Using deep learning to investigate the neuroimaging correlates of psychiatric and neurological disorders: Methods and applications

Biomedical informatics applications for precision management of neurodegenerative diseases

Modern medicine is in the midst of a revolution driven by "big data," rapidly advancing computing power, and broader integration of technology into healthcare. Highly detailed and individualized profiles of both health and disease states are now possible, including biomarkers, genomic profiles, cognitive and behavioral phenotypes, high-frequency assessments, and medical imaging. Although these data are incredibly complex, they can potentially be used to understand multi-determinant causal relationships, elucidate modifiable factors, and ultimately customize treatments based on individual parameters. Especially for neurodegenerative diseases, where an effective therapeutic agent has yet to be discovered, there remains a critical need for an interdisciplinary perspective on data and information management due to the number of unanswered questions. Biomedical informatics is a multidisciplinary field that falls at the intersection of information technology, computer and data science, engineering, and healthcare that will be instrumental for uncovering novel insights into neurodegenerative disease research, including both causal relationships and therapeutic targets and maximizing the utility of both clinical and research data. The present study aims to provide a brief overview of biomedical informatics and how clinical data applications such as clinical decision support tools can be developed to derive new knowledge from the wealth of available data to advance clinical care and scientific research of neurodegenerative diseases in the era of precision medicine.

How random is the random forest? Random forest algorithm on the service of structural imaging biomarkers for Alzheimer's disease: from Alzheimer's disease neuroimaging initiative (ADNI) database

Neuroinformatics is a fascinating research field that applies computational models and analytical tools to high dimensional experimental neuroscience data for a better understanding of how the brain functions or dysfunctions in brain diseases. Neuroinformaticians work in the intersection of neuroscience and informatics supporting the integration of various sub-disciplines (behavioural neuroscience, genetics, cognitive psychology, etc.) working on brain research. Neuroinformaticians are the pathway of information exchange between informaticians and clinicians for a better understanding of the outcome of computational models and the clinical interpretation of the analysis. Machine learning is one of the most significant computational developments in the last decade giving tools to neuroinformaticians and finally to radiologists and clinicians for an automatic and early diagnosis-prognosis of a brain disease. Random forest (RF) algorithm has been successfully applied to high-dimensional neuroimaging data for feature reduction and also has been applied to classify the clinical label of a subject using single or multi-modal neuroimaging datasets. Our aim was to review the studies where RF was applied to correctly predict the Alzheimer's disease (AD), the conversion from mild cognitive impairment (MCI) and its robustness to overfitting, outliers and handling of non-linear data. Finally, we described our RF-based model that gave us the 1st position in an international challenge for automated prediction of MCI from MRI data.

Multi-Site Diagnostic Classification of Schizophrenia Using Discriminant Deep Learning with Functional Connectivity MRI

BACKGROUND

A lack of a sufficiently large sample at single sites causes poor generalizability in automatic diagnosis classification of heterogeneous psychiatric disorders such as schizophrenia based on brain imaging scans. Advanced deep learning methods may be capable of learning subtle hidden patterns from high dimensional imaging data, overcome potential site-related variation, and achieve reproducible cross-site classification. However, deep learning-based cross-site transfer classification, despite less imaging site-specificity and more generalizability of diagnostic models, has not been investigated in schizophrenia.

METHODS

A large multi-site functional MRI sample (n = 734, including 357 schizophrenic patients from seven imaging resources) was collected, and a deep discriminant autoencoder network, aimed at learning imaging site-shared functional connectivity features, was developed to discriminate schizophrenic individuals from healthy controls.

FINDINGS

Accuracies of approximately 85·0% and 81·0% were obtained in multi-site pooling classification and leave-site-out transfer classification, respectively. The learned functional connectivity features revealed dysregulation of the cortical-striatal-cerebellar circuit in schizophrenia, and the most discriminating functional connections were primarily located within and across the default, salience, and control networks.

INTERPRETATION

The findings imply that dysfunctional integration of the cortical-striatal-cerebellar circuit across the default, salience, and control networks may play an important role in the "disconnectivity" model underlying the pathophysiology of schizophrenia. The proposed discriminant deep learning method may be capable of learning reliable connectome patterns and help in understanding the pathophysiology and achieving accurate prediction of schizophrenia across multiple independent imaging sites.

