Magnetic Resonance Imaging Modalities Research Articles

Referrals for Pediatric Appendicitis to a Tertiary Care Children's Hospital.

This study aimed to analyze pediatric referrals for definite or possible appendicitis, to compare clinical predictors and laboratory values between patients with and without a final diagnosis of appendicitis, and to determine the accuracy of prereferral diagnostic interpretations of computed tomography scans, ultrasound, and magnetic resonance imaging modalities. We conducted a retrospective analysis of pediatric patients referred from 2015 to 2019 to a tertiary care children's emergency department with definitive or possible appendicitis. Data abstracted included patient demographics, clinical symptoms, physical examination findings, laboratory results, and diagnostic imaging findings (by the referring center and the pediatric radiologist at the accepting center). An Alvarado and Appendicitis Inflammatory Response (AIR) score was calculated for each patient. Analysis was performed on 381 patients; 226 (59%) had a final diagnosis of appendicitis. Patients with appendicitis were more likely to have symptoms of nausea ( P < 0.0001) and vomiting ( P < 0.0001), have a higher mean temperature ( P = 0.025), right lower quadrant abdominal pain to palpation ( P = <0.0001), rebound tenderness ( P < 0.0001), a higher mean Alvarado score [5.35 vs 3.45 ( P < 0.0001)], and a higher mean AIR score [4.02 vs 2.17 ( P < 0.0001)]. Of the 97 diagnostic images initially interpreted as appendicitis by the referring center, 10 (10.3%) were read as no evidence of appendicitis. Of the 62 diagnostic images initially interpreted as "possible appendicitis" by the referring center, 34 (54.8%) were read as no evidence of appendicitis. Of those diagnostic images initially interpreted as "appendicitis" or "possible appendicitis" by the referring center, 24/89 (27.0%) of computed tomography scans, 17/62 (27.4%) of ultrasounds, and 3/8 (37.5%) of magnetic resonance imaging results were read as no evidence of appendicitis. Usage of established scoring algorithms, such as Alvarado and AIR, may decrease the unnecessary cost of diagnostic imaging and transfer to tertiary care. Virtual radiology consultations may be 1 potential solution to improve the referral process for pediatric appendicitis if initial interpretation is uncertain.

Brain Magnetic Resonance Imaging (MRI) in Spinal Muscular Atrophy: A Scoping Review.

5q Spinal Muscular Atrophy (SMA) is a prototypical lower motor neuron disorder. However, the characteristic early motor impairment raises the question on the scope of brain involvement with implications for further investigations on the brain as a potential therapeutic target. To review changes across the SMA clinical spectrum reported on brain magnetic resonance imaging (MRI). We conducted a scoping review of existing literature on PubMed and EMBASE. Two reviewers searched and retrieved relevant articles on magnetic resonance brain imaging in individuals with SMA censoring to April 2022. Full-text articles published in peer-reviewed journals or abstracts accepted to conferences in English and French were included. Twelve articles were identified describing a total of 39 patients [age range: 11 days to 41 years old, type 0 (n = 5), type 1 (n = 4), type 2 (n = 2), type 3 (n = 22), type 4 (n = 6)]. All reported structural changes and did not explore other MRI modalities. In individuals with infantile onset SMA, cortical and subcortical brain abnormalities in white matter, basal ganglia, thalamus, hippocampus, and high intensity areas around lateral ventricles and thalami were reported over time. In individuals with later-onset SMA, reduced cerebellar and lobular volume were observed as well as increased grey matter density in motor areas. Limited data on brain imaging in SMA highlights both cortical and subcortical involvement in SMA, supporting the hypothesis that changes are not restricted to lower motor neuron pathways. Further studies are needed to determine the extent and prevalence of structural and functional brain changes across SMA types.

Percutaneous Superimposed O-Arm-MRI-Navigated Biopsy for Spinal Column Pathologies.

Classifying spinal tumors can be challenging due to nonspecific clinical and radiological qualities, and a precise biopsy is crucial for an accurate diagnosis and treatment planning. This study aimed to enhance the accuracy and efficiency of spinal biopsies integrating Cone Beam Computed Tomography (CBCT) and magnetic resonance imaging (MRI) modalities using an O-arm CT navigation system. Eighteen patients with different spinal lesions underwent 18 biopsies following the Stealth Station navigation system Spine 8 protocol. Preoperative MRI scans were merged with intraoperative CT navigation systems for continuous monitoring during the biopsy process. The combined imaging technique accurately identified the diseased lesion type in all biopsies, demonstrating 100% sensitivity and specificity. In conclusion, combining MRI and CT imaging modalities significantly improved spinal biopsy accuracy and efficiency, differentiating between pathological entities. However, large-scale studies are desired to validate these findings and investigate potential benefits in different clinical scenarios. Although this method requires general anesthesia, its potential profits in avoiding misdiagnosed lesions and decreasing the need for further invasive procedures make it a promising approach for improving spinal biopsy accuracy and efficiency.

