthe Netherlands
- Leiden Institute for Brain and CognitionLeiden UniversityLeidenthe Netherlands
| | - Rogier A. Feis
- Department of RadiologyLeiden University Medical CenterLeidenthe Netherlands
- Leiden Institute for Brain and CognitionLeiden UniversityLeidenthe Netherlands
| | - Lotte G. M. Cremers
- Department of EpidemiologyErasmus MC University Medical CenterRotterdamthe Netherlands
- Department of Radiology and Nuclear MedicineErasmus MC University Medical CenterRotterdamthe Netherlands
| | - Anita Lechner
- Department of NeurologyMedical University of GrazAustria
| | | | - Mark de Rooij
- Institute of PsychologyLeiden UniversityLeidenthe Netherlands
- Leiden Institute for Brain and CognitionLeiden UniversityLeidenthe Netherlands
| | - Wiro J. Niessen
- Department of Radiology and Nuclear MedicineErasmus MC University Medical CenterRotterdamthe Netherlands
- Department of Medical InformaticsErasmus MC University Medical CenterRotterdamthe Netherlands
- Faculty of Applied SciencesDelft University of TechnologyDelftthe Netherlands
| | - M. Arfan Ikram
- Department of EpidemiologyErasmus MC University Medical CenterRotterdamthe Netherlands
- Department of Radiology and Nuclear MedicineErasmus MC University Medical CenterRotterdamthe Netherlands
- Department of NeurologyErasmus MC University Medical CenterRotterdamthe Netherlands
| | - Serge A. R. B. Rombouts
- Institute of PsychologyLeiden UniversityLeidenthe Netherlands
- Department of RadiologyLeiden University Medical CenterLeidenthe Netherlands
- Leiden Institute for Brain and CognitionLeiden UniversityLeidenthe Netherlands
| |
Collapse
|
226
|
Hu X, Zhang L, Bu X, Li H, Li B, Tang W, Lu L, Hu X, Tang S, Gao Y, Yang Y, Roberts N, Gong Q, Huang X. Localized Connectivity in Obsessive-Compulsive Disorder: An Investigation Combining Univariate and Multivariate Pattern Analyses. Front Behav Neurosci 2019; 13:122. [PMID: 31249515 PMCID: PMC6584748 DOI: 10.3389/fnbeh.2019.00122] [Citation(s) in RCA: 19] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/28/2018] [Accepted: 05/20/2019] [Indexed: 02/05/2023] Open
Abstract
Recent developments in psychoradiological researches have highlighted the disrupted organization of large-scale functional brain networks in obsessive-compulsive disorder (OCD). However, whether abnormal activation of localized brain areas would affect network dysfunction remains to be fully characterized. We applied both univariate analysis and multivariate pattern analysis (MVPA) approaches to investigate the abnormalities of regional homogeneity (ReHo), an index to measure the localized connectivity, in 88 medication-free patients with OCD and 88 healthy control subjects (HCS). Resting-state functional magnetic resonance imaging (RS-fMRI) data of all the participants were acquired in a 3.0-T scanner. First, we adopted a traditional univariate analysis to explore ReHo alterations between the patient group and the control group. Subsequently, we utilized a support vector machine (SVM) to examine whether ReHo could be further used to differentiate patients with OCD from HCS at the individual level. Relative to HCS, OCD patients showed lower ReHo in the bilateral cerebellum and higher ReHo in the bilateral superior frontal gyri (SFG), right inferior parietal gyrus (IPG), and precuneus [P < 0.05, family-wise error (FWE) correction]. ReHo value in the left SFG positively correlated with Yale-Brown Obsessive Compulsive Scale (Y-BOCS) total score (r = 0 0.241, P = 0.024) and obsessive subscale (r = 0.224, P = 0.036). The SVM classification regarding ReHo yielded an accuracy of 78.98% (sensitivity = 78.41%, specificity = 79.55%) with P < 0.001 after permutation testing. The most discriminative regions contributing to the SVM classification were mainly located in the frontal, temporal, and parietal regions as well as in the cerebellum while the right orbital frontal cortex was identified with the highest discriminative power. Our findings not only suggested that the localized activation disequilibrium between the prefrontal cortex (PFC) and the cerebellum appeared to be associated with the pathophysiology of OCD but also indicated the translational role of the localized connectivity as a potential discriminative pattern to detect OCD at the individual level.
Collapse
Affiliation(s)
- Xinyu Hu
- Huaxi MR Research Center (HMRRC), West China Hospital of Sichuan University, Chengdu, China
| | - Lianqing Zhang
- Huaxi MR Research Center (HMRRC), West China Hospital of Sichuan University, Chengdu, China
| | - Xuan Bu
- Huaxi MR Research Center (HMRRC), West China Hospital of Sichuan University, Chengdu, China
| | - Hailong Li
- Huaxi MR Research Center (HMRRC), West China Hospital of Sichuan University, Chengdu, China
| | - Bin Li
- Mental Health Center, West China Hospital of Sichuan University, Chengdu, China
| | - Wanjie Tang
- Mental Health Center, West China Hospital of Sichuan University, Chengdu, China
| | - Lu Lu
- Huaxi MR Research Center (HMRRC), West China Hospital of Sichuan University, Chengdu, China
| | - Xiaoxiao Hu
- Huaxi MR Research Center (HMRRC), West China Hospital of Sichuan University, Chengdu, China
| | - Shi Tang
- Huaxi MR Research Center (HMRRC), West China Hospital of Sichuan University, Chengdu, China
| | - Yingxue Gao
- Huaxi MR Research Center (HMRRC), West China Hospital of Sichuan University, Chengdu, China
| | - Yanchun Yang
- Mental Health Center, West China Hospital of Sichuan University, Chengdu, China
| | - Neil Roberts
- Clinical Research Imaging Centre (CRIC), The Queen's Medical Research Institute (QMRI), University of Edinburgh, Edinburgh, United Kingdom
| | - Qiyong Gong
- Huaxi MR Research Center (HMRRC), West China Hospital of Sichuan University, Chengdu, China
| | - Xiaoqi Huang
- Huaxi MR Research Center (HMRRC), West China Hospital of Sichuan University, Chengdu, China
| |
Collapse
|
227
|
Abstract
Sentiment analysis (SA), also known as opinion mining, is a growing important research area. Generally, it helps to automatically determine if a text expresses a positive, negative or neutral sentiment. It enables to mine the huge increasing resources of shared opinions such as social networks, review sites and blogs. In fact, SA is used by many fields and for various languages such as English and Arabic. However, since Arabic is a highly inflectional and derivational language, it raises many challenges. In fact, SA of Arabic text should handle such complex morphology. To better handle these challenges, we decided to provide the research community and Arabic users with a new efficient framework for Arabic Sentiment Analysis (ASA). Our primary goal is to improve the performance of ASA by exploiting deep learning while varying the preprocessing techniques. For that, we implement and evaluate two deep learning models namely convolutional neural network (CNN) and long short-term memory (LSTM) models. The framework offers various preprocessing techniques for ASA (including stemming, normalisation, tokenization and stop words). As a result of this work, we first provide a new rich and publicly available Arabic corpus called Moroccan Sentiment Analysis Corpus (MSAC). Second, the proposed framework demonstrates improvement in ASA. In fact, the experimental results prove that deep learning models have a better performance for ASA than classical approaches (support vector machines, naive Bayes classifiers and maximum entropy). They also show the key role of morphological features in Arabic Natural Language Processing (NLP).
