Brain Magnetic Resonance Imaging Datasets Research Articles

Diagnosis and classification of Alzheimer's disease by using a convolution neural network algorithm

Alzheimer's disease (AD) is a high-risk and atrophic neurological illness that slowly and gradually destroys brain cells (i.e. neurons). As the most common type of amentia, AD affects 60–65% of all people with amentia and poses major health dangers to middle-aged and elderly people. For classification of AD in the early stage, classification systems and computer-aided diagnostic techniques have been developed. Previously, machine learning approaches were applied to develop diagnostic systems by extracting features from neural images. Currently, deep learning approaches have been used in many real-time medical imaging applications. In this study, two deep neural network techniques, AlexNet and Restnet50, were applied for the classification and recognition of AD. The data used in this study to evaluate and test the proposed model included those from brain magnetic resonance imaging (MRI) images collected from the Kaggle website. A convolutional neural network (CNN) algorithm was applied to classify AD efficiently. CNNs were pre-trained using AlexNet and Restnet50 transfer learning models. The results of this experimentation showed that the proposed method is superior to the existing systems in terms of detection accuracy. The AlexNet model achieved outstanding performance based on five evaluation metrics (accuracy, F1 score, precision, sensitivity, and specificity) for the brain MRI datasets. AlexNet displayed an accuracy of 94.53%, specificity of 98.21%, F1 score of 94.12%, and sensitivity of 100%, outperforming Restnet50. The proposed method can help improve CAD methods for AD in medical investigations.

Deep Learning in Large and Multi-Site Structural Brain MR Imaging Datasets.

Large, multi-site, heterogeneous brain imaging datasets are increasingly required for the training, validation, and testing of advanced deep learning (DL)-based automated tools, including structural magnetic resonance (MR) image-based diagnostic and treatment monitoring approaches. When assembling a number of smaller datasets to form a larger dataset, understanding the underlying variability between different acquisition and processing protocols across the aggregated dataset (termed “batch effects”) is critical. The presence of variation in the training dataset is important as it more closely reflects the true underlying data distribution and, thus, may enhance the overall generalizability of the tool. However, the impact of batch effects must be carefully evaluated in order to avoid undesirable effects that, for example, may reduce performance measures. Batch effects can result from many sources, including differences in acquisition equipment, imaging technique and parameters, as well as applied processing methodologies. Their impact, both beneficial and adversarial, must be considered when developing tools to ensure that their outputs are related to the proposed clinical or research question (i.e., actual disease-related or pathological changes) and are not simply due to the peculiarities of underlying batch effects in the aggregated dataset. We reviewed applications of DL in structural brain MR imaging that aggregated images from neuroimaging datasets, typically acquired at multiple sites. We examined datasets containing both healthy control participants and patients that were acquired using varying acquisition protocols. First, we discussed issues around Data Access and enumerated the key characteristics of some commonly used publicly available brain datasets. Then we reviewed methods for correcting batch effects by exploring the two main classes of approaches: Data Harmonization that uses data standardization, quality control protocols or other similar algorithms and procedures to explicitly understand and minimize unwanted batch effects; and Domain Adaptation that develops DL tools that implicitly handle the batch effects by using approaches to achieve reliable and robust results. In this narrative review, we highlighted the advantages and disadvantages of both classes of DL approaches, and described key challenges to be addressed in future studies.

Sparse Representation-Based Discriminative Metric Learning for Brain MRI Image Retrieval.