Ensemble method employing quantitative biomarkers and deep learning approach from structural magnetic resonance imaging to diagnose Alzheimer’s disease

Abstract Introduction: Alzheimer’s disease (AD) is a neurodegenerative condition that impairs activities of daily living and sharply declines gross cognitive ability. Over 152 million individuals worldwide will live with the dreaded consequence of a longer lifespan by the year 2050, making it a pressing public health issue. Magnetic resonance imaging (MRI) provides excellent soft tissue contrast and helps image the brain in vivo, non-invasively. Aims and Objectives: To summarize AD’s anatomical, physiological, and pathophysiological changes and derivation of quantifiable biomarkers from MRI to develop artificial intelligence (AI) based computer-aided detection (CAD) system to classify subjects among AD, mild cognitive impairment (MCI), and cognitively normal (CN). Materials and Methods: This retrospective study uses clinical and standardized, pre-processed, quality-controlled, and quality-checked—structural MRI imaging (diagnosed/labeled) data of 1069 subjects, age, gender, and class matched, taken from Alzheimer’s disease neuroimaging initiative. A pipeline is developed to get quantified biomarkers from the assessment of (1) cortical thickness, (2) volumetric segmentation for whole brain volumes, and (3) region of interest (ROI) areas most affected in AD. A gradient boosting method is used to predict class labels. The second approach implements a convolution neural network (CNN) model comprising 3D ROI. Results: Implemented CAD system using an ensemble gradient boosting approach has demonstrated good receiver operating characteristics characteristic and yielded balanced accuracy (BA) of 82.31%, 78.52%, and 72.73%, and the CNN approach has given better results 88.44%, 82.96%, and 74.34% for classification task AD versus CN, AD versus MCI, and MCI versus CN, respectively. Conclusion: This study has used a substantially large dataset of 1069 subjects. The deep learning-based efficient and optimal CNN model has used significantly large ROI-based 3-Dimentional volume, resulting in impressive performance improvements over comparable methods. The CNN model had given higher accuracy (6.13% for AD vs. CN, 4.44% for AD vs. MCI and 1.61% for MCI vs. CN) over gradient boosting, as the model uses significantly large ROI-based 3D brain volume and an inherent capability of it in learning most discriminative features automatically. However, quantitative biomarkers derived from brain morphometry, which accesses structural changes, yield reasonable estimates over pathophysiological alterations across the brain and augment a clinician with insightful and a holistic view, resulting in higher confidence over predicated class label by CNN and is a step closer to explainable AI. Accuracy for MCI versus CN drops as these classes share similar features and characteristics and can be improved by integrating biomarkers from other MRI modalities.

Emotional Regulation and Adolescent Concussion: Overview and Role of Neuroimaging.

Emotional dysregulation symptoms following a concussion are associated with an increased risk for emotional dysregulation disorders (e.g., depression and anxiety), especially in adolescents. However, predicting the emergence or worsening of emotional dysregulation symptoms after concussion and the extent to which this predates the onset of subsequent psychiatric morbidity after injury remains challenging. Although advanced neuroimaging techniques, such as functional magnetic resonance imaging and diffusion magnetic resonance imaging, have been used to detect and monitor concussion-related brain abnormalities in research settings, their clinical utility remains limited. In this narrative review, we have performed a comprehensive search of the available literature regarding emotional regulation, adolescent concussion, and advanced neuroimaging techniques in electronic databases (PubMed, Scopus, and Google Scholar). We highlight clinical evidence showing the heightened susceptibility of adolescents to experiencing emotional dysregulation symptoms following a concussion. Furthermore, we describe and provide empirical support for widely used magnetic resonance imaging modalities (i.e., functional and diffusion imaging), which are utilized to detect abnormalities in circuits responsible for emotional regulation. Additionally, we assess how these abnormalities relate to the emotional dysregulation symptoms often reported by adolescents post-injury. Yet, it remains to be determined if a progression of concussion-related abnormalities exists, especially in brain regions that undergo significant developmental changes during adolescence. We conclude that neuroimaging techniques hold potential as clinically useful tools for predicting and, ultimately, monitoring the treatment response to emotional dysregulation in adolescents following a concussion.

Role of Artificial Intelligence for Autism Diagnosis Using DTI and fMRI: A Survey.

Autism spectrum disorder (ASD) is a wide range of diseases characterized by difficulties with social skills, repetitive activities, speech, and nonverbal communication. The Centers for Disease Control (CDC) estimates that 1 in 44 American children currently suffer from ASD. The current gold standard for ASD diagnosis is based on behavior observational tests by clinicians, which suffer from being subjective and time-consuming and afford only late detection (a child must have a mental age of at least two to apply for an observation report). Alternatively, brain imaging-more specifically, magnetic resonance imaging (MRI)-has proven its ability to assist in fast, objective, and early ASD diagnosis and detection. With the recent advances in artificial intelligence (AI) and machine learning (ML) techniques, sufficient tools have been developed for both automated ASD diagnosis and early detection. More recently, the development of deep learning (DL), a young subfield of AI based on artificial neural networks (ANNs), has successfully enabled the processing of brain MRI data with improved ASD diagnostic abilities. This survey focuses on the role of AI in autism diagnostics and detection based on two basic MRI modalities: diffusion tensor imaging (DTI) and functional MRI (fMRI). In addition, the survey outlines the basic findings of DTI and fMRI in autism. Furthermore, recent techniques for ASD detection using DTI and fMRI are summarized and discussed. Finally, emerging tendencies are described. The results of this study show how useful AI is for early, subjective ASD detection and diagnosis. More AI solutions that have the potential to be used in healthcare settings will be introduced in the future.