Modified Convolutional Neural Network Based on Dropout and the Stochastic Gradient Descent Optimizer

This study proposes a modified convolutional neural network (CNN) algorithm that is based on dropout and the stochastic gradient descent (SGD) optimizer (MCNN-DS), after analyzing the problems of CNNs in extracting the convolution features, to improve the feature recognition rate and reduce the time-cost of CNNs. The MCNN-DS has a quadratic CNN structure and adopts the rectified linear unit as the activation function to avoid the gradient problem and accelerate convergence. To address the overfitting problem, the algorithm uses an SGD optimizer, which is implemented by inserting a dropout layer into the all-connected and output layers, to minimize cross entropy. This study used the datasets MNIST, HCL2000, and EnglishHand as the benchmark data, analyzed the performance of the SGD optimizer under different learning parameters, and found that the proposed algorithm exhibited good recognition performance when the learning rate was set to [0.05, 0.07]. The performances of WCNN, MLP-CNN, SVM-ELM, and MCNN-DS were compared. Statistical results showed the following: (1) For the benchmark MNIST, the MCNN-DS exhibited a high recognition rate of 99.97%, and the time-cost of the proposed algorithm was merely 21.95% of MLP-CNN, and 10.02% of SVM-ELM; (2) Compared with SVM-ELM, the average improvement in the recognition rate of MCNN-DS was 2.35% for the benchmark HCL2000, and the time-cost of MCNN-DS was only 15.41%; (3) For the EnglishHand test set, the lowest recognition rate of the algorithm was 84.93%, the highest recognition rate was 95.29%, and the average recognition rate was 89.77%.

Connectome analysis with diffusion MRI in idiopathic Parkinson's disease: Evaluation using multi-shell, multi-tissue, constrained spherical deconvolution

Parkinson's disease (PD) is a progressive neurodegenerative disorder that affects extensive regions of the central nervous system. In this work, we evaluated the structural connectome of patients with PD, as mapped by diffusion-weighted MRI tractography and a multi-shell, multi-tissue (MSMT) constrained spherical deconvolution (CSD) method to increase the precision of tractography at tissue interfaces. The connectome was mapped with probabilistic MSMT-CSD in 21 patients with PD and in 21 age- and gender-matched controls. Mapping was also performed by deterministic single-shell, single tissue (SSST)-CSD tracking and probabilistic SSST-CSD tracking for comparison. A support vector machine was trained to predict diagnosis based on a linear combination of graph metrics. We showed that probabilistic MSMT-CSD could detect significantly reduced global strength, efficiency, clustering, and small-worldness, and increased global path length in patients with PD relative to healthy controls; by contrast, probabilistic SSST-CSD only detected the difference in global strength and small-worldness. In patients with PD, probabilistic MSMT-CSD also detected a significant reduction in local efficiency and detected clustering in the motor, frontal temporoparietal associative, limbic, basal ganglia, and thalamic areas. The network-based statistic identified a subnetwork of reduced connectivity by MSMT-CSD and probabilistic SSST-CSD in patients with PD, involving key components of the cortico–basal ganglia–thalamocortical network. Finally, probabilistic MSMT-CSD had superior diagnostic accuracy compared with conventional probabilistic SSST-CSD and deterministic SSST-CSD tracking. In conclusion, probabilistic MSMT-CSD detected a greater extent of connectome pathology in patients with PD, including those with cortico–basal ganglia–thalamocortical network disruptions. Connectome analysis based on probabilistic MSMT-CSD may be useful when evaluating the extent of white matter connectivity disruptions in PD.

•

Connectomes mapped in Parkinson's disease (PD) using multi-shell tractography.

•

Multi-shell tractography provided improved sensitivity to connectome pathology.

•

Machine learning accurately predicted PD diagnosis based on connectome.

•

Connectome pathology in PD was localized to basal ganglia-thalamocortical circuits.