Collapse
Affiliation(s)
- Ahmed Oussous
- National School of Applied Sciences (ENSA), Ibn Tofail University, Morocco
| | | | - Ayoub Ait Lahcen
- National School of Applied Sciences (ENSA), Ibn Tofail University, Morocco; LRIT, Unité associée au CNRST (URAC 29), Mohammed V-Agdal University, Morocco
| | - Samir Belfkih
- National School of Applied Sciences (ENSA), Ibn Tofail University, Morocco
| |
Collapse
|
228
|
Sossi V, Cheng JC, Klyuzhin IS. Imaging in Neurodegeneration: Movement Disorders. IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES 2019. [DOI: 10.1109/trpms.2018.2871760] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/20/2022]
|
229
|
Walter M, Alizadeh S, Jamalabadi H, Lueken U, Dannlowski U, Walter H, Olbrich S, Colic L, Kambeitz J, Koutsouleris N, Hahn T, Dwyer DB. Translational machine learning for psychiatric neuroimaging. Prog Neuropsychopharmacol Biol Psychiatry 2019; 91:113-121. [PMID: 30290208 DOI: 10.1016/j.pnpbp.2018.09.014] [Citation(s) in RCA: 38] [Impact Index Per Article: 7.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/14/2018] [Revised: 09/14/2018] [Accepted: 09/30/2018] [Indexed: 11/19/2022]
Abstract
Despite its initial promise, neuroimaging has not been widely translated into clinical psychiatry to assist in the prediction of diagnoses, prognoses, and optimal therapeutic strategies. Machine learning approaches may enhance the translational potential of neuroimaging because they specifically focus on overcoming biases by optimizing the generalizability of pipelines that measure complex brain patterns to predict targets at a single-subject level. This article introduces some fundamentals of a translational machine learning approach before selectively reviewing literature to-date. Promising initial results are then balanced by the description of limitations that should be considered in order to interpret existing research and maximize the possibility of future translation. Future directions are then presented in order to inspire further research and progress the field towards clinical translation.
Collapse
Affiliation(s)
- Martin Walter
- Department of Psychiatry and Psychotherapy, Eberhard Karls University Tuebingen, Germany.
| | - Sarah Alizadeh
- Department of Psychiatry and Psychotherapy, Eberhard Karls University Tuebingen, Germany
| | - Hamidreza Jamalabadi
- Department of Psychiatry and Psychotherapy, Eberhard Karls University Tuebingen, Germany
| | - Ulrike Lueken
- Department of Psychology, Humboldt-Universität zu Berlin, Berlin, Germany
| | - Udo Dannlowski
- Department of Psychiatry, University of Muenster, Muenster, Germany
| | - Henrik Walter
- Department of Psychiatry and Psychotherapy CCM, Charité Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt Universität zu Berlin, and Berlin Institute of Health, Berlin, Germany
| | - Sebastian Olbrich
- Department for Psychiatry, Psychotherapy and Psychosomatic Medicine, Zürich, Switzerland
| | - Lejla Colic
- Department of Behavioral Neurology, Leibniz Institute for Neurobiology, Magdeburg, Germany
| | - Joseph Kambeitz
- Department of Psychiatry and Psychotherapy, Ludwig Maximilian University, Germany
| | | | - Tim Hahn
- Department of Psychiatry, University of Muenster, Muenster, Germany
| | - Dominic B Dwyer
- Department of Psychiatry and Psychotherapy, Ludwig Maximilian University, Germany
| |
Collapse
|
230
|
Glaser JI, Benjamin AS, Farhoodi R, Kording KP. The roles of supervised machine learning in systems neuroscience. Prog Neurobiol 2019; 175:126-137. [PMID: 30738835 PMCID: PMC8454059 DOI: 10.1016/j.pneurobio.2019.01.008] [Citation(s) in RCA: 61] [Impact Index Per Article: 12.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/01/2018] [Revised: 01/23/2019] [Accepted: 01/28/2019] [Indexed: 01/18/2023]
Abstract
Over the last several years, the use of machine learning (ML) in neuroscience has been rapidly increasing. Here, we review ML's contributions, both realized and potential, across several areas of systems neuroscience. We describe four primary roles of ML within neuroscience: (1) creating solutions to engineering problems, (2) identifying predictive variables, (3) setting benchmarks for simple models of the brain, and (4) serving itself as a model for the brain. The breadth and ease of its applicability suggests that machine learning should be in the toolbox of most systems neuroscientists.
Collapse
Affiliation(s)
- Joshua I Glaser
- Department of Bioengineering, University of Pennsylvania, United States.
| | - Ari S Benjamin
- Department of Bioengineering, University of Pennsylvania, United States.
| | - Roozbeh Farhoodi
- Department of Bioengineering, University of Pennsylvania, United States.
| | - Konrad P Kording
- Department of Bioengineering, University of Pennsylvania, United States; Department of Neuroscience, University of Pennsylvania, United States; Canadian Institute for Advanced Research, Canada.
| |
Collapse
|
231
|
A Novel Texture Extraction Technique with T1 Weighted MRI for the Classification of Alzheimer’s Disease. J Neurosci Methods 2019; 318:84-99. [DOI: 10.1016/j.jneumeth.2019.01.011] [Citation(s) in RCA: 25] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2018] [Revised: 01/19/2019] [Accepted: 01/19/2019] [Indexed: 02/06/2023]
|
232
|
Girault JB, Munsell BC, Puechmaille D, Goldman BD, Prieto JC, Styner M, Gilmore JH. White matter connectomes at birth accurately predict cognitive abilities at age 2. Neuroimage 2019; 192:145-155. [PMID: 30825656 DOI: 10.1016/j.neuroimage.2019.02.060] [Citation(s) in RCA: 37] [Impact Index Per Article: 7.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/07/2018] [Revised: 02/18/2019] [Accepted: 02/22/2019] [Indexed: 12/14/2022] Open
Abstract
Cognitive ability is an important predictor of mental health outcomes that is influenced by neurodevelopment. Evidence suggests that the foundational wiring of the human brain is in place by birth, and that the white matter (WM) connectome supports developing brain function. It is unknown, however, how the WM connectome at birth supports emergent cognition. In this study, a deep learning model was trained using cross-validation to classify full-term infants (n = 75) as scoring above or below the median at age 2 using WM connectomes generated from diffusion weighted magnetic resonance images at birth. Results from this model were used to predict individual cognitive scores. We additionally identified WM connections important for classification. The model was also evaluated in a separate set of preterm infants (n = 37) scanned at term-age equivalent. Findings revealed that WM connectomes at birth predicted 2-year cognitive score group with high accuracy in both full-term (89.5%) and preterm (83.8%) infants. Scores predicted by the model were strongly correlated with actual scores (r = 0.98 for full-term and r = 0.96 for preterm). Connections within the frontal lobe, and between the frontal lobe and other brain areas were found to be important for classification. This work suggests that WM connectomes at birth can accurately predict a child's 2-year cognitive group and individual score in full-term and preterm infants. The WM connectome at birth appears to be a useful neuroimaging biomarker of subsequent cognitive development that deserves further study.