Brain Tumor Class Detection in Flair/T2 Modality MRI Slices Using Elephant-Herd Algorithm Optimized Features.

Several advances in computing facilities were made due to the advancement of science and technology, including the implementation of automation in multi-specialty hospitals. This research aims to develop an efficient deep-learning-based brain-tumor (BT) detection scheme to detect the tumor in FLAIR- and T2-modality magnetic-resonance-imaging (MRI) slices. MRI slices of the axial-plane brain are used to test and verify the scheme. The reliability of the developed scheme is also verified through clinically collected MRI slices. In the proposed scheme, the following stages are involved: (i) pre-processing the raw MRI image, (ii) deep-feature extraction using pretrained schemes, (iii) watershed-algorithm-based BT segmentation and mining the shape features, (iv) feature optimization using the elephant-herding algorithm (EHA), and (v) binary classification and verification using three-fold cross-validation. Using (a) individual features, (b) dual deep features, and (c) integrated features, the BT-classification task is accomplished in this study. Each experiment is conducted separately on the chosen BRATS and TCIA benchmark MRI slices. This research indicates that the integrated feature-based scheme helps to achieve a classification accuracy of 99.6667% when a support-vector-machine (SVM) classifier is considered. Further, the performance of this scheme is verified using noise-attacked MRI slices, and better classification results are achieved.

Multimodality MRI synchronous construction based deep learning framework for MRI-guided radiotherapy synthetic CT generation

Synthesizing computed tomography (CT) images from magnetic resonance imaging (MRI) data can provide the necessary electron density information for accurate dose calculation in the treatment planning of MRI-guided radiation therapy (MRIgRT). Inputting multimodality MRI data can provide sufficient information for accurate CT synthesis: however, obtaining the necessary number of MRI modalities is clinically expensive and time-consuming. In this study, we propose a multimodality MRI synchronous construction based deep learning framework from a single T1-weight (T1) image for MRIgRT synthetic CT (sCT) image generation. The network is mainly based on a generative adversarial network with sequential subtasks of intermediately generating synthetic MRIs and jointly generating the sCT image from the single T1 MRI. It contains a multitask generator and a multibranch discriminator, where the generator consists of a shared encoder and a splitted multibranch decoder. Specific attention modules are designed within the generator for feasible high-dimensional feature representation and fusion. Fifty patients with nasopharyngeal carcinoma who had undergone radiotherapy and had CT and sufficient MRI modalities scanned (5550 image slices for each modality) were used in the experiment. Results showed that our proposed network outperforms state-of-the-art sCT generation methods well with the least MAE, NRMSE, and comparable PSNR and SSIM index measure. Our proposed network exhibits comparable or even superior performance than the multimodality MRI-based generation method although it only takes a single T1 MRI image as input, thereby providing a more effective and economic solution for the laborious and high-cost generation of sCT images in clinical applications.

Incidental demyelination in magnetic resonance imaging and 10-year risk of multiple sclerosis: A data lake cohort study.

There is an absence of data from large population-based cohort studies on the incidence of radiologically isolated syndrome (RIS). The incidence of RIS and the subsequent risk for multiple sclerosis (MS) were investigated. A population-based, retrospective cohort study was conducted using a data-lake-based analysis of digitalized radiology reports. All brain and spinal cord magnetic resonance imaging (MRI) in people aged 16-70 during the years 2005-2010 (n = 102,224) were screened using optimized search terms to detect cases with RIS. The subjects with RIS were followed up until January 2022. The cumulative incidence of RIS was 0.03% when all MRI modalities were included and 0.06% when only brain MRI was included according to MAGNIMS 2018 recommendation criteria. With the Okuda 2009 criteria, the respective figures were 0.03% and 0.05% (86% concordance). The overall risk for MS after RIS was similar, 32% by using the MAGNIMS and 32% by using the Okuda definition of RIS. Individuals aged <35.5 years exhibited the most significant predisposition to MS (80%), whilst those >35.5 years had less than 10% risk of MS. MS diagnosed after RIS constituted 0.8% of the incident MS cases in the population during 2005-2010. A population-wide context was provided for the incidence of RIS and its relationship to MS. MAGNIMS recommendations were only slightly more sensitive to detect RIS compared to the Okuda criteria. RIS has a subtle effect on the overall incidence of MS, yet the risk for MS in individuals under the age of 35.5 years is substantial.

Discriminant Efficacy of mpMