Brain Magnetic Resonance Imaging Analysis Research Articles

Comparative assessment of established and deep learning-based segmentation methods for hippocampal volume estimation in brain magnetic resonance imaging analysis.

In this study, our objective was to assess the performance of two deep learning-based hippocampal segmentation methods, SynthSeg and TigerBx, which are readily available to the public. We contrasted their performance with that of two established techniques, FreeSurfer-Aseg and FSL-FIRST, using three-dimensional T1-weighted MRI scans (n = 1447) procured from public databases. Our evaluation focused on the accuracy and reproducibility of these tools in estimating hippocampal volume. The findings suggest that both SynthSeg and TigerBx are on a par with Aseg and FIRST in terms of segmentation accuracy and reproducibility, but offer a significant advantage in processing speed, generating results in less than 1 min compared with several minutes to hours for the latter tools. In terms of Alzheimer's disease classification based on the hippocampal atrophy rate, SynthSeg and TigerBx exhibited superior performance. In conclusion, we evaluated the capabilities of two deep learning-based segmentation techniques. The results underscore their potential value in clinical and research environments, particularly when investigating neurological conditions associated with hippocampal structures.

SuMRak: a multi-tool solution for preclinical brain MRI data analysis.

Magnetic resonance imaging (MRI) is invaluable for understanding brain disorders, but data complexity poses a challenge in experimental research. In this study, we introduce suMRak, a MATLAB application designed for efficient preclinical brain MRI analysis. SuMRak integrates brain segmentation, volumetry, image registration, and parameter map generation into a unified interface, thereby reducing the number of separate tools that researchers may require for straightforward data handling. All functionalities of suMRak are implemented using the MATLAB App Designer and the MATLAB-integrated Python engine. A total of six helper applications were developed alongside the main suMRak interface to allow for a cohesive and streamlined workflow. The brain segmentation strategy was validated by comparing suMRak against manual segmentation and ITK-SNAP, a popular open-source application for biomedical image segmentation. When compared with the manual segmentation of coronal mouse brain slices, suMRak achieved a high Sørensen-Dice similarity coefficient (0.98 ± 0.01), approaching manual accuracy. Additionally, suMRak exhibited significant improvement (p = 0.03) when compared to ITK-SNAP, particularly for caudally located brain slices. Furthermore, suMRak was capable of effectively analyzing preclinical MRI data obtained in our own studies. Most notably, the results of brain perfusion map registration to T2-weighted images were shown, improving the topographic connection to anatomical areas and enabling further data analysis to better account for the inherent spatial distortions of echoplanar imaging. SuMRak offers efficient MRI data processing of preclinical brain images, enabling researchers' consistency and precision. Notably, the accelerated brain segmentation, achieved through K-means clustering and morphological operations, significantly reduces processing time and allows for easier handling of larger datasets.

Magnetic Resonance Imaging Characteristics of LGI1-Antibody and CASPR2-Antibody Encephalitis

Rapid and accurate diagnosis of autoimmune encephalitis encourages prompt initiation of immunotherapy toward improved patient outcomes. However, clinical features alone may not sufficiently narrow the differential diagnosis, and awaiting autoantibody results can delay immunotherapy. To identify simple magnetic resonance imaging (MRI) characteristics that accurately distinguish 2 common forms of autoimmune encephalitis, LGI1- and CASPR2-antibody encephalitis (LGI1/CASPR2-Ab-E), from 2 major differential diagnoses, viral encephalitis (VE) and Creutzfeldt-Jakob disease (CJD). This cross-sectional study involved a retrospective, blinded analysis of the first available brain MRIs (taken 2000-2022) from 192 patients at Oxford University Hospitals in the UK and Mayo Clinic in the US. These patients had LGI1/CASPR2-Ab-E, VE, or CJD as evaluated by 2 neuroradiologists (discovery cohort; n = 87); findings were validated in an independent cohort by 3 neurologists (n = 105). Groups were statistically compared with contingency tables. Data were analyzed in 2023. MRI findings including T2 or fluid-attenuated inversion recovery (FLAIR) hyperintensities, swelling or volume loss, presence of gadolinium contrast enhancement, and diffusion-weighted imaging changes. Correlations with clinical features. Among 192 participants with MRIs reviewed, 71 were female (37%) and 121 were male (63%); the median age was 66 years (range, 19-92 years). By comparison with VE and CJD, in LGI1/CASPR2-Ab-E, T2 and/or FLAIR hyperintensities were less likely to extend outside the temporal lobe (3/42 patients [7%] vs 17/18 patients [94%] with VE; P < .001, and 3/4 patients [75%] with CJD; P = .005), less frequently exhibited swelling (12/55 [22%] with LGI1/CASPR2-Ab-E vs 13/22 [59%] with VE; P = .003), and showed no diffusion restriction (0 patients vs 16/22 [73%] with VE and 8/10 [80%] with CJD; both P < .001) and rare contrast enhancement (1/20 [5%] vs 7/17 [41%] with VE; P = .01). These findings were validated in an independent cohort and generated an area under the curve of 0.97, sensitivity of 90%, and specificity of 95% among cases with T2/FLAIR hyperintensity in the hippocampus and/or amygdala. In this study, T2 and/or FLAIR hyperintensities confined to the temporal lobes, without diffusion restriction or contrast enhancement, robustly distinguished LGI1/CASPR2-Ab-E from key differential diagnoses. These observations should assist clinical decision-making toward expediting immunotherapy. Their generalizability to other forms of autoimmune encephalitis and VE should be examined in future studies.

GPU-Based Parallel Processing Techniques for Enhanced Brain Magnetic Resonance Imaging Analysis: A Review of Recent Advances.

The approach of using more than one processor to compute in order to overcome the complexity of different medical imaging methods that make up an overall job is known as GPU (graphic processing unit)-based parallel processing. It is extremely important for several medical imaging techniques such as image classification, object detection, image segmentation, registration, and content-based image retrieval, since the GPU-based parallel processing approach allows for time-efficient computation by a software, allowing multiple computations to be completed at once. On the other hand, a non-invasive imaging technology that may depict the shape of an anatomy and the biological advancements of the human body is known as magnetic resonance imaging (MRI). Implementing GPU-based parallel processing approaches in brain MRI analysis with medical imaging techniques might be helpful in achieving immediate and timely image capture. Therefore, this extended review (the extension of the IWBBIO2023 conference paper) offers a thorough overview of the literature with an emphasis on the expanding use of GPU-based parallel processing methods for the medical analysis of brain MRIs with the imaging techniques mentioned above, given the need for quicker computation to acquire early and real-time feedback in medicine. Between 2019 and 2023, we examined the articles in the literature matrix that include the tasks, techniques, MRI sequences, and processing results. As a result, the methods discussed in this review demonstrate the advancements achieved until now in minimizing computing runtime as well as the obstacles and problems still to be solved in the future.

Intracranial tuberculomas: review of MRI findings and clinical features

To present a comprehensive analysis of the clinical features and magnetic resonance imaging (MRI) findings of intracranial tuberculomas in Indonesia. This was a retrospective analysis of brain MRI from 58 patients (29 women), mean age±SD=39±2 years, diagnosed with intracranial tuberculomas. Clinical data, including symptoms, cerebrospinal fluid examination results, and MRI were also analysed. The diagnosis of intracranial tuberculoma was confirmed based on observed MRI changes following anti-tuberculosis therapy. A total of 603 tuberculomas were fully detected via MRI in all patients. Among these lesions, 507 (84%) were located in the cerebrum, 61 (10%) in the cerebellum, 19 (3%) in the basal ganglia, 12 (2%) in the brain stem, and four (1%) in the thalamus. The MRI signals were classified into two groups: tuberculomas with caseating granulomas and tuberculomas with non-caseating granulomas. Among the patients, 29 had concomitant meningitis, seven had hydrocephalus, and four had cerebral infarction. Evidence of pulmonary tuberculosis was found in 16 patients, with one patient having coexisting thoracic vertebral tuberculosis. The present study confirmed the significance of MRI as a valuable tool in the diagnosis of intracranial tuberculomas and the detection of associated abnormalities. The combination of MRI findings with clinical features can enhance the overall diagnostic accuracy for intracranial tuberculomas.

Differences in Brain Atrophy Pattern between People with Multiple Sclerosis and Systemic Diseases with Central Nervous System Involvement Based on Two-Dimensional Linear Measures.

Conventional brain magnetic resonance imaging (MRI) in systemic diseases with central nervous system involvement (SDCNS) may imitate MRI findings of multiple sclerosis (MS). In order to better describe the MRI characteristics of these conditions, in our study we assessed brain volume parameters in MS (n = 58) and SDCNS (n = 41) patients using two-dimensional linear measurements (2DLMs): bicaudate ratio (BCR), corpus callosum index (CCI) and width of third ventricle (W3V). In SDCNS patients, all 2DLMs were affected by age (CCI p = 0.005, BCR p < 0.001, W3V p < 0.001, respectively), whereas in MS patients only BCR and W3V were (p = 0.001 and p = 0.015, respectively). Contrary to SDCNS, in the MS cohort BCR and W3V were associated with T1 lesion volume (T1LV) (p = 0.020, p = 0.009, respectively) and T2 lesion volume (T2LV) (p = 0.015, p = 0.009, respectively). CCI was associated with T1LV in the MS cohort only (p = 0.015). Moreover, BCR was significantly higher in the SDCNS group (p = 0.01) and CCI was significantly lower in MS patients (p = 0.01). The best predictive model to distinguish MS and SDCNS encompassed gender, BCR and T2LV as the explanatory variables (sensitivity 0.91; specificity 0.68; AUC 0.86). Implementation of 2DLMs in the brain MRI analysis of MS and SDCNS patients allowed for the identification of diverse patterns of local brain atrophy in these clinical conditions.

RanMerFormer: Randomized vision transformer with token merging for brain tumor classification

Brains are the control center of the nervous system in human bodies, and brain tumor is one of the most deadly diseases. Currently, magnetic resonance imaging (MRI) is the most effective way to brain tumors early detection in clinical diagnoses due to its superior imaging quality for soft tissues. Manual analysis of brain MRI is error-prone which depends on empirical experience and the fatigue state of the radiologists to a large extent. Computer-aided diagnosis (CAD) systems are becoming more and more impactful because they can provide accurate prediction results based on medical images with advanced techniques from computer vision. Therefore, a novel CAD method for brain tumor classification named RanMerFormer is presented in this paper. A pre-trained vision transformer is used as the backbone model. Then, a merging mechanism is proposed to remove the redundant tokens in the vision transformer, which improves computing efficiency substantially. Finally, a randomized vector functional-link serves as the head in the proposed RanMerFormer, which can be trained swiftly. All the simulation results are obtained from two public benchmark datasets, which reveal that the proposed RanMerFormer can achieve state-of-the-art performance for brain tumor classification. The trained RanMerFormer can be applied in real-world scenarios to assist in brain tumor diagnosis.

Application of Medical Image 3D Visualization Web Platform in Auxiliary Diagnosis and Preoperative Planning

Three-dimensional visualization of medical image data can enable doctors to observe images from more angles and higher dimensions. It is of great significance for doctors to assist in diagnosis and preoperative planning. Most 3D visualization systems are based on desktop applications, which are too dependent on hardware and operating system. This makes it difficult to use across platforms and maintain. Web-based systems tend to have limited capabilities. To this end, we developed a web application, which not only provides DICOM (Digital Imaging and Communications in Medicine) image browsing and annotation functions, but also provides three-dimensional post-processing functions of multiplanar reconstruction, volume rendering, lung parenchyma segmentation and brain MRI (Magnetic Resonance Imaging) analysis. In order to improve the rendering speed, we use the Marching Cube algorithm for 3D reconstruction in the background in an asynchronous way, and save the reconstructed model as glTF (GL Transmission Format). At the same time, Draco compression algorithm is used to optimize the glTF model to achieve more efficient rendering. After performance evaluation, the system reconstructed a CT (Computed Tomography) series of 242 slices and the optimized model was only 6.37mb with a rendering time of less than 2.5s. Three-dimensional visualization of the lung parenchyma clearly shows the volume, location, and shape of pulmonary nodules. The segmentation and reconstruction of different brain tissues can reveal the spatial three-dimensional structure and adjacent relationship of glioma in the brain, which has great application value in auxiliary diagnosis and preoperative planning.

Analysis of Brain MRI: AI-Assisted Healthcare Framework for the Smart Cities

The use of intelligent machines to work and react like humans is vital in emerging smart cities. Computer-aided analysis of complex and huge MRI (Magnetic Resonance Imaging) scans is very important in healthcare applications. Among AI (Artificial Intelligence) driven healthcare applications, tumor detection is one of the contemporary research fields that have become attractive to researchers. There are several modalities of imaging performed on the brain for the purpose of tumor detection. This paper offers a deep learning approach for detecting brain tumors from MR (Magnetic Resonance) images based on changes in the division of the training and testing data and the structure of the CNN (Convolutional Neural Network) layers. The proposed approach is carried out on a brain tumor dataset from the National Centre of Image-Guided Therapy, including about 4700 MRI images of ten brain tumor cases with both normal and abnormal states. The dataset is divided into test, and train subsets with a ratio of the training set to the validation set of 70:30. The main contribution of this paper is introducing an optimum deep learning structure of CNN layers. The simulation results are obtained for 50 epochs in the training phase. The simulation results reveal that the optimum CNN architecture consists of four layers.

Application of Machine Learning Techniques for Characterization of Ischemic Stroke with MRI Images: A Review.

Magnetic resonance imaging (MRI) is a standard tool for the diagnosis of stroke, but its manual interpretation by experts is arduous and time-consuming. Thus, there is a need for computer-aided-diagnosis (CAD) models for the automatic segmentation and classification of stroke on brain MRI. The heterogeneity of stroke pathogenesis, morphology, image acquisition modalities, sequences, and intralesional tissue signal intensity, as well as lesion-to-normal tissue contrast, pose significant challenges to the development of such systems. Machine learning (ML) is increasingly being used in predictive neuroimaging diagnosis and prognostication. This paper reviews image processing and machine learning techniques that have been applied to detect ischemic stroke on brain MRI, including details on image acquisition, pre-processing, techniques to segment, extraction of features, and classification into stroke types. The main objective of this work is to find the state-of-art machine learning techniques used to predict the ischemic stroke and their application in clinical set-up. The article selection is performed according to PRISMA guideline. The state-of-the-art on automated MRI stroke diagnosis, with a focus on machine learning, is discussed, along with its advantages and limitations. We found that the various machine learning models discussed in this article are able to detect the infarcts with an acceptable accuracy of 70–90%. However, no one has highlighted the time complexity to predict the stroke in the model developed, which is an important factor. The work concludes with proposals for future recommendations for building efficient and robust deep learning (DL) models for quantitative brain MRI analysis. In recent work, with the application of DL approaches, using large datasets to train the models has improved the detection accuracy and reduced computational complexity. We suggest that the design of a decision support system based on artificial intelligence (AI) and clinical data presenting symptoms is essential to support clinicians to accelerate diagnosis and timeous therapy in the emergency management of stroke.

Automated analysis of low-field brain MRI in cerebral malaria.

A central challenge of medical imaging studies is to extract biomarkers that characterize disease pathology or outcomes. Modern automated approaches have found tremendous success in high-resolution, high-quality magnetic resonance images. These methods, however, may not translate to low-resolution images acquired on magnetic resonance imaging (MRI) scanners with lower magnetic field strength. In low-resource settings where low-field scanners are more common and there is a shortage of radiologists to manually interpret MRI scans, it is critical to develop automated methods that can augment or replace manual interpretation, while accommodating reduced image quality. We present a fully automated framework for translating radiological diagnostic criteria into image-based biomarkers, inspired by a project in which children with cerebral malaria (CM) were imaged using low-field 0.35 Tesla MRI. We integrate multiatlas label fusion, which leverages high-resolution images from another sample as prior spatial information, with parametric Gaussian hidden Markov models based on image intensities, to create a robust method for determining ventricular cerebrospinal fluid volume. We also propose normalized image intensity and texture measurements to determine the loss of gray-to-white matter tissue differentiation and sulcal effacement. These integrated biomarkers have excellent classification performance for determining severe brain swelling due toCM.

Cognitive profile in idiopathic autonomic failure: relation with white matter hyperintensities and neurofilament levels.