Magnetic resonance imaging (MRI) can have a good diagnostic function for important organs and parts of the body. MRI technology has become a common and important disease detection technology. At the same time, medical imaging data is increasing at an explosive rate. Retrieving similar medical images from a huge database is of great significance to doctors’ auxiliary diagnosis and treatment. In this paper, combining the advantages of sparse representation and metric learning, a sparse representation-based discriminative metric learning (SRDML) approach is proposed for medical image retrieval of brain MRI. The SRDML approach uses a sparse representation framework to learn robust feature representation of brain MRI, and uses metric learning to project new features into the metric space with matching discrimination. In such a metric space, the optimal similarity measure is obtained by using the local constraints of atoms and the pairwise constraints of coding coefficients, so that the distance between similar images is less than the given threshold, and the distance between dissimilar images is greater than another given threshold. The experiments are designed and tested on the brain MRI dataset created by Chang. Experimental results show that the SRDML approach can obtain satisfactory retrieval performance and achieve accurate brain MRI image retrieval.

Brain Tumor/Mass Classification Framework Using Magnetic-Resonance-Imaging-Based Isolated and Developed Transfer Deep-Learning Model.

With the advancement in technology, machine learning can be applied to diagnose the mass/tumor in the brain using magnetic resonance imaging (MRI). This work proposes a novel developed transfer deep-learning model for the early diagnosis of brain tumors into their subclasses, such as pituitary, meningioma, and glioma. First, various layers of isolated convolutional-neural-network (CNN) models are built from scratch to check their performances for brain MRI images. Then, the 22-layer, binary-classification (tumor or no tumor) isolated-CNN model is re-utilized to re-adjust the neurons’ weights for classifying brain MRI images into tumor subclasses using the transfer-learning concept. As a result, the developed transfer-learned model has a high accuracy of 95.75% for the MRI images of the same MRI machine. Furthermore, the developed transfer-learned model has also been tested using the brain MRI images of another machine to validate its adaptability, general capability, and reliability for real-time application in the future. The results showed that the proposed model has a high accuracy of 96.89% for an unseen brain MRI dataset. Thus, the proposed deep-learning framework can help doctors and radiologists diagnose brain tumors early.

Improving Effectiveness of Different Deep Transfer Learning-Based Models for Detecting Brain Tumors From MR Images

Early classification of brain tumors from magnetic resonance imaging (MRI) plays an important role in the diagnosis of such diseases. There are many diagnostic imaging methods used to identify tumors in the brain. MRI is commonly used for such tasks because of its unmatched image quality. The relevance of artificial intelligence (AI) in the form of deep learning (DL) has revolutionized new methods of automated medical image diagnosis. This study aimed to develop a robust and efficient method based on transfer learning technique for classifying brain tumors using MRI. In this article, the popular deep learning architectures are utilized to develop brain tumor diagnostic system. The pre-trained models such as Xception, NasNet Large, DenseNet121 and InceptionResNetV2 are used to extract the deep features from brain MRI. The experiment was performed using two benchmark datasets that are openly accessible from the web. Images from the dataset were first cropped, preprocessed, and augmented for accurate and fast training. Deep transfer learning models are trained and tested on a brain MRI dataset using three different optimization algorithms (ADAM, SGD, and RMSprop). The performance of the transfer learning models is evaluated using performance metrics such as accuracy, sensitivity, precision, specificity and F1-score. From the experimental results, our proposed CNN model based on the Xception architecture using ADAM optimizer is better than the other three proposed models. The Xception model achieved accuracy, sensitivity, precision specificity, and F1-score values of 99.67%, 99.68%, 99.68%, 99.66%, and 99.68% on the MRI-large dataset, and 91.94%, 96.55%, 87.50%, 87.88%, and 91.80% on the MRI-small dataset, respectively. The proposed method is superior to the existing literature, indicating that it can be used to quickly and accurately classify brain tumors.

Alzheimer's Disease Classification Accuracy is Improved by MRI Harmonization based on Attention-Guided Generative Adversarial Networks.

Alzheimer's disease (AD) accounts for 60% of dementia cases worldwide; patients with the disease typically suffer from irreversible memory loss and progressive decline in multiple cognitive domains. With brain imaging techniques such as magnetic resonance imaging (MRI), microscopic brain changes are detectable even before abnormal memory loss is detected clinically. Patterns of brain atrophy can be measured using MRI, which gives us an opportunity to facilitate AD detection using image classification techniques. Even so, MRI scanning protocols and scanners differ across studies. The resulting differences in image contrast and signal to noise make it important to train and test classification models on multiple datasets, and to handle shifts in image characteristics across protocols (also known as domain transfer or domain adaptation). Here, we examined whether adversarial domain adaptation can boost the performance of a Convolutional Neural Network (CNN) model designed to classify AD. To test this, we used an Attention-Guided Generative Adversarial Network (GAN) to harmonize images from three publicly available brain MRI datasets - ADNI, AIBL and OASIS - adjusting for scanner-dependent effects. Our AG-GAN optimized a joint objective function that included attention loss, pixel loss, cycle-consistency loss and adversarial loss; the model was trained bidirectionally in an end-to-end fashion. For AD classification, we adapted the popular 2D AlexNet CNN to handle 3D images. Classification based on harmonized MR images significantly outperformed classification based on the three datasets in non-harmonized form, motivating further work on image harmonization using adversarial techniques.

A Contrast Augmentation Approach to Improve Multi-Scanner Generalization in MRI.

Most data-driven methods are very susceptible to data variability. This problem is particularly apparent when applying Deep Learning (DL) to brain Magnetic Resonance Imaging (MRI), where intensities and contrasts vary due to acquisition protocol, scanner- and center-specific factors. Most publicly available brain MRI datasets originate from the same center and are homogeneous in terms of scanner and used protocol. As such, devising robust methods that generalize to multi-scanner and multi-center data is crucial for transferring these techniques into clinical practice. We propose a novel data augmentation approach based on Gaussian Mixture Models (GMM-DA) with the goal of increasing the variability of a given dataset in terms of intensities and contrasts. The approach allows to augment the training dataset such that the variability in the training set compares to what is seen in real world clinical data, while preserving anatomical information. We compare the performance of a state-of-the-art U-Net model trained for segmenting brain structures with and without the addition of GMM-DA. The models are trained and evaluated on single- and multi-scanner datasets. Additionally, we verify the consistency of test-retest results on same-patient images (same and different scanners). Finally, we investigate how the presence of bias field influences the performance of a model trained with GMM-DA. We found that the addition of the GMM-DA improves the generalization capability of the DL model to other scanners not present in the training data, even when the train set is already multi-scanner. Besides, the consistency between same-patient segmentation predictions is improved, both for same-scanner and different-scanner repetitions. We conclude that GMM-DA could increase the transferability of DL models into clinical scenarios.

Quality-driven deep active learning method for 3D brain MRI segmentation

Automatic segmentation of the brain Magnetic Resonance Imaging (MRI) plays a crucial role in many brain MRI processing algorithms, which is effective for the prevention, detection, monitoring, and treatment planning of brain disease. Currently, deep learning algorithms have shown outstanding performance in brain segmentation. Most algorithms train models with fully annotated brain MRI datasets. However, full annotation of 3D brain MRI is laborious and time-consuming. Using sparsely annotated datasets to train models may be one appropriate solution to reduce annotation cost. However, the approach of 3D dense segmentation with sparse annotation has not been fully studied. In this paper, we develop a segmentation framework combined with the quality-driven active learning (QDAL) module for suggestive annotation. In the proposed Active Learning module, attention mechanism and deep supervision mode are used to improve the segmentation accuracy and feedback segmentation quality information. Meanwhile, we observe a high correlation coefficient between the proposed two surrogate metrics and the real segmentation accuracy of per slice in one scan. We validate our framework on two public brain MRI datasets for brain region extraction and brain tissue segmentation. The comparative experiments demonstrate that the QDAL method outperforms the other four popular sampling strategies. The segmentation network with the guidance of the QDAL method only needs 15–20% annotated slices in brain extraction task, and 30–40% annotated slices in tissue segmentation task to achieve competitive results compared with training with full supervision.

