Brain Magnetic Resonance Imaging Datasets Research Articles

Towards a unified approach for unsupervised brain MRI Motion Artefact Detection with few shot Anomaly Detection

Automated Motion Artefact Detection (MAD) in Magnetic Resonance Imaging (MRI) is a field of study that aims to automatically flag motion artefacts in order to prevent the requirement for a repeat scan. In this paper, we identify and tackle the three current challenges in the field of automated MAD; (1) reliance on fully-supervised training, meaning they require specific examples of Motion Artefacts (MA), (2) inconsistent use of benchmark datasets across different works and use of private datasets for testing and training of newly proposed MAD techniques and (3) a lack of sufficiently large datasets for MRI MAD. To address these challenges, we demonstrate how MAs can be identified by formulating the problem as an unsupervised Anomaly Detection (AD) task. We compare the performance of three State-of-the-Art AD algorithms DeepSVDD, Interpolated Gaussian Descriptor and FewSOME on two open-source Brain MRI datasets on the task of MAD and MA severity classification, with FewSOME achieving a MAD AUC >90% on both datasets and a Spearman Rank Correlation Coefficient of 0.8 on the task of MA severity classification. These models are trained in the few shot setting, meaning large Brain MRI datasets are not required to build robust MAD algorithms. This work also sets a standard protocol for testing MAD algorithms on open-source benchmark datasets. In addition to addressing these challenges, we demonstrate how our proposed ‘anomaly-aware’ scoring function improves FewSOME’s MAD performance in the setting where one and two shots of the anomalous class are available for training. Code available at https://github.com/niamhbelton/Unsupervised-Brain-MRI-Motion-Artefact-Detection/.

NBEST: Deep-learning-based non-human primates Brain Extraction and Segmentation Toolbox across ages, sites and species

Accurate processing and analysis of non-human primate (NHP) brain magnetic resonance imaging (MRI) serves an indispensable role in understanding brain evolution, development, aging, and diseases. Despite the accumulation of diverse NHP brain MRI datasets at various developmental stages and from various imaging sites/scanners, existing computational tools designed for human MRI typically perform poor on NHP data, due to huge differences in brain sizes, morphologies, and imaging appearances across species, sites, and ages, highlighting the imperative for NHP-specialized MRI processing tools. To address this issue, in this paper, we present a robust, generic, and fully automated computational pipeline, called non-human primates Brain Extraction and Segmentation Toolbox (nBEST), whose main functionality includes brain extraction, non-cerebrum removal, and tissue segmentation. Building on cutting-edge deep learning techniques by employing lifelong learning to flexibly integrate data from diverse NHP populations and innovatively constructing 3D U-NeXt architecture, nBEST can well handle structural NHP brain MR images from multi-species, multi-site, and multi-developmental-stage (from neonates to the elderly). We extensively validated nBEST based on, to our knowledge, the largest assemblage dataset in NHP brain studies, encompassing 1,469 scans with 11 species (e.g., rhesus macaques, cynomolgus macaques, chimpanzees, marmosets, squirrel monkeys, etc.) from 23 independent datasets. Compared to alternative tools, nBEST outperforms in precision, applicability, robustness, comprehensiveness, and generalizability, greatly benefiting downstream longitudinal, cross-sectional, and cross-species quantitative analyses. We have made nBEST an open-source toolbox (https://github.com/TaoZhong11/nBEST) and we are committed to its continual refinement through lifelong learning with incoming data to greatly contribute to the research field.

Brain MR Image Classification Using Superpixel-Based Deep Transfer Learning.

Nowadays, brain MR (Magnetic Resonance) images are widely used by clinicians to examine the brain's anatomy to look into various pathological conditions like cerebrovascular incidents and neuro-degenerative diseases. Generally, these diseases can be identified with the MR images as "normal" and "abnormal" brains in a two-class classification problem or as disease-specific classes in a multi-class problem. This article presents an ensemble transfer learning-inspired deep architecture that uses the simple linear iterative clustering (SLIC)-based superpixel algorithm along with convolutional neural network (CNN) to classify the MR images as normal or abnormal. Superpixel algorithm segments the input MR images into clusters of regions defined by similarity measures using perceptual feature space. These superpixel images are beneficial as they can provide a compact and meaningful role in computationally demanding applications. The superpixel images are then fed to the deep convolutional neural network (CNN) to classify the images. Three brain MR image datasets, NITR-DHH, DS-75, and DS-160, are used to conduct the experimentation. Through the use of deep transfer learning, the model achieves performance accuracy of 88.15% (NITR-DHH), 98.15% (DS-160), and 98.33% (DS-75) even with the small-scale medical image dataset. The experimentally obtained results demonstrate that the proposed method is promising and efficient for clinical applications for diagnosing different brain diseases via MR images.

PDFF-CNN: An attention-guided dynamic multi-orientation feature fusion method for gestational age prediction on imbalanced fetal brain MRI dataset.

Fetal brain magnetic resonance imaging (MRI)-based gestational age prediction has been widely used to characterize normal fetal brain development and diagnose congenital brainmalformations. The uncertainty of fetal position and external interference leads to variable localization and direction of the fetal brain. In addition, pregnant women typically concentrate on receiving MRI scans during the fetal anomaly scanning week, leading to an imbalanced distribution of fetal brain MRI data. The above-mentioned problems pose great challenges for deep learning-based fetal brain MRI gestational ageprediction. In this study, a pyramid squeeze attention (PSA)-guided dynamic feature fusion CNN (PDFF-CNN) is proposed to robustly predict gestational ages from fetal brain MRI images on an imbalanced dataset. PDFF-CNN contains four components: transformation module, feature extraction module, dynamic feature fusion module, and balanced mean square error (MSE) loss. The transformation and feature extraction modules are employed by using the PSA to learn multiscale and multi-orientation feature representations in a parallel weight-sharing Siamese network. The dynamic feature fusion module automatically learns the weights of feature vectors generated in the feature extraction module to dynamically fuse multiscale and multi-orientation brain sulci and gyri features. Considering the fact of the imbalanced dataset, the balanced MSE loss is used to mitigate the negative impact of imbalanced data distribution on gestational age predictionperformance. Evaluated on an imbalanced fetal brain MRI dataset of 1327 routine clinical T2-weighted MRI images from 157 subjects, PDFF-CNN achieved promising gestational age prediction performance with an overall mean absolute error of 0.848 weeks and an of 0.904. Furthermore, the attention activation maps of PDFF-CNN were derived, which revealed regional features that contributed to gestational age prediction at each gestationalstage. These results suggest that the proposed PDFF-CNN might have broad clinical applicability in guiding treatment interventions and delivery planning, which has the potential to be helpful with prenatal diagnosis.

Hybrid‐NET: A fusion of DenseNet169 and advanced machine learning classifiers for enhanced brain tumor diagnosis

AbstractThe computer‐aided diagnostic (CAD) method to detect human brain tumors relies heavily on automated tumor characterization. Although CAD method has been extensively researched, significant obstacles still exist. Magnetic resonance imaging (MRI) classifiers brain tumors into glioma, meningioma, and pituitary tumors. However, accurately distinguishing between these tumor types remains a complex challenge in medical imaging. The recently developed deep learning and machine learning (ML) techniques have shown immense potential in image classification. However, the low numbers of medical image archives also pose a problem for medical image classification. As a result, fewer medical images are available to use in deep learning research and development. To address this issue, we use three highly effective ML classifiers with deep convolutional learned features for medical image classification. The MRI images of the three distinct types of brain tumors may be found in an open dataset on Figshare, which tests the automated approach's efficacy. Features are extracted from brain MRI scans using the DenseNet169 model. Extracted features are fed into a multiclass three ML classifiers (RF, SVM, XGBoost) for improved performance. Results from testing and evaluation of the entire framework are promising, especially compared to the field's state‐of‐the art technique. The suggested model outperformed the state‐of‐the‐art technique, with an overall classification accuracy of 95.10%. To verify the enhanced performance of the proposed system, extensive tests are conducted on the brain MRI dataset available on Figshare. The optimal hyper‐parameter fading classifier is seen to outperform the Softmax classifier for the features when there is limited training data.

SOFNet: Optical-flow based large-scale slice augmentation of brain MRI

Brain magnetic resonance imaging (MRI) data from multiple centers often exhibit variations in imaging conditions, such as the types of nuclear magnetic resonance instruments used and the presence of random noise. Additionally, discrepancies in the gap between MRI slices further complicate the usability of the data for advanced artificial intelligence (AI) analysis. Deep learning-based methods have emerged as practical solutions to address the challenge. However, existing research has largely overlooked the augmentation of brain MRI data, particularly when confronted with significant slice gaps, such as around 6 mm observed in our clinical brain MRI slices. In response to this research gap, we aim to develop novel approaches for augmenting brain MRI data, focusing on more significant slice gaps. To achieve this, we propose SOFNet, which utilizes the optical flow-based and encoder–decoder backbone. The primary objective of our model is to interpolate MRI slices while preserving feature consistency. Leveraging the optical flow method, which has exhibited exceptional performance compared to other super-resolution algorithms, our proposed approach has been evaluated on three distinct brain MRI datasets, explicitly addressing the gap between 4.2 mm and 6.0 mm. The experimental results highlight the significant enhancement in super-resolution quality achieved by SOFNet in generating adapted brain MRI data, surpassing other single-image super-resolution (SISR) methods in feature completion. To ensure the credibility of the interpolated brain MRI slices, we conducted experiments on three axes of MRI based on metrics such as peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). These experiments demonstrate the effectiveness of our approach in transforming low-resolution MRI data into clear and reliable brain MRIs, thereby enabling improved analysis using AI techniques.

PFP-HOG: Pyramid and Fixed-Size Patch-Based HOG Technique for Automated Brain Abnormality Classification with MRI.

Detecting neurological abnormalities such as brain tumors and Alzheimer's disease (AD) using magnetic resonance imaging (MRI) images is an important research topic in the literature. Numerous machine learning models have been used to detect brain abnormalities accurately. This study addresses the problem of detecting neurological abnormalities in MRI. The motivation behind this problem lies in the need for accurate and efficient methods to assist neurologists in the diagnosis of these disorders. In addition, many deep learning techniques have been applied to MRI to develop accurate brain abnormality detection models, but these networks have high time complexity. Hence, a novel hand-modeled feature-based learning network is presented to reduce the time complexity and obtain high classification performance. The model proposed in this work uses a new feature generation architecture named pyramid and fixed-size patch (PFP). The main aim of the proposed PFP structure is to attain high classification performance using essential feature extractors with both multilevel and local features. Furthermore, the PFP feature extractor generates low- and high-level features using a handcrafted extractor. To obtain the high discriminative feature extraction ability of the PFP, we have used histogram-oriented gradients (HOG); hence, it is named PFP-HOG. Furthermore, the iterative Chi2 (IChi2) is utilized to choose the clinically significant features. Finally, the k-nearest neighbors (kNN) with tenfold cross-validation is used for automated classification. Four MRI neurological databases (AD dataset, brain tumor dataset 1, brain tumor dataset 2, and merged dataset) have been utilized to develop our model. PFP-HOG and IChi2-based models attained 100%, 94.98%, 98.19%, and 97.80% using the AD dataset, brain tumor dataset1, brain tumor dataset 2, and merged brain MRI dataset, respectively. These findings not only provide an accurate and robust classification of various neurological disorders using MRI but also hold the potential to assist neurologists in validating manual MRI brain abnormality screening.

Multi-modal brain magnetic resonance imaging database covering marmosets with a wide age range

Magnetic resonance imaging (MRI) is a non-invasive neuroimaging technique that is useful for identifying normal developmental and aging processes and for data sharing. Marmosets have a relatively shorter life expectancy than other primates, including humans, because they grow and age faster. Therefore, the common marmoset model is effective in aging research. The current study investigated the aging process of the marmoset brain and provided an open MRI database of marmosets across a wide age range. The Brain/MINDS Marmoset Brain MRI Dataset contains brain MRI information from 216 marmosets ranging in age from 1 and 10 years. At the time of its release, it is the largest public dataset in the world. It also includes multi-contrast MRI images. In addition, 91 of 216 animals have corresponding high-resolution ex vivo MRI datasets. Our MRI database, available at the Brain/MINDS Data Portal, might help to understand the effects of various factors, such as age, sex, body size, and fixation, on the brain. It can also contribute to and accelerate brain science studies worldwide.

Super-resolution of brain MRI images based on denoising diffusion probabilistic model

Super-resolution of brain magnetic resonance imaging (MRI) generates high resolution brain images as opposed to low-resolution ones, thus providing more detailed anatomical information for diagnosis of neurodegenerative diseases. Although denoising diffusion probabilistic model (DDPM) has displayed remarkable performance in super-resolution of face and natural images, its application to producing high-resolution brain MRI images has not been explored. This study proposed a new deep-learning super-resolution framework for brain MRI images based on DDPM, via incorporating self-attention mechanism into DDPM. The main improvements are as follows: (a) Only one input channel is preserved. (b) The number of baseline channels is reduced from 64 to 32, to improve training speed. (c) Self-attention mechanism is added to 32 × 32, 16 × 16, and 8 × 8 resolution layers rather than only to 16 × 16 layer. (d) Feature-wise affine transformation is added to residual block. Experimental results on open T1- and diffusion-weighted brain MRI datasets show that our DDPM model outperformed the state-of-the-art super-resolution methods. In terms of learned perceptual image patch similarity (LPIPS) metric, the proposed DDPM model achieved the least distortion of generated super-resolution brain MRI images. This framework can also be conveniently used to reconstruct high-resolution MRI images of other body parts such as spinal and knee in future.

Hybrid Deep Learning Models for Multi-classification of Tumour from Brain MRI

Background: Brain tumour categorisation can be assisted with computer-aided diagnostic (CAD) for medical applications. Biopsies to classify brain tumours can be costly and time-consuming. Radiologists may also misclassify brain tumour types when handling large amounts of data with multiple classes. In this case, technological advancements and machine learning can help. Objective: This study proposes hybrid deep learning approaches for classifying brain tumours using convolutional neural networks (CNN) and machine learning (ML) classifiers. Methods: A new 23-layer CNN architecture is developed for brain deep feature extraction from magnetic resonance imaging (MRI). Random forest (RF) and support vector machine (SVM) classifiers are then used to evaluate the extracted in-depth features from the flattened layer of the CNN model. This study is unique because it employs CNN, CNN-RF, CNN-SVM, and tuned Inception V3 deep learning models on multi-class brain MRI datasets. The proposed hybrid method is run on two publicly available datasets. Results: Among the four models, the CNN-RF model achieves 96.52% accuracy on the Fig share 3c dataset, while the CNN-SVM model achieves 95.41% accuracy on the large Kaggle 4c dataset with four classes (glioma, meningioma, normal, pituitary). Conclusion: Experimental outcomes show that the hybrid techniques can significantly enhance the classification performance, especially on multi-class datasets (glioma, meningioma, normal, pituitary). This study also examines the various weight strategies for dealing with overfitting analytics. Keywords: Brain Tumour, Convolutional Neural Network, Feature Extraction, Multi-Classification, Machine Learning Classifiers

Brain MRI high resolution image creation and segmentation with the new GAN method

Brain magnetic resonance imaging segmentation is a recent and still popular research area. Good and accurate segmentation results play an important role in the diagnosis of cancer or other brain diseases. In this article, a novel Generative Adversarial Network architecture is proposed for brain magnetic resonance imaging segmentation. The proposed method is called SSimDCL (Supervised SimDCL). Four studies were conducted in this article. In the first study, the SSimDCL method on the two-dimensional brain magnetic resonance imaging dataset was compared with the current state-of-art architectures CycleGAN, CUT, FastCUT, DCLGAN, and SimDCL. In the second study, the dataset resolution was improved. In the third study, being measured the efficiency of the newly created dataset. And the SSimDCL is trained for both the dataset with increased resolution and the normal dataset, and the results are obtained. In the fourth study, the results of the SSimDCL and the VolBrain brain magnetic resonance imaging segmentation results, which are widely used today, are included. When VolBrain segmentation and SSimDCL segmentation are compared. The results were compared both visually and metrically. Fréchet Inception Distance (FID), Kernel Inception Distance (KID), Peak Signal to Noise Ratio (PSNR) and Learned Perceptual Image Patch Similarity (LPIPS) were used as measurement metrics. The Jaccard and Dice similarity metrics were also used in the analysis. It was observed that the SSimDCL give satisfactory results in all four studies. This method can be used as an automatic brain MRI image segmentation system.

PTNet3D: A 3D High-Resolution Longitudinal Infant Brain MRI Synthesizer Based on Transformers.

An increased interest in longitudinal neurodevelopment during the first few years after birth has emerged in recent years. Noninvasive magnetic resonance imaging (MRI) can provide crucial information about the development of brain structures in the early months of life. Despite the success of MRI collections and analysis for adults, it remains a challenge for researchers to collect high-quality multimodal MRIs from developing infant brains because of their irregular sleep pattern, limited attention, inability to follow instructions to stay still during scanning. In addition, there are limited analytic approaches available. These challenges often lead to a significant reduction of usable MRI scans and pose a problem for modeling neurodevelopmental trajectories. Researchers have explored solving this problem by synthesizing realistic MRIs to replace corrupted ones. Among synthesis methods, the convolutional neural network-based (CNN-based) generative adversarial networks (GANs) have demonstrated promising performance. In this study, we introduced a novel 3D MRI synthesis framework- pyramid transformer network (PTNet3D)- which relies on attention mechanisms through transformer and performer layers. We conducted extensive experiments on high-resolution Developing Human Connectome Project (dHCP) and longitudinal Baby Connectome Project (BCP) datasets. Compared with CNN-based GANs, PTNet3D consistently shows superior synthesis accuracy and superior generalization on two independent, large-scale infant brain MRI datasets. Notably, we demonstrate that PTNet3D synthesized more realistic scans than CNN-based models when the input is from multi-age subjects. Potential applications of PTNet3D include synthesizing corrupted or missing images. By replacing corrupted scans with synthesized ones, we observed significant improvement in infant whole brain segmentation.

Isolated Convolutional-Neural-Network-Based Deep-Feature Extraction for Brain Tumor Classification Using Shallow Classifier.

In today’s world, a brain tumor is one of the most serious diseases. If it is detected at an advanced stage, it might lead to a very limited survival rate. Therefore, brain tumor classification is crucial for appropriate therapeutic planning to improve patient life quality. This research investigates a deep-feature-trained brain tumor detection and differentiation model using classical/linear machine learning classifiers (MLCs). In this study, transfer learning is used to obtain deep brain magnetic resonance imaging (MRI) scan features from a constructed convolutional neural network (CNN). First, multiple layers (19, 22, and 25) of isolated CNNs are constructed and trained to evaluate the performance. The developed CNN models are then utilized for training the multiple MLCs by extracting deep features via transfer learning. The available brain MRI datasets are employed to validate the proposed approach. The deep features of pre-trained models are also extracted to evaluate and compare their performance with the proposed approach. The proposed CNN deep-feature-trained support vector machine model yielded higher accuracy than other commonly used pre-trained deep-feature MLC training models. The presented approach detects and distinguishes brain tumors with 98% accuracy. It also has a good classification rate (97.2%) for an unknown dataset not used to train the model. Following extensive testing and analysis, the suggested technique might be helpful in assisting doctors in diagnosing brain tumors.

Deep feature extraction based brain image classification model using preprocessed images: PDRNet

BackgroundStroke is a neurological condition that occurs when cerebral vessels become blocked and have reduced blood flow. This research proposes a hybrid deep feature-based feature engineering model to achieve high classification performance. Materials and methodIn this research, three brain magnetic resonance image datasets were used to test the proposed model. A deep feature engineering model has been proposed to deploy the raw MRI and four preprocessing algorithms: GradCAM, histogram-matching, canny edge detection, and Locally Interpretable Model-Agnostic Explanations(LIME). The deep features have been extracted using Resnet101 and DenseNet201 pre-trained convolutional neural networks (CNN). Thus, this model is titled preprocessing based DenseNet and ResNet (PDRNet). The iterative neighborhood component analysis (INCA) function selects the most suitable features. These features are trained and validated using support vector machine (SVM) classifiers. Iterative Majority Voting (IMV) has been applied to the results obtained from the SVM. The best classification result has been selected by deploying IMV. ResultsOur proposed PDRNet achieved a classification accuracy of 97.56% for Dataset 1, 99.32% for Dataset 2, and 99.16% for Dataset 3. The success of the presented model is demonstrated using these calculated accuracies. ConclusionsOur proposed hybrid deep feature model was tested on two datasets with two and four classes. It has also been compared to other state-of-art deep learning-based models, and our model performs better. These results and findings clearly demonstrate the success of the introduced hybrid deep feature engineering method.

Multi-mask self-supervised learning for physics-guided neural networks in highly accelerated magnetic resonance imaging.

Self-supervised learning has shown great promise because of its ability to train deep learning (DL) magnetic resonance imaging (MRI) reconstruction methods without fully sampled data. Current self-supervised learning methods for physics-guided reconstruction networks split acquired undersampled data into two disjoint sets, where one is used for data consistency (DC) in the unrolled network, while the other is used to define the training loss. In this study, we propose an improved self-supervised learning strategy that more efficiently uses the acquired data to train a physics-guided reconstruction network without a database of fully sampled data. The proposed multi-mask self-supervised learning via data undersampling (SSDU) applies a holdout masking operation on the acquired measurements to split them into multiple pairs of disjoint sets for each training sample, while using one of these pairs for DC units and the other for defining loss, thereby more efficiently using the undersampled data. Multi-mask SSDU is applied on fully sampled 3D knee and prospectively undersampled 3D brain MRI datasets, for various acceleration rates and patterns, and compared with the parallel imaging method, CG-SENSE, and single-mask SSDU DL-MRI, as well as supervised DL-MRI when fully sampled data are available. The results on knee MRI show that the proposed multi-mask SSDU outperforms SSDU and performs as well as supervised DL-MRI. A clinical reader study further ranks the multi-mask SSDU higher than supervised DL-MRI in terms of signal-to-noise ratio and aliasing artifacts. Results on brain MRI show that multi-mask SSDU achieves better reconstruction quality compared with SSDU. The reader study demonstrates that multi-mask SSDU at R = 8 significantly improves reconstruction compared with single-mask SSDU at R = 8, as well as CG-SENSE at R = 2.

Robust 3D brain segmentation in magnetic resonance image with weighted feature fusion

Accurate tissue segmentation in brain magnetic resonance image is of paramount importance for brain reconstruction and analysis. Supervoxels analysis enables relatively robust segmentation of brain tissues, by assigning the supervoxels to tissue clusters according to the inherent information of multiple features captured from the supervoxels. In this popular framework, difficulties are encountered in clustering imposed by the insufficient selection, deficient utilisation of features, and rough supervoxel boundaries due to the influence of noise. To address these aforementioned challenges, the authors propose a weighted feature fusion clustering segmentation method for dividing supervoxels into three tissues on the basis of a robust feature fused similarity matrix. To comprehensively capture the similarities of features among the supervoxels, we construct three complementary similarity matrices on the basis of multiple features from three aspects, that is, appearance, shape, and space location. Next, the authors propose a weighted similarity network fusion method to discriminatively fuse the three similarity matrices into one single matrix. This novel fusion process cannot only extract the common and complementary information of features, but also automatically adjust the weight of similarities according to its reliability. Finally, we achieve initial segmentation results by performing spectral clustering on the fused similarity matrix. To optimise the segmented boundaries affected by noise in the initial segmentation results, the authors construct a voxel-wise diffusion energy function by considering the intensity information of neighbouring voxels. Experiments on two public brain magnetic resonance image datasets demonstrate the robustness of the proposed approach.

Brain Tumor Classification Based on Hybrid Optimized Multi-features Analysis Using Magnetic Resonance Imaging Dataset

ABSTRACT Brain tumors are deadly but become deadliest because of delayed and inefficient diagnosis process. Large variations in tumor types also instigate additional complexity. Machine vision brain tumor diagnosis addresses the problem. This research’s objective was to develop a brain tumor classification model based on machine vision techniques using brain Magnetic Resonance Imaging (MRI). For this purpose, a novel hybrid-brain-tumor-classification (HBTC) framework was designed and evaluated for the classification of cystic (cyst), glioma, meningioma (menin), and metastatic (meta) brain tumors. The proposed framework lessens the inherent complexities and boosts performance of the brain tumor diagnosis process. The brain MRI dataset was input to the HBTC framework, pre-processed, segmented to localize the tumor region. From the segmented dataset Co-occurrence matrix (COM), run-length matrix (RLM), and gradient features were extracted. After the application of hybrid multi-features, the nine most optimized features were selected and input to the framework’s classifiers, namely multilayer perception (MLP), J48, meta bagging (MB), and random tree (RT) to classify cyst, glioma, menin, and meta tumors. Maximum brain tumor classification performance achieved by the HBTC framework was 98.8%. The components and performance of the proposed framework show that it is a novel and robust classification framework.

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.