Deep Learning with Convolutional Neural Network for Differentiation of Liver Masses at Dynamic Contrast-enhanced CT: A Preliminary Study

Purpose To investigate diagnostic performance by using a deep learning method with a convolutional neural network (CNN) for the differentiation of liver masses at dynamic contrast agent-enhanced computed tomography (CT). Materials and Methods This clinical retrospective study used CT image sets of liver masses over three phases (noncontrast-agent enhanced, arterial, and delayed). Masses were diagnosed according to five categories (category A, classic hepatocellular carcinomas [HCCs]; category B, malignant liver tumors other than classic and early HCCs; category C, indeterminate masses or mass-like lesions [including early HCCs and dysplastic nodules] and rare benign liver masses other than hemangiomas and cysts; category D, hemangiomas; and category E, cysts). Supervised training was performed by using 55 536 image sets obtained in 2013 (from 460 patients, 1068 sets were obtained and they were augmented by a factor of 52 [rotated, parallel-shifted, strongly enlarged, and noise-added images were generated from the original images]). The CNN was composed of six convolutional, three maximum pooling, and three fully connected layers. The CNN was tested with 100 liver mass image sets obtained in 2016 (74 men and 26 women; mean age, 66.4 years ± 10.6 [standard deviation]; mean mass size, 26.9 mm ± 25.9; 21, nine, 35, 20, and 15 liver masses for categories A, B, C, D, and E, respectively). Training and testing were performed five times. Accuracy for categorizing liver masses with CNN model and the area under receiver operating characteristic curve for differentiating categories A-B versus categories C-E were calculated. Results Median accuracy of differential diagnosis of liver masses for test data were 0.84. Median area under the receiver operating characteristic curve for differentiating categories A-B from C-E was 0.92. Conclusion Deep learning with CNN showed high diagnostic performance in differentiation of liver masses at dynamic CT. ^© RSNA, 2017 Online supplemental material is available for this article.

Resting State fMRI Functional Connectivity-Based Classification Using a Convolutional Neural Network Architecture

Machine learning techniques have become increasingly popular in the field of resting state fMRI (functional magnetic resonance imaging) network based classification. However, the application of convolutional networks has been proposed only very recently and has remained largely unexplored. In this paper we describe a convolutional neural network architecture for functional connectome classification called connectome-convolutional neural network (CCNN). Our results on simulated datasets and a publicly available dataset for amnestic mild cognitive impairment classification demonstrate that our CCNN model can efficiently distinguish between subject groups. We also show that the connectome-convolutional network is capable to combine information from diverse functional connectivity metrics and that models using a combination of different connectivity descriptors are able to outperform classifiers using only one metric. From this flexibility follows that our proposed CCNN model can be easily adapted to a wide range of connectome based classification or regression tasks, by varying which connectivity descriptor combinations are used to train the network.

Random Forest Algorithm for the Classification of Neuroimaging Data in Alzheimer's Disease: A Systematic Review

Objective: Machine learning classification has been the most important computational development in the last years to satisfy the primary need of clinicians for automatic early diagnosis and prognosis. Nowadays, Random Forest (RF) algorithm has been successfully applied for reducing high dimensional and multi-source data in many scientific realms. Our aim was to explore the state of the art of the application of RF on single and multi-modal neuroimaging data for the prediction of Alzheimer's disease.

Methods: A systematic review following PRISMA guidelines was conducted on this field of study. In particular, we constructed an advanced query using boolean operators as follows: (“random forest” OR “random forests”) AND neuroimaging AND (“alzheimer's disease” OR alzheimer's OR alzheimer) AND (prediction OR classification). The query was then searched in four well-known scientific databases: Pubmed, Scopus, Google Scholar and Web of Science.

Results: Twelve articles—published between the 2007 and 2017—have been included in this systematic review after a quantitative and qualitative selection. The lesson learnt from these works suggest that when RF was applied on multi-modal data for prediction of Alzheimer's disease (AD) conversion from the Mild Cognitive Impairment (MCI), it produces one of the best accuracies to date. Moreover, the RF has important advantages in terms of robustness to overfitting, ability to handle highly non-linear data, stability in the presence of outliers and opportunity for efficient parallel processing mainly when applied on multi-modality neuroimaging data, such as, MRI morphometric, diffusion tensor imaging, and PET images.

Conclusions: We discussed the strengths of RF, considering also possible limitations and by encouraging further studies on the comparisons of this algorithm with other commonly used classification approaches, particularly in the early prediction of the progression from MCI to AD.