Wilson disease tissue classification and characterization using seven artificial intelligence models embedded with 3D optimization paradigm on a weak training brain magnetic resonance imaging datasets: a supercomputer application.

Wilson's disease (WD) is caused by copper accumulation in the brain and liver, and if not treated early, can lead to severe disability and death. WD has shown white matter hyperintensity (WMH) in the brain magnetic resonance scans (MRI) scans, but the diagnosis is challenging due to (i) subtle intensity changes and (ii) weak training MRI when using artificial intelligence (AI). Design and validate seven types of high-performing AI-based computer-aided design (CADx) systems consisting of 3D optimized classification, and characterization of WD against controls. We propose a "conventional deep convolution neural network" (cDCNN) and an "improved DCNN" (iDCNN) where rectified linear unit (ReLU) activation function was modified ensuring "differentiable at zero." Three-dimensional optimization was achieved by recording accuracy while changing the CNN layers and augmentation by several folds. WD was characterized using (i) CNN-based feature map strength and (ii) Bispectrum strengths of pixels having higher probabilities of WD. We further computed the (a) area under the curve (AUC), (b) diagnostic odds ratio (DOR), (c) reliability, and (d) stability and (e) benchmarking. Optimal results were achieved using 9 layers of CNN, with 4-fold augmentation. iDCNN yields superior performance compared to cDCNN with accuracy and AUC of 98.28 ± 1.55, 0.99 (p < 0.0001), and 97.19 ± 2.53%, 0.984 (p < 0.0001), respectively. DOR of iDCNN outperformed cDCNN fourfold. iDCNN also outperformed (a) transfer learning-based "Inception V3" paradigm by 11.92% and (b) four types of "conventional machine learning-based systems": k-NN, decision tree, support vector machine, and random forest by 55.13%, 28.36%, 15.35%, and 14.11%, respectively. The AI-based systems can potentially be useful in the early WD diagnosis. Graphical Abstract.

Multi-class brain tumor classification using residual network and global average pooling

A rapid increase in brain tumor cases mandates researchers for the automation of brain tumor detection and diagnosis. Multi-tumor brain image classification became a contemporary research task due to the diverse characteristics of tumors. Recently, deep neural networks are commonly used for medical image classification to assist neurologists. Vanishing gradient problem and overfitting are the demerits of the deep networks. In this paper, we have proposed a deep network model that uses ResNet-50 and global average pooling to resolve the vanishing gradient and overfitting problems. To evaluate the efficiency of the proposed model simulation has been carried out using a three-tumor brain magnetic resonance image dataset consisting of 3064 images. Key performance metrics have used to analyze the performance of the proposed model and its competitive models. We have achieved a mean accuracy of 97.08% and 97.48% with data augmentation and without data augmentation, respectively. Our proposed model outperforms existing models in classification accuracy.

Longitudinal Brain MR Image Modeling Using Personalized Memory for Alzheimer’s Disease

Longitudinal analysis of a disease is an important issue to understand its progression and design prognosis and early diagnostic tools. From the longitudinal images where data is collected from multiple time points, both the spatial structural information and the longitudinal variations are captured. The temporal dynamics are more informative than static observations of the symptoms, particularly for neurodegenerative diseases such as Alzheimer’s disease, whose progression spans over the years with early subtle changes. In this paper, we propose a new generative framework to predict the lesion progression over time. Our method first encodes images into the structural and longitudinal state vectors, where interpolation or extrapolation of feature vectors in the time axis can be performed for the manipulation of these feature vectors. These processed feature vectors can be decoded into image space to predict the image at the time point which we are interested in. During the training, we force the model to encode longitudinal changes into longitudinal state features and capture the structural information in a separate vector. Moreover, we introduce a personalized memory for the online update scheme, which adapts the model to the target subject, which helps the model preserve fine details of brain image structures in each subject. Experimental results on the public longitudinal brain magnetic resonance imaging dataset show the effectiveness of the proposed method.