ObjectiveTo disclose the nature of cognitive deficits in a cohort of patients with idiopathic autonomic failure (IAF) by exploring the relation among cognitive functions, cardiovascular autonomic failure (AF) and clinical progression to another α‐synucleinopathy (phenoconversion).MethodsWe retrospectively identified all patients with a clinical diagnosis of IAF who underwent a comprehensive neuropsychological evaluation, clinical examination and cardiovascular autonomic tests from the IAF‐BO cohort. Brain magnetic resonance imaging (MRI) studies and cerebrospinal fluid (CSF) analysis, including neurofilament light chain (NfL), Alzheimer disease core biomarkers, and α‐synuclein seeding activity were further evaluated when available.Correlations among cognitive functions, clinical features, cardiovascular AF, cerebral white matter hyperintensities (WMH) load, and CSF biomarkers were estimated using Spearman correlation coefficient.ResultsThirteen out of 30 (43%) patients with IAF displayed cognitive deficits (CI) mainly concerning executive functioning. Seven out of 30 (23%) met the criteria for mild cognitive impairment (MCI).The diagnosis of CI and MCI was not associated with phenoconversion or autonomic function parameters, including duration and severity of neurogenic orthostatic hypotension, presence and severity of supine hypertension, and nocturnal dipper profile.Twenty patients underwent a brain MRI and CSF analysis. MCI was related to WMH load (r = 0.549) and NfL levels (r = 0.656), while autonomic function parameters were not associated with either WMH or NfL levels.InterpretationCardiovascular AF and phenoconversion, underlying the spreading of neurodegeneration to the central nervous system, were not independent drivers of cognitive dysfunction in IAF. We identified WMH load and NfL levels as potential biomarkers of the neural network disruption associated with cognitive impairment in patients with IAF.

Quantitative Structural Brain Magnetic Resonance Imaging Analyses: Methodological Overview and Application to Rett Syndrome.

Congenital genetic disorders often present with neurological manifestations such as neurodevelopmental disorders, motor developmental retardation, epilepsy, and involuntary movement. Through qualitative morphometric evaluation of neuroimaging studies, remarkable structural abnormalities, such as lissencephaly, polymicrogyria, white matter lesions, and cortical tubers, have been identified in these disorders, while no structural abnormalities were identified in clinical settings in a large population. Recent advances in data analysis programs have led to significant progress in the quantitative analysis of anatomical structural magnetic resonance imaging (MRI) and diffusion-weighted MRI tractography, and these approaches have been used to investigate psychological and congenital genetic disorders. Evaluation of morphometric brain characteristics may contribute to the identification of neuroimaging biomarkers for early diagnosis and response evaluation in patients with congenital genetic diseases. This mini-review focuses on the methodologies and attempts employed to study Rett syndrome using quantitative structural brain MRI analyses, including voxel- and surface-based morphometry and diffusion-weighted MRI tractography. The mini-review aims to deepen our understanding of how neuroimaging studies are used to examine congenital genetic disorders.

Detection and Classification of MRI-Based Brain Tumor via Jaya Algorithm and Twin Support Vector Machine

Brain tumor detection and classification is one of the challenging tasks in the medical image application. Early detection of a brain tumor can help diagnosis and treatment of the patients. Magnetic Resonance Imaging (MRI) is widely used for the detection of brain tumor. Manual analysis of brain MRI, and classification of brain tumor is a tedious and time-consuming job. This paper introduces a novel approach to brain tumor segmentation and classification using BRATS 2015 datasets. Our system exploits the benefits of Jaya Algorithm (JA) as an optimization technique for finding multi-level thresholds to segment the tumor part from the MRI. Feature extraction is implemented by Gray Level Co-occurrence Matrix (GLCM), followed by Principal Component Analysis (PCA) for feature reduction. Due to its inherent distinct features and advantages, a machine-learning approach, Twin Support Vector Machine (TSVM) is used as a classifier. The prediction accuracy of the proposed system yielded up to 97.89 % with sensitivity 96.48%, 98.97 precision, 97.91% F1 Score, and 0.0798 MSE. The accuracy, sensitivity, F1 Score, and MSE are found comparable to the other state-of-arts machine learning methods.

Automated differentiation of Alzheimer’s condition using Kernel Density Estimation based texture analysis of single slice brain MR images

Abstract Computer-assisted tools can aid in the detection of Alzheimer disease (AD) which is a progressive neurodegenerative disorder that can lead to cognitive impairments and eventually death. The accumulated effects due to AD can cause changes in the appearance of grey matter, white matter and cerebrospinal fluid in brain Magnetic Resonance (MR) images. This study aims to use Kernel Density Estimation (KDE) technique to analyse the textural changes from single slice brain MR images for the detection of AD. The preprocessed, skull stripped T1-weighted MR brain images are obtained from the publicly available OASIS database. A single axial slice per subject is chosen from a volumetric image for further processing to reduce the computational load. Multivariate KDE technique is applied to each pixel, by considering the changes in the neighbourhood based on selected bandwidth to obtain corresponding density estimates. Statistical features quantifying the distribution of density estimates are extracted to characterise textural variations in images. Linear discriminant analysis (LDA) classifier is implemented with ten-fold cross-validation for detecting AD. An optimum bandwidth of 18 for the KDE technique is selected based on the classification performance. Out of seven extracted texture features, three are found to be statistically significant in distinguishing AD. The classification with LDA yields an accuracy of 72.3% with a sensitivity of 80.6% for identifying AD from healthy subjects. The proposed method is efficient in detecting AD by revealing the textural changes within the brain slice without the involvement of any segmentation technique. Thus, the novel KDE-based texture analysis proves to be an effective tool for the automated diagnosis of AD from single slice brain MR images.

Three-dimensional deep learning with spatial erasing for unsupervised anomaly segmentation in brain MRI

PurposeBrain Magnetic Resonance Images (MRIs) are essential for the diagnosis of neurological diseases. Recently, deep learning methods for unsupervised anomaly detection (UAD) have been proposed for the analysis of brain MRI. These methods rely on healthy brain MRIs and eliminate the requirement of pixel-wise annotated data compared to supervised deep learning. While a wide range of methods for UAD have been proposed, these methods are mostly 2D and only learn from MRI slices, disregarding that brain lesions are inherently 3D and the spatial context of MRI volumes remains unexploited.MethodsWe investigate whether using increased spatial context by using MRI volumes combined with spatial erasing leads to improved unsupervised anomaly segmentation performance compared to learning from slices. We evaluate and compare 2D variational autoencoder (VAE) to their 3D counterpart, propose 3D input erasing, and systemically study the impact of the data set size on the performance.ResultsUsing two publicly available segmentation data sets for evaluation, 3D VAEs outperform their 2D counterpart, highlighting the advantage of volumetric context. Also, our 3D erasing methods allow for further performance improvements. Our best performing 3D VAE with input erasing leads to an average DICE score of 31.40% compared to 25.76% for the 2D VAE.ConclusionsWe propose 3D deep learning methods for UAD in brain MRI combined with 3D erasing and demonstrate that 3D methods clearly outperform their 2D counterpart for anomaly segmentation. Also, our spatial erasing method allows for further performance improvements and reduces the requirement for large data sets.

Quantitative evaluation of white matter hyperintensities in patients with heart failure using an innovative magnetic resonance image analysis method: Association with disrupted circadian blood pressure variation.

White matter hyperintensities (WMHs) are risk factors for future cognitive impairment and are associated with an abnormal circadian blood pressure (BP) rhythm in patients with hypertension. However, whether this association exists in patients with heart failure (HF) is unclear. We performed a cross‐sectional study of hospitalized patients with HF who underwent ambulatory BP monitoring and brain magnetic resonance imaging (MRI). A non‐dipper BP pattern was defined as a < 10% nocturnal BP decline. WMHs on brain MRI scans were quantitated using a novel image analysis software (FUSION: FUsed Software for Imaging Of Nervous system). We enrolled 28 hospitalized patients with HF (age: 70.0 ± 9.8 years, 64.3% men). In the brain MRI analysis, the non‐dipper group had higher WMH volume (18.9 ± 19.8 vs. 7.7 ± 8.3 mL, P = .047) and percentage of WMH/total brain volume (1.31 ± 1.28% vs. 0.55 ± 0.58%, P = .04) than the dipper group. In conclusion, using the newly developed MRI analysis software, we successfully quantitatively measured the volume of WMHs and found that the WMH volume increased 2.4 times in patients with a non‐dipper pattern of nocturnal BP compared with those with a normal dipper pattern.

Deep learning of brain magnetic resonance images: A brief review.

Magnetic resonance imaging (MRI) is one of the most popular techniques in brain science and is important for understanding brain function and neuropsychiatric disorders. However, the processing and analysis of MRI is not a trivial task with lots of challenges. Recently, deep learning has shown superior performance over traditional machine learning approaches in image analysis. In this survey, we give a brief review of the recent popular deep learning approaches and their applications in brain MRI analysis. Furthermore, popular brain MRI databases and deep learning tools are also introduced. The strength and weaknesses of different approaches are addressed, and challenges as well as future directions are also discussed.

Volumetric brain magnetic resonance imaging analysis in children with obstructive sleep apnea

ObjectivesPediatric Obstructive Sleep Apnea (OSA) is associated with neurocognitive deficits. Cerebral structural alterations in the frontal cortex, cerebellum, and hippocampus have been reported in adult OSA patients. These brain areas are important for executive functioning, motor regulation of breathing, and memory function, respectively. Corresponding evidence comparing cerebral structures in pediatric OSA patients is limited. The objective of this study is to investigate MRI differences in cortical thickness and cortical volume in children with and without OSA. Study designProspective, single institutional case-control study. MethodsForty-five children were recruited at a pediatric tertiary care center (27 with OSA; mean age 9.9 ± 1.9 years, and 18 controls; mean age 10.5 ± 1.0 years). The OSA group underwent magnetic resonance imaging (MRI), polysomnography (PSG) and completed the Pediatric Daytime Sleepiness Scale (PDSS) and the Child's Sleep Habits Questionnaire (CSHQ). High-resolution T1-weighted MRI was utilized to examine cortical thickness and gray and white matter volume in children with OSA compared to a healthy group of demographically-comparable children without OSA selected from a pre-existing MRI dataset. ResultsChildren with OSA showed multiple regions of cortical thinning primarily in the left hemisphere. Reduced gray matter (GM) volume was noted in the OSA group in multiple frontal regions of the left hemisphere (superior frontal, rostral medial frontal, and caudal medial frontal regions). Reduced white matter (WM) volume in both the left and right hemisphere was observed in regions of the frontal, parietal, and occipital lobes in children with OSA. ConclusionThis study noted differences in cortical thickness and GM and WM regional brain volumes in children with OSA. These findings are consistent with other pediatric studies, which also report differences between healthy children and those with OSA. We found that the severity of OSA does not correlate with the extent of MRI alterations.

TSC2 pathogenic variants are predictive of severe clinical manifestations in TSC infants: results of the EPISTOP study

To perform comprehensive genotyping of TSC1 and TSC2 in a cohort of 94 infants with tuberous sclerosis complex (TSC) and correlate with clinical manifestations. Infants were enrolled at age <4 months, and subject to intensive clinical monitoring including electroencephalography (EEG), brain magnetic resonance imaging (MRI), and neuropsychological assessment. Targeted massively parallel sequencing (MPS), genome sequencing, and multiplex ligation-dependent probe amplification (MLPA) were used for variant detection in TSC1/TSC2. Pathogenic variants in TSC1 or TSC2 were identified in 93 of 94 (99%) subjects, with 23 in TSC1 and 70 in TSC2. Nine (10%) subjects had mosaicism. Eight of 24 clinical features assessed at age 2 years were significantly less frequent in those with TSC1 versus TSC2 variants including cortical tubers, hypomelanotic macules, facial angiofibroma, renal cysts, drug-resistant epilepsy, developmental delay, subependymal giant cell astrocytoma, and median seizure-free survival. Additionally, quantitative brain MRI analysis showed a marked difference in tuber and subependymal nodule/giant cell astrocytoma volume for TSC1 versus TSC2. TSC2 pathogenic variants are associated with a more severe clinical phenotype than mosaic TSC2 or TSC1 variants in TSC infants. Early assessment of gene variant status and mosaicism might have benefit for clinical management in infants and young children with TSC.