Collapse
Affiliation(s)
- Jessica B Girault
- Department of Psychiatry, UNC Chapel Hill, Chapel Hill, NC, 27599, USA
| | - Brent C Munsell
- Department of Computer Science, College of Charleston, Charleston, SC, 29424, USA
| | | | - Barbara D Goldman
- Department of Psychology & Neuroscience, UNC Chapel Hill, Chapel Hill, NC, 27599, USA
| | - Juan C Prieto
- Department of Psychiatry, UNC Chapel Hill, Chapel Hill, NC, 27599, USA
| | - Martin Styner
- Department of Psychiatry, UNC Chapel Hill, Chapel Hill, NC, 27599, USA
| | - John H Gilmore
- Department of Psychiatry, UNC Chapel Hill, Chapel Hill, NC, 27599, USA.
| |
Collapse
|
233
|
Lin LC, Ouyang CS, Wu RC, Yang RC, Chiang CT. Alternative Diagnosis of Epilepsy in Children Without Epileptiform Discharges Using Deep Convolutional Neural Networks. Int J Neural Syst 2019; 30:1850060. [DOI: 10.1142/s0129065718500600] [Citation(s) in RCA: 25] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/10/2023]
Abstract
Numerous nonepileptic paroxysmal events, such as syncope and psychogenic nonepileptic seizures, may imitate seizures and impede diagnosis. Misdiagnosis can lead to mistreatment, affecting patients’ lives considerably. Electroencephalography is commonly used for diagnosing epilepsy. Although on electroencephalograms (EEGs), epileptiform discharges (ED) specifically indicate epilepsy, only approximately 50% of patients with epilepsy have ED in their first EEG. In this study, we developed a deep convolutional neural network (ConvNet)-based classifier to distinguish EEG between patients with epilepsy without ED and controls. Overall, 25 patients with epilepsy without ED in their EEGs and 25 age-matched patients with Tourette syndrome or syncope were enrolled. Their EEGs were classified using the deep ConvNet. When the EEG data without overlapping were used, the accuracy, sensitivity, and specificity were 65.00%, 48.00%, and 82.00%, respectively. The performance measures improved when the input EEG data were augmented through overlapping. With 95% EEG data overlapping, the accuracy, sensitivity, and specificity increased to 80.00%, 70.00%, and 90.00%, respectively. The proposed method could be regarded as a pilot study to demonstrate a proof of concept of a potential diagnostic value of deep ConvNet in patients with epilepsy without ED. Further studies are needed to assist neurologists in distinguishing nonepileptic paroxysmal events from epilepsy.
Collapse
Affiliation(s)
- Lung-Chang Lin
- Department of Pediatrics, School of Medicine, College of Medicine, Kaohsiung Medical University Hospital Kaohsiung, Medical University, 100, Shih-Chuan 1st Road, Kaohsiung 80708, Taiwan
| | - Chen-Sen Ouyang
- Department of Information Engineering, I-Shou University, No. 1, Section 1, Syuecheng Road, Dashu District, Kaohsiung 84001, Taiwan
| | - Rong-Ching Wu
- Departments of Electrical Engineering, I-Shou University, No. 1, Section 1, Syuecheng Road, Dashu District, Kaohsiung 84001, Taiwan
| | - Rei-Cheng Yang
- Department of Pediatrics, School of Medicine, College of Medicine, Kaohsiung Medical University Hospital Kaohsiung, Medical University, 100, Shih-Chuan 1st Road, Kaohsiung 80708, Taiwan
| | - Ching-Tai Chiang
- Department of Computer and Communication, National Pingtung University, 51 Min Sheng East Road, Pingtung, 90003, Taiwan
| |
Collapse
|
234
|
Zhu Y, Qi S, Zhang B, He D, Teng Y, Hu J, Wei X. Connectome-Based Biomarkers Predict Subclinical Depression and Identify Abnormal Brain Connections With the Lateral Habenula and Thalamus. Front Psychiatry 2019; 10:371. [PMID: 31244688 PMCID: PMC6581735 DOI: 10.3389/fpsyt.2019.00371] [Citation(s) in RCA: 41] [Impact Index Per Article: 8.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/07/2018] [Accepted: 05/13/2019] [Indexed: 01/13/2023] Open
Abstract
Subclinical depression (SD) has been considered as the precursor to major depressive disorder. Accurate prediction of SD and identification of its etiological origin are urgent. Bursts within the lateral habenula (LHb) drive depression in rats, but whether dysfunctional LHb is associated with SD in human is unknown. Here we develop connectome-based biomarkers which predict SD and identify dysfunctional brain regions and connections. T1 weighted images and resting-state functional MRI (fMRI) data were collected from 34 subjects with SD and 40 healthy controls (HCs). After the brain is parcellated into 48 brain regions (246 subregions) using the human Brainnetome Atlas, the functional network of each participant is constructed by calculating the correlation coefficient for the time series of fMRI signals of each pair of subregions. Initial candidates of abnormal connections are identified by the two-sample t-test and input into Support Vector Machine models as features. A total of 24 anatomical-region-based models, 231 sliding-window-based models, and 100 random-selection-based models are built. The performance of these models is estimated through leave-one-out cross-validation and evaluated by measures of accuracy, sensitivity, confusion matrix, receiver operating characteristic curve, and the area under the curve (AUC). After confirming the region with the highest accuracy, subregions within the thalamus and connections associated with subregions of LHb are compared. It is found that five prediction models using connections of the thalamus, posterior superior temporal sulcus, cingulate gyrus, superior parietal lobule, and superior frontal gyrus achieve an accuracy >0.9 and an AUC >0.93. Among 90 abnormal connections associated with the thalamus, the subregion of the right posterior parietal thalamus where LHb is located has the most connections (n = 18), the left subregion only has 3 connections. In SD group, 10 subregions in the thalamus have significantly different node degrees with those in the HC group, while 8 subregions have lower degrees ( p < 0.01), including the one with LHb. These results implicate abnormal brain connections associated with the thalamus and LHb to be associated with SD. Integration of these connections by machine learning can provide connectome-based biomarkers to accurately diagnose SD.
Collapse
Affiliation(s)
- Yunkai Zhu
- Sino-Dutch Biomedical and Information Engineering School, Northeastern University, Shenyang, China
| | - Shouliang Qi
- Sino-Dutch Biomedical and Information Engineering School, Northeastern University, Shenyang, China.,Key Laboratory of Medical Image Computing of Northeastern University (Ministry of Education), Shenyang, China
| | - Bo Zhang
- Sino-Dutch Biomedical and Information Engineering School, Northeastern University, Shenyang, China
| | - Dianning He
- Sino-Dutch Biomedical and Information Engineering School, Northeastern University, Shenyang, China
| | - Yueyang Teng
- Sino-Dutch Biomedical and Information Engineering School, Northeastern University, Shenyang, China.,Key Laboratory of Medical Image Computing of Northeastern University (Ministry of Education), Shenyang, China
| | - Jiani Hu
- Department of Radiology, Wayne State University, Detroit, United States
| | - Xinhua Wei
- Department of Radiology, Guangzhou First People's Hospital, School of Medicine, South China University of Technology, Guangzhou, China
| |
Collapse
|
235
|
Tulay EE, Metin B, Tarhan N, Arıkan MK. Multimodal Neuroimaging: Basic Concepts and Classification of Neuropsychiatric Diseases. Clin EEG Neurosci 2019; 50:20-33. [PMID: 29925268 DOI: 10.1177/1550059418782093] [Citation(s) in RCA: 36] [Impact Index Per Article: 7.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/08/2023]
Abstract
Neuroimaging techniques are widely used in neuroscience to visualize neural activity, to improve our understanding of brain mechanisms, and to identify biomarkers-especially for psychiatric diseases; however, each neuroimaging technique has several limitations. These limitations led to the development of multimodal neuroimaging (MN), which combines data obtained from multiple neuroimaging techniques, such as electroencephalography, functional magnetic resonance imaging, and yields more detailed information about brain dynamics. There are several types of MN, including visual inspection, data integration, and data fusion. This literature review aimed to provide a brief summary and basic information about MN techniques (data fusion approaches in particular) and classification approaches. Data fusion approaches are generally categorized as asymmetric and symmetric. The present review focused exclusively on studies based on symmetric data fusion methods (data-driven methods), such as independent component analysis and principal component analysis. Machine learning techniques have recently been introduced for use in identifying diseases and biomarkers of disease. The machine learning technique most widely used by neuroscientists is classification-especially support vector machine classification. Several studies differentiated patients with psychiatric diseases and healthy controls with using combined datasets. The common conclusion among these studies is that the prediction of diseases increases when combining data via MN techniques; however, there remain a few challenges associated with MN, such as sample size. Perhaps in the future N-way fusion can be used to combine multiple neuroimaging techniques or nonimaging predictors (eg, cognitive ability) to overcome the limitations of MN.
Collapse
Affiliation(s)
| | | | - Nevzat Tarhan
- 1 Uskudar University, Istanbul, Turkey.,2 NPIstanbul Hospital, Istanbul, Turkey
| | | |
Collapse
|
236
|
Classification of Schizophrenia Patients and Healthy Controls Using ICA of Complex-Valued fMRI Data and Convolutional Neural Networks. ADVANCES IN NEURAL NETWORKS – ISNN 2019 2019. [DOI: 10.1007/978-3-030-22808-8_53] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
|
237
|
Reus VI, Lindqvist D. Psychiatric manifestations of neurologic diseases: Etiology, phenomenology, and treatment. HANDBOOK OF CLINICAL NEUROLOGY 2019; 165:1-4. [PMID: 31727208 DOI: 10.1016/b978-0-444-64012-3.00001-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/10/2023]
Abstract
Understanding the etiology and meaning of behavioral symptomatology in the context of neurologic disease, and choosing the most effective intervention is a vexing task. This introduction summarizes the history of our understanding of the relationship between behavioral symptoms and primary neurologic conditions, and considers the ways in which both psychiatric and neurologic disorders occurring simultaneously may inform both knowledge of etiology and treatment decisions.
Collapse
Affiliation(s)
- Victor I Reus
- Department of Psychiatry, University of California, San Francisco (UCSF) School of Medicine, San Francisco, CA, United States.
| | | |
Collapse
|
238
|
Development of Neuroimaging-Based Biomarkers in Psychiatry. ADVANCES IN EXPERIMENTAL MEDICINE AND BIOLOGY 2019; 1192:159-195. [PMID: 31705495 DOI: 10.1007/978-981-32-9721-0_9] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Abstract
This chapter presents an overview of accumulating neuroimaging data with emphasis on translational potential. The subject will be described in the context of three disease states, i.e., schizophrenia, bipolar disorder, and major depressive disorder, and for three clinical goals, i.e., disease risk assessment, subtyping, and treatment decision.
Collapse
|
239
|
Basaia S, Agosta F, Wagner L, Canu E, Magnani G, Santangelo R, Filippi M. Automated classification of Alzheimer's disease and mild cognitive impairment using a single MRI and deep neural networks. Neuroimage Clin 2018; 21:101645. [PMID: 30584016 PMCID: PMC6413333 DOI: 10.1016/j.nicl.2018.101645] [Citation(s) in RCA: 199] [Impact Index Per Article: 33.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/17/2018] [Revised: 11/21/2018] [Accepted: 12/15/2018] [Indexed: 10/27/2022]
Abstract
We built and validated a deep learning algorithm predicting the individual diagnosis of Alzheimer's disease (AD) and mild cognitive impairment who will convert to AD (c-MCI) based on a single cross-sectional brain structural MRI scan. Convolutional neural networks (CNNs) were applied on 3D T1-weighted images from ADNI and subjects recruited at our Institute (407 healthy controls [HC], 418 AD, 280 c-MCI, 533 stable MCI [s-MCI]). CNN performance was tested in distinguishing AD, c-MCI and s-MCI. High levels of accuracy were achieved in all the classifications, with the highest rates achieved in the AD vs HC classification tests using both the ADNI dataset only (99%) and the combined ADNI + non-ADNI dataset (98%). CNNs discriminated c-MCI from s-MCI patients with an accuracy up to 75% and no difference between ADNI and non-ADNI images. CNNs provide a powerful tool for the automatic individual patient diagnosis along the AD continuum. Our method performed well without any prior feature engineering and regardless the variability of imaging protocols and scanners, demonstrating that it is exploitable by not-trained operators and likely to be generalizable to unseen patient data. CNNs may accelerate the adoption of structural MRI in routine practice to help assessment and management of patients.
Collapse
Affiliation(s)
- Silvia Basaia
- Neuroimaging Research Unit, Institute of Experimental Neurology, Division of Neuroscience, San Raffaele Scientific Institute, Vita-Salute San Raffaele University, Milan, Italy
| | - Federica Agosta
- Neuroimaging Research Unit, Institute of Experimental Neurology, Division of Neuroscience, San Raffaele Scientific Institute, Vita-Salute San Raffaele University, Milan, Italy
| | | | - Elisa Canu
- Neuroimaging Research Unit, Institute of Experimental Neurology, Division of Neuroscience, San Raffaele Scientific Institute, Vita-Salute San Raffaele University, Milan, Italy
| | - Giuseppe Magnani
- Department of Neurology, Institute of Experimental Neurology, Division of Neuroscience, San Raffaele Scientific Institute, Vita-Salute San Raffaele University, Milan, Italy
| | - Roberto Santangelo
- Department of Neurology, Institute of Experimental Neurology, Division of Neuroscience, San Raffaele Scientific Institute, Vita-Salute San Raffaele University, Milan, Italy
| | - Massimo Filippi
- Neuroimaging Research Unit, Institute of Experimental Neurology, Division of Neuroscience, San Raffaele Scientific Institute, Vita-Salute San Raffaele University, Milan, Italy; Department of Neurology, Institute of Experimental Neurology, Division of Neuroscience, San Raffaele Scientific Institute, Vita-Salute San Raffaele University, Milan, Italy.
| |
Collapse
|
240
|
Lundervold AS, Lundervold A. An overview of deep learning in medical imaging focusing on MRI. Z Med Phys 2018; 29:102-127. [PMID: 30553609 DOI: 10.1016/j.zemedi.2018.11.002] [Citation(s) in RCA: 713] [Impact Index Per Article: 118.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/02/2018] [Revised: 11/19/2018] [Accepted: 11/21/2018] [Indexed: 02/06/2023]
Abstract
What has happened in machine learning lately, and what does it mean for the future of medical image analysis? Machine learning has witnessed a tremendous amount of attention over the last few years. The current boom started around 2009 when so-called deep artificial neural networks began outperforming other established models on a number of important benchmarks. Deep neural networks are now the state-of-the-art machine learning models across a variety of areas, from image analysis to natural language processing, and widely deployed in academia and industry. These developments have a huge potential for medical imaging technology, medical data analysis, medical diagnostics and healthcare in general, slowly being realized. We provide a short overview of recent advances and some associated challenges in machine learning applied to medical image processing and image analysis. As this has become a very broad and fast expanding field we will not survey the entire landscape of applications, but put particular focus on deep learning in MRI. Our aim is threefold: (i) give a brief introduction to deep learning with pointers to core references; (ii) indicate how deep learning has been applied to the entire MRI processing chain, from acquisition to image retrieval, from segmentation to disease prediction; (iii) provide a starting point for people interested in experimenting and perhaps contributing to the field of deep learning for medical imaging by pointing out good educational resources, state-of-the-art open-source code, and interesting sources of data and problems related medical imaging.
Collapse
Affiliation(s)
- Alexander Selvikvåg Lundervold
- Mohn Medical Imaging and Visualization Centre (MMIV), Haukeland University Hospital, Norway; Department of Computing, Mathematics and Physics, Western Norway University of Applied Sciences, Norway.
| | - Arvid Lundervold
- Mohn Medical Imaging and Visualization Centre (MMIV), Haukeland University Hospital, Norway; Neuroinformatics and Image Analysis Laboratory, Department of Biomedicine, University of Bergen, Norway; Department of Health and Functioning, Western Norway University of Applied Sciences, Norway.
| |
Collapse
|
241
|
Miller JB. Big data and biomedical informatics: Preparing for the modernization of clinical neuropsychology. Clin Neuropsychol 2018; 33:287-304. [PMID: 30513257 DOI: 10.1080/13854046.2018.1523466] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/27/2022]
Abstract
OBJECTIVE Neuropsychology is poised for a fundamental shift as we modernize the ways in which behavior is measured. The amount and complexity of data generated by these new methods will be several orders of magnitude greater than what is currently created by analog measures and will quickly adopt characteristics of "Big Data." Adequate preparation for managing the influx of data will be critical for technology integration and modernization to be successful. Drawing from information technology, mathematics, statistics, computer science, and engineering, as well as, biology, genetics, and medicine, the field of biomedical informatics has rapidly evolved from its early days in computational biology to a burgeoning independent discipline that has much to offer neuropsychology. METHOD Following a critical review of the relevant literature, the present article (1) provides an introductory overview of biomedical informatics and how these concepts are relevant to neuropsychology; (2) describes how biomedical informatics applications can be utilized to leverage existing data sources more effectively; and (3) discusses ideas for future developments designed to facilitate integration of new data derived from novel, technologically driven measurement tools. Within this context, applications intended for use by both the individual neuropsychologist to increase clinical efficiencies, as well as, larger field-wide initiatives intended to generate new information and derive new knowledge are discussed. CONCLUSIONS By no means a comprehensive review of biomedical informatics, the present paper highlights that our approach to data needs to become a multidisciplinary endeavor in order to develop applications capable of effectively utilizing modern data sources.
Collapse
Affiliation(s)
- Justin B Miller
- a Cleveland Clinic Lou Ruvo Center for Brain Health , Las Vegas , Nevada , USA
| |
Collapse
|
242
|
Vakli P, Deák-Meszlényi RJ, Hermann P, Vidnyánszky Z. Transfer learning improves resting-state functional connectivity pattern analysis using convolutional neural networks. Gigascience 2018; 7:5160132. [PMID: 30395218 PMCID: PMC6283213 DOI: 10.1093/gigascience/giy130] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/19/2018] [Accepted: 10/24/2018] [Indexed: 12/15/2022] Open
Abstract
Background Deep learning is gaining importance in the prediction of cognitive states and brain pathology based on neuroimaging data. Including multiple hidden layers in artificial neural networks enables unprecedented predictive power; however, the proper training of deep neural networks requires thousands of exemplars. Collecting this amount of data is not feasible in typical neuroimaging experiments. A handy solution to this problem, which has largely fallen outside the scope of deep learning applications in neuroimaging, is to repurpose deep networks that have already been trained on large datasets by fine-tuning them to target datasets/tasks with fewer exemplars. Here, we investigated how this method, called transfer learning, can aid age category classification and regression based on brain functional connectivity patterns derived from resting-state functional magnetic resonance imaging. We trained a connectome-convolutional neural network on a larger public dataset and then examined how the knowledge learned can be used effectively to perform these tasks on smaller target datasets collected with a different type of scanner and/or imaging protocol and pre-processing pipeline. Results Age classification on the target datasets benefitted from transfer learning. Significant improvement (∼9%–13% increase in accuracy) was observed when the convolutional layers’ weights were initialized based on the values learned on the public dataset and then fine-tuned to the target datasets. Transfer learning also appeared promising in improving the otherwise poor prediction of chronological age. Conclusions Transfer learning is a plausible solution to adapt convolutional neural networks to neuroimaging data with few exemplars and different data acquisition and pre-processing protocols.
Collapse
Affiliation(s)
- Pál Vakli
- Brain Imaging Centre, Research Centre for Natural Sciences, Hungarian Academy of Sciences, Magyar tudósok körútja 2., 1117 Budapest, Hungary
| | - Regina J Deák-Meszlényi
- Brain Imaging Centre, Research Centre for Natural Sciences, Hungarian Academy of Sciences, Magyar tudósok körútja 2., 1117 Budapest, Hungary.,Department of Cognitive Science, Budapest University of Technology and Economics, Egry József utca 1., 1111 Budapest, Hungary
| | - Petra Hermann
- Brain Imaging Centre, Research Centre for Natural Sciences, Hungarian Academy of Sciences, Magyar tudósok körútja 2., 1117 Budapest, Hungary
| | - Zoltán Vidnyánszky
- Brain Imaging Centre, Research Centre for Natural Sciences, Hungarian Academy of Sciences, Magyar tudósok körútja 2., 1117 Budapest, Hungary.,Department of Cognitive Science, Budapest University of Technology and Economics, Egry József utca 1., 1111 Budapest, Hungary
| |
Collapse
|
243
|
Sakai K, Yamada K. Machine learning studies on major brain diseases: 5-year trends of 2014–2018. Jpn J Radiol 2018; 37:34-72. [DOI: 10.1007/s11604-018-0794-4] [Citation(s) in RCA: 73] [Impact Index Per Article: 12.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/21/2018] [Accepted: 11/14/2018] [Indexed: 12/17/2022]
|
244
|
Abstract
Artificial neural networks (ANN) have attracted significant attention from researchers because many complex problems can be solved by training them. If enough data are provided during the training process, ANNs are capable of achieving good performance results. However, if training data are not enough, the predefined neural network model suffers from overfitting and underfitting problems. To solve these problems, several regularization techniques have been devised and widely applied to applications and data analysis. However, it is difficult for developers to choose the most suitable scheme for a developing application because there is no information regarding the performance of each scheme. This paper describes comparative research on regularization techniques by evaluating the training and validation errors in a deep neural network model, using a weather dataset. For comparisons, each algorithm was implemented using a recent neural network library of TensorFlow. The experiment results showed that an autoencoder had the worst performance among schemes. When the prediction accuracy was compared, data augmentation and the batch normalization scheme showed better performance than the others.
Collapse
|
245
|
Pinaya WHL, Mechelli A, Sato JR. Using deep autoencoders to identify abnormal brain structural patterns in neuropsychiatric disorders: A large-scale multi-sample study. Hum Brain Mapp 2018; 40:944-954. [PMID: 30311316 PMCID: PMC6492107 DOI: 10.1002/hbm.24423] [Citation(s) in RCA: 53] [Impact Index Per Article: 8.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/14/2018] [Revised: 09/25/2018] [Accepted: 10/02/2018] [Indexed: 11/11/2022] Open
Abstract
Machine learning is becoming an increasingly popular approach for investigating spatially distributed and subtle neuroanatomical alterations in brain-based disorders. However, some machine learning models have been criticized for requiring a large number of cases in each experimental group, and for resembling a "black box" that provides little or no insight into the nature of the data. In this article, we propose an alternative conceptual and practical approach for investigating brain-based disorders which aim to overcome these limitations. We used an artificial neural network known as "deep autoencoder" to create a normative model using structural magnetic resonance imaging data from 1,113 healthy people. We then used this model to estimate total and regional neuroanatomical deviation in individual patients with schizophrenia and autism spectrum disorder using two independent data sets (n = 263). We report that the model was able to generate different values of total neuroanatomical deviation for each disease under investigation relative to their control group (p < .005). Furthermore, the model revealed distinct patterns of neuroanatomical deviations for the two diseases, consistent with the existing neuroimaging literature. We conclude that the deep autoencoder provides a flexible and promising framework for assessing total and regional neuroanatomical deviations in neuropsychiatric populations.
Collapse
Affiliation(s)
- Walter H L Pinaya
- Center of Mathematics, Computing, and Cognition, Universidade Federal do ABC, São Bernardo do Campo, SP, Brazil.,Center for Engineering, Modeling and Applied Social Sciences, Universidade Federal do ABC, São Bernardo do Campo, SP, Brazil.,Department of Psychosis Studies, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK
| | - Andrea Mechelli
- Department of Psychosis Studies, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK
| | - João R Sato
- Center of Mathematics, Computing, and Cognition, Universidade Federal do ABC, São Bernardo do Campo, SP, Brazil
| |
Collapse
|
246
|
Madsen KH, Krohne LG, Cai XL, Wang Y, Chan RCK. Perspectives on Machine Learning for Classification of Schizotypy Using fMRI Data. Schizophr Bull 2018; 44:S480-S490. [PMID: 29554367 PMCID: PMC6188516 DOI: 10.1093/schbul/sby026] [Citation(s) in RCA: 17] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/23/2022]
Abstract
Functional magnetic resonance imaging is capable of estimating functional activation and connectivity in the human brain, and lately there has been increased interest in the use of these functional modalities combined with machine learning for identification of psychiatric traits. While these methods bear great potential for early diagnosis and better understanding of disease processes, there are wide ranges of processing choices and pitfalls that may severely hamper interpretation and generalization performance unless carefully considered. In this perspective article, we aim to motivate the use of machine learning schizotypy research. To this end, we describe common data processing steps while commenting on best practices and procedures. First, we introduce the important role of schizotypy to motivate the importance of reliable classification, and summarize existing machine learning literature on schizotypy. Then, we describe procedures for extraction of features based on fMRI data, including statistical parametric mapping, parcellation, complex network analysis, and decomposition methods, as well as classification with a special focus on support vector classification and deep learning. We provide more detailed descriptions and software as supplementary material. Finally, we present current challenges in machine learning for classification of schizotypy and comment on future trends and perspectives.
Collapse
Affiliation(s)
- Kristoffer H Madsen
- Danish Research Centre for Magnetic Resonance, Centre for Functional and Diagnostic Imaging and Research, Copenhagen University Hospital Hvidovre, Hvidovre, Denmark,Department of Applied Mathematics and Computer Science, Technical University of Denmark, Kongens Lyngby, Denmark,To whom correspondence should be addressed; tel: +45 38622975; fax:+45 36351680; e-mail:
| | - Laerke G Krohne
- Danish Research Centre for Magnetic Resonance, Centre for Functional and Diagnostic Imaging and Research, Copenhagen University Hospital Hvidovre, Hvidovre, Denmark,Department of Applied Mathematics and Computer Science, Technical University of Denmark, Kongens Lyngby, Denmark
| | - Xin-lu Cai
- Neuropsychology and Applied Cognitive Neuroscience Laboratory, CAS Key Laboratory of Mental Health, Institute of Psychology, Chinese Academy of Sciences, Beijing, China
| | - Yi Wang
- Neuropsychology and Applied Cognitive Neuroscience Laboratory, CAS Key Laboratory of Mental Health, Institute of Psychology, Chinese Academy of Sciences, Beijing, China,Department of Psychology, University of Chinese Academy of Sciences, Beijing, China,Sino-Danish College, University of Chinese Academy of Sciences, Beijing, China
| | - Raymond C K Chan
- Neuropsychology and Applied Cognitive Neuroscience Laboratory, CAS Key Laboratory of Mental Health, Institute of Psychology, Chinese Academy of Sciences, Beijing, China,Department of Psychology, University of Chinese Academy of Sciences, Beijing, China,Sino-Danish College, University of Chinese Academy of Sciences, Beijing, China
| |
Collapse
|
247
|
Ceschin R, Zahner A, Reynolds W, Gaesser J, Zuccoli G, Lo CW, Gopalakrishnan V, Panigrahy A. A computational framework for the detection of subcortical brain dysmaturation in neonatal MRI using 3D Convolutional Neural Networks. Neuroimage 2018; 178:183-197. [PMID: 29793060 PMCID: PMC6503677 DOI: 10.1016/j.neuroimage.2018.05.049] [Citation(s) in RCA: 24] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2018] [Revised: 05/04/2018] [Accepted: 05/19/2018] [Indexed: 12/16/2022] Open
Abstract
Deep neural networks are increasingly being used in both supervised learning for classification tasks and unsupervised learning to derive complex patterns from the input data. However, the successful implementation of deep neural networks using neuroimaging datasets requires adequate sample size for training and well-defined signal intensity based structural differentiation. There is a lack of effective automated diagnostic tools for the reliable detection of brain dysmaturation in the neonatal period, related to small sample size and complex undifferentiated brain structures, despite both translational research and clinical importance. Volumetric information alone is insufficient for diagnosis. In this study, we developed a computational framework for the automated classification of brain dysmaturation from neonatal MRI, by combining a specific deep neural network implementation with neonatal structural brain segmentation as a method for both clinical pattern recognition and data-driven inference into the underlying structural morphology. We implemented three-dimensional convolution neural networks (3D-CNNs) to specifically classify dysplastic cerebelli, a subset of surface-based subcortical brain dysmaturation, in term infants born with congenital heart disease. We obtained a 0.985 ± 0. 0241-classification accuracy of subtle cerebellar dysplasia in CHD using 10-fold cross-validation. Furthermore, the hidden layer activations and class activation maps depicted regional vulnerability of the superior surface of the cerebellum, (composed of mostly the posterior lobe and the midline vermis), in regards to differentiating the dysplastic process from normal tissue. The posterior lobe and the midline vermis provide regional differentiation that is relevant to not only to the clinical diagnosis of cerebellar dysplasia, but also genetic mechanisms and neurodevelopmental outcome correlates. These findings not only contribute to the detection and classification of a subset of neonatal brain dysmaturation, but also provide insight to the pathogenesis of cerebellar dysplasia in CHD. In addition, this is one of the first examples of the application of deep learning to a neuroimaging dataset, in which the hidden layer activation revealed diagnostically and biologically relevant features about the clinical pathogenesis. The code developed for this project is open source, published under the BSD License, and designed to be generalizable to applications both within and beyond neonatal brain imaging.
Collapse
Affiliation(s)
- Rafael Ceschin
- Department of Biomedical Informatics, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA; Department of Radiology, Children's Hospital of Pittsburgh of UPMC, Pittsburgh, PA, USA.
| | - Alexandria Zahner
- Department of Radiology, Children's Hospital of Pittsburgh of UPMC, Pittsburgh, PA, USA
| | - William Reynolds
- Department of Radiology, Children's Hospital of Pittsburgh of UPMC, Pittsburgh, PA, USA
| | - Jenna Gaesser
- Division of Neurology, Department of Pediatrics, Children's Hospital of Pittsburgh of UPMC, Pittsburgh, PA, USA
| | - Giulio Zuccoli
- Department of Radiology, Children's Hospital of Pittsburgh of UPMC, Pittsburgh, PA, USA
| | - Cecilia W Lo
- Department of Developmental Biology, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA
| | - Vanathi Gopalakrishnan
- Department of Biomedical Informatics, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA
| | - Ashok Panigrahy
- Department of Biomedical Informatics, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA; Department of Radiology, Children's Hospital of Pittsburgh of UPMC, Pittsburgh, PA, USA
| |
Collapse
|
248
|
Kocak B, Yardimci AH, Bektas CT, Turkcanoglu MH, Erdim C, Yucetas U, Koca SB, Kilickesmez O. Textural differences between renal cell carcinoma subtypes: Machine learning-based quantitative computed tomography texture analysis with independent external validation. Eur J Radiol 2018; 107:149-157. [PMID: 30292260 DOI: 10.1016/j.ejrad.2018.08.014] [Citation(s) in RCA: 75] [Impact Index Per Article: 12.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/20/2018] [Revised: 08/04/2018] [Accepted: 08/13/2018] [Indexed: 12/01/2022]
Abstract
OBJECTIVE To develop externally validated, reproducible, and generalizable models for distinguishing three major subtypes of renal cell carcinomas (RCCs) using machine learning-based quantitative computed tomography (CT) texture analysis (qCT-TA). MATERIALS AND METHODS Sixty-eight RCCs were included in this retrospective study for model development and internal validation. Another 26 RCCs were included from public databases (The Cancer Genome Atlas-TCGA) for independent external validation. Following image preparation steps (reconstruction, resampling, normalization, and discretization), 275 texture features were extracted from unenhanced and corticomedullary phase CT images. Feature selection was firstly done with reproducibility analysis by three radiologists, and; then, with a wrapper-based classifier-specific algorithm. A nested cross-validation was performed for feature selection and model optimization. Base classifiers were the artificial neural network (ANN) and support vector machine (SVM). Base classifiers were also combined with three additional algorithms to improve generalizability performance. Classifications were done with the following groups: (i), non-clear cell RCC (non-cc-RCC) versus clear cell RCC (cc-RCC) and (ii), cc-RCC versus papillary cell RCC (pc-RCC) versus chromophobe cell RCC (chc-RCC). Main performance metric for comparisons was the Matthews correlation coefficient (MCC). RESULTS Number of the reproducible features is smaller for the unenhanced images (93 out of 275) compared to the corticomedullary phase images (232 out of 275). Overall performance metrics of the machine learning-based qCT-TA derived from corticomedullary phase images were better than those of unenhanced images. Using corticomedullary phase images, ANN with adaptive boosting algorithm performed best for discrimination of non-cc-RCCs from cc-RCCs (MCC = 0.728) with an external validation accuracy, sensitivity, and specificity of 84.6%, 69.2%, and 100%, respectively. On the other hand, the performance of the machine learning-based qCT-TA is rather poor for distinguishing three major subtypes. The SVM with bagging algorithm performed best for discrimination of pc-RCC from other RCC subtypes (MCC = 0.804) with an external validation accuracy, sensitivity, and specificity of 69.2%, 71.4%, and 100%, respectively. CONCLUSIONS Machine learning-based qCT-TA can distinguish non-cc-RCCs from cc-RCCs with a satisfying performance. On the other hand, the performance of the method for distinguishing three major subtypes is rather poor. Corticomedullary phase CT images provide much more valuable texture parameters than unenhanced images.
Collapse
Affiliation(s)
- Burak Kocak
- Istanbul Training and Research Hospital, Department of Radiology, Istanbul, Turkey.
| | - Aytul Hande Yardimci
- Istanbul Training and Research Hospital, Department of Radiology, Istanbul, Turkey
| | - Ceyda Turan Bektas
- Istanbul Training and Research Hospital, Department of Radiology, Istanbul, Turkey
| | - Mehmet Hamza Turkcanoglu
- Batman Women and Children's Health Training and Research Hospital, Department of Radiology, Istanbul, Turkey
| | - Cagri Erdim
- Istanbul Training and Research Hospital, Department of Radiology, Istanbul, Turkey
| | - Ugur Yucetas
- Istanbul Training and Research Hospital, Department of Urology, Istanbul, Turkey
| | - Sevim Baykal Koca
- Istanbul Training and Research Hospital, Department of Pathology, Istanbul, Turkey
| | - Ozgur Kilickesmez
- Istanbul Training and Research Hospital, Department of Radiology, Istanbul, Turkey
| |
Collapse
|
249
|
Du Y, Fu Z, Calhoun VD. Classification and Prediction of Brain Disorders Using Functional Connectivity: Promising but Challenging. Front Neurosci 2018; 12:525. [PMID: 30127711 PMCID: PMC6088208 DOI: 10.3389/fnins.2018.00525] [Citation(s) in RCA: 172] [Impact Index Per Article: 28.7] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2018] [Accepted: 07/12/2018] [Indexed: 12/13/2022] Open
Abstract
Brain functional imaging data, especially functional magnetic resonance imaging (fMRI) data, have been employed to reflect functional integration of the brain. Alteration in brain functional connectivity (FC) is expected to provide potential biomarkers for classifying or predicting brain disorders. In this paper, we present a comprehensive review in order to provide guidance about the available brain FC measures and typical classification strategies. We survey the state-of-the-art FC analysis methods including widely used static functional connectivity (SFC) and more recently proposed dynamic functional connectivity (DFC). Temporal correlations among regions of interest (ROIs), data-driven spatial network and functional network connectivity (FNC) are often computed to reflect SFC from different angles. SFC can be extended to DFC using a sliding-window framework, and intrinsic connectivity states along the time-varying connectivity patterns are typically extracted using clustering or decomposition approaches. We also briefly summarize window-less DFC approaches. Subsequently, we highlight various strategies for feature selection including the filter, wrapper and embedded methods. In terms of model building, we include traditional classifiers as well as more recently applied deep learning methods. Moreover, we review representative applications with remarkable classification accuracy for psychosis and mood disorders, neurodevelopmental disorder, and neurological disorders using fMRI data. Schizophrenia, bipolar disorder, autism spectrum disorder (ASD), attention deficit hyperactivity disorder (ADHD), Alzheimer's disease and mild cognitive impairment (MCI) are discussed. Finally, challenges in the field are pointed out with respect to the inaccurate diagnosis labeling, the abundant number of possible features and the difficulty in validation. Some suggestions for future work are also provided.
Collapse
Affiliation(s)
- Yuhui Du
- The Mind Research Network, Albuquerque, NM, United States
- School of Computer & Information Technology, Shanxi University, Taiyuan, China
| | - Zening Fu
- The Mind Research Network, Albuquerque, NM, United States
| | - Vince D. Calhoun
- The Mind Research Network, Albuquerque, NM, United States
- Department of Electrical and Computer Engineering, University of New Mexico, Albuquerque, NM, United States
| |
Collapse
|
250
|
Reading the (functional) writing on the (structural) wall: Multimodal fusion of brain structure and function via a deep neural network based translation approach reveals novel impairments in schizophrenia. Neuroimage 2018; 181:734-747. [PMID: 30055372 DOI: 10.1016/j.neuroimage.2018.07.047] [Citation(s) in RCA: 36] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/25/2017] [Revised: 07/16/2018] [Accepted: 07/18/2018] [Indexed: 01/01/2023] Open
Abstract
This work presents a novel approach to finding linkage/association between multimodal brain imaging data, such as structural MRI (sMRI) and functional MRI (fMRI). Motivated by the machine translation domain, we employ a deep learning model, and consider two different imaging views of the same brain like two different languages conveying some common facts. That analogy enables finding linkages between two modalities. The proposed translation-based fusion model contains a computing layer that learns "alignments" (or links) between dynamic connectivity features from fMRI data and static gray matter patterns from sMRI data. The approach is evaluated on a multi-site dataset consisting of eyes-closed resting state imaging data collected from 298 subjects (age- and gender matched 154 healthy controls and 144 patients with schizophrenia). Results are further confirmed on an independent dataset consisting of eyes-open resting state imaging data from 189 subjects (age- and gender matched 91 healthy controls and 98 patients with schizophrenia). We used dynamic functional connectivity (dFNC) states as the functional features and ICA-based sources from gray matter densities as the structural features. The dFNC states characterized by weakly correlated intrinsic connectivity networks (ICNs) were found to have stronger association with putamen and insular gray matter pattern, while the dFNC states of profuse strongly correlated ICNs exhibited stronger links with the gray matter pattern in precuneus, posterior cingulate cortex (PCC), and temporal cortex. Further investigation with the estimated link strength (or alignment score) showed significant group differences between healthy controls and patients with schizophrenia in several key regions including temporal lobe, and linked these to connectivity states showing less occupancy in healthy controls. Moreover, this novel approach revealed significant correlation between a cognitive score (attention/vigilance) and the function/structure alignment score that was not detected when data modalities were considered separately.
Collapse
|