Partially Supervised Kernel Induced Rough Fuzzy Clustering for Brain Tissue Segmentation

In modern imaging diagnosis Magnetic Resonance Imaging (MRI) is possibly one of the widely used effective techniques particularly for brain tissue segmentation. Clustering techniques may not be perfect always. Clustering can be significantly improved by supervising partially. A novel partially supervised kernel induced rough fuzzy clustering is proposed for brain tissue segmentation by employing a small quantity of labeled pixels with constraint seeded policy. Labeled pixels act as the constraints which are utilized to initialize the clustering process and guide the method towards a more accurate partitioning. Kernel trick used here enhances the possibility of linear partition of different complex segments of brain which cannot separate linearly in its original feature space. Whereas, the rough and fuzzy set handles the overlappingness, vagueness and indiscernibility of different tissue regions. A variety of benchmark brain MRI datasets are used for the experiments. The ability of the method is compared with state-of-the-art clustering segmentation techniques and evaluated using different validity indices. Experimental results confirm that the technique considerably enhances the segmentation accuracy with a little quantity of supervision. Enhancement in accuracy gained by the method compared to the other techniques are 0.3, 0.37, 1.15, and 1.03% for IBSR datasets 144, 150, 155, and 167, respectively, and 1.02% for the BrainWeb dataset 85. Statistical impact of the method is confirmed from the paired t-test results.

Computer-Aided Diagnosis of Alzheimer's Disease through Weak Supervision Deep Learning Framework with Attention Mechanism.

Alzheimer’s disease (AD) is the most prevalent neurodegenerative disease causing dementia and poses significant health risks to middle-aged and elderly people. Brain magnetic resonance imaging (MRI) is the most widely used diagnostic method for AD. However, it is challenging to collect sufficient brain imaging data with high-quality annotations. Weakly supervised learning (WSL) is a machine learning technique aimed at learning effective feature representation from limited or low-quality annotations. In this paper, we propose a WSL-based deep learning (DL) framework (ADGNET) consisting of a backbone network with an attention mechanism and a task network for simultaneous image classification and image reconstruction to identify and classify AD using limited annotations. The ADGNET achieves excellent performance based on six evaluation metrics (Kappa, sensitivity, specificity, precision, accuracy, F1-score) on two brain MRI datasets (2D MRI and 3D MRI data) using fine-tuning with only 20% of the labels from both datasets. The ADGNET has an F1-score of 99.61% and sensitivity is 99.69%, outperforming two state-of-the-art models (ResNext WSL and SimCLR). The proposed method represents a potential WSL-based computer-aided diagnosis method for AD in clinical practice.

Bias-Corrected Intuitionistic Fuzzy C-Means With Spatial Neighborhood Information Approach for Human Brain MRI Image Segmentation

Segmentationof MRI imagesin the presence of artifacts such as noise and bias field effect (BFE) is challenging. In this article, to handle both artifacts, we have formulated an intuitionistic fuzzy set (IFS) theory based bias-corrected intuitionistic fuzzy c-means with spatial neighborhood information (SNI) method for magnetic resonance imaging (MRI) image segmentation. We represent the image in terms of IFSs using two well-known intuitionistic fuzzy generation functions, namely Sugeno’s negation function (SNF) and Yager’s negation function (YNF). In this way, the proposed approach takes advantage of the IFS theory to address the uncertainty and vagueness present in data. The SNI term helps to retain the fine image details in the segmentation process, which is usually lost when smoothing is used. The BFE is modeled as a slow varying intensity field additive in nature with mean zero in IFS framework. The proposed approach estimates the bias field and produces a segmented image simultaneously. The segmentation performance of the proposed method is evaluated in terms of the Dice score, average segmentation accuracy (ASA), and index of variation. Further, the comparison of the proposed method with other similar state-of-the-art methods on two well-known publicly available Brain MRI datasets shows the significant improvements in segmentation performance in terms of ASA, Dice score, and index of variation. The proposed approach achieves 93% ASA in the presence of severe bias field and noise artifacts on BrainWeb simulated dataset, which outperformed the state-of-the-art methods.

DeepDicomSort: An Automatic Sorting Algorithm for Brain Magnetic Resonance Imaging Data

With the increasing size of datasets used in medical imaging research, the need for automated data curation is arising. One important data curation task is the structured organization of a dataset for preserving integrity and ensuring reusability. Therefore, we investigated whether this data organization step can be automated. To this end, we designed a convolutional neural network (CNN) that automatically recognizes eight different brain magnetic resonance imaging (MRI) scan types based on visual appearance. Thus, our method is unaffected by inconsistent or missing scan metadata. It can recognize pre-contrast T1-weighted (T1w),post-contrast T1-weighted (T1wC), T2-weighted (T2w), proton density-weighted (PDw) and derived maps (e.g. apparent diffusion coefficient and cerebral blood flow). In a first experiment,we used scans of subjects with brain tumors: 11065 scans of 719 subjects for training, and 2369 scans of 192 subjects for testing. The CNN achieved an overall accuracy of 98.7%. In a second experiment, we trained the CNN on all 13434 scans from the first experiment and tested it on 7227 scans of 1318 Alzheimer’s subjects. Here, the CNN achieved an overall accuracy of 98.5%. In conclusion, our method can accurately predict scan type, and can quickly and automatically sort a brain MRI dataset virtually without the need for manual verification. In this way, our method can assist with properly organizing a dataset, which maximizes the shareability and integrity of the data.

Automated diagnosis of multi-class brain abnormalities using MRI images: A deep convolutional neural network based method

Automated detection of multi-class brain abnormalities through magnetic resonance imaging (MRI) has received much attention due to its clinical significance and therefore has become an active area of research over the years. The earlier automated schemes often followed traditional machine learning paradigms, in which the proper choice of features and classifiers has remained a major concern. Therefore, deep learning algorithms have been profoundly applied in various medical imaging applications. In this paper, a deep convolutional neural network (CNN) based automated approach is designed for the diagnosis of multi-class brain abnormalities. The proposed CNN model comprises five layers with learnable parameters: four convolutional layers and one fully-connected layer. The objective of designing such a custom deep network is to achieve greater classification performance with reduced number of parameters. The proposed model is evaluated on two benchmark multi-class brain MRI datasets namely, MD-1 and MD-2. The model achieved a classification accuracy of 100.00% and 97.50% on MD-1 and MD-2 datasets respectively. Moreover, four pre-trained CNN models based on the transfer learning approach have been tested over the same datasets. The comparative analysis with existing schemes indicates the superiority of the proposed method.

An adaptive sparse Bayesian model combined with probabilistic label fusion for multiple sclerosis lesion segmentation in brain MRI

This paper presents a novel method for automatic segmentation of multiple sclerosis (MS) lesion in brain magnetic resonance (MR) image. The first research directly focuses on the development of an algorithm called the adaptive sparse Bayesian decision theorem (ASBDT), which integrates Markov random field theorem and Gibbs random field theorem to segment MS lesion in T1-w, T2-w and FLAIR images, respectively. The second research focus is based on a probabilistic label fusion (PLF) algorithm, which utilizes a set of prior known multi-atlas obtained from T1-w, T2-w and FLAIR images, respectively. The PLF algorithm is based on local weighted voting strategy, in which a specific coefficient obtained using the maximum likelihood function between the prior known atlas and the target image is assigned as the weight to individual atlas. The proposed segmentation approach is evaluated by 20 brain MR image data sets from the MICCAI MS Lesion Segmentation Challenge. The values of evaluation parameters TPR, PPV, DSC indicate that our approach is better than some other methods. According to the McDonald Criteria updated in 2017, the number and volume is a key point in defining the disease, we calculate the total MS lesion volume and number. Therefore, this novel approach has an added value for the clinical evaluation of MS lesion patients.

A robust clustering algorithm using spatial fuzzy C-means for brain MR images

Magnetic Resonance Imaging (MRI) is a medical imaging modality that is commonly employed for the analysis of different diseases. However, these images come with several problems such as noise and other imaging artifacts added during acquisition process. The researchers have actual challenges for segmentation under the consideration of these effects. In medical images, a well-known clustering approach like Fuzzy C-Means widely used for segmentation. The performance of FCM algorithm is fast in noise-free images; however, this method did not consider the spatial context of the image due to which its performance suffers when images corrupted with noise and other imaging relics. In this paper, a weighted spatial Fuzzy C-Means (wsFCM) segmentation method is proposed that considered the spatial information of image. Moreover, a spatial function is also developed that integrate a membership function. In order assess this function, a neighborhood window is established around a pixel and more weights have been assigned to those pixels which have greater correlation with central pixel in local neighborhood. By integration of this spatial function in membership function, the modified membership function strengthens the original membership function in handling the noise and intensity inhomogeneity, which has the ability to preserves and maintains structural information like edges. A comprehensive set of experimentation is performed on publicly accessible simulated and real standard brain MRI datasets. The performance of the proposed method has been compared with existing state-of-the-art methods. The results show that the performance of the proposed method is better and robust in handling noise and intensity inhomogeneity than of the existing works.

Missing MRI Pulse Sequence Synthesis Using Multi-Modal Generative Adversarial Network.

Magnetic resonance imaging (MRI) is being increasingly utilized to assess, diagnose, and plan treatment for a variety of diseases. The ability to visualize tissue in varied contrasts in the form of MR pulse sequences in a single scan provides valuable insights to physicians, as well as enabling automated systems performing downstream analysis. However, many issues like prohibitive scan time, image corruption, different acquisition protocols, or allergies to certain contrast materials may hinder the process of acquiring multiple sequences for a patient. This poses challenges to both physicians and automated systems since complementary information provided by the missing sequences is lost. In this paper, we propose a variant of generative adversarial network (GAN) capable of leveraging redundant information contained within multiple available sequences in order to generate one or more missing sequences for a patient scan. The proposed network is designed as a multi-input, multi-output network which combines information from all the available pulse sequences and synthesizes the missing ones in a single forward pass. We demonstrate and validate our method on two brain MRI datasets each with four sequences, and show the applicability of the proposed method in simultaneously synthesizing all missing sequences in any possible scenario where either one, two, or three of the four sequences may be missing. We compare our approach with competing unimodal and multi-modal methods, and show that we outperform both quantitatively and qualitatively.

Deep extreme learning machine with leaky rectified linear unit for multiclass classification of pathological brain images

Automatic binary classification of brain magnetic resonance (MR) images has made remarkable progress in the past decade. In comparison, a few pieces of work has been reported on multiclass classification of brain MR images. However, there exist enough scopes for improved automation and accuracy. Most of the existing schemes follow the multi-stage pipeline structure of conventional machine learning framework, where the features are designed manually or hand-crafted. In recent years, deep learning models have attracted great interest from researchers for analyzing medical images that eliminate the traditional steps of machine learning. In this paper, we present an automated method based on deep extreme learning machine (ELM) also termed as multilayer ELM (ML-ELM) for multiclass classification of the pathological brain. ML-ELM is a multilayer architecture stacked with ELM based autoencoders. The effectiveness of leaky rectified linear unit (LReLU) activation function is investigated with ML-ELM. Extensive simulations on a multiclass brain MR image dataset indicate that the ML-ELM with LReLU activation (ML-ELM+LReLU) achieves higher performance with faster training speed compared to its counterparts as well as state-of-the-art schemes. The basic purpose of employing ML-ELM+LReLU algorithm is to eliminate the need for hand-crafted feature extraction and to develop a more stable and generalized system for multiclass brain MR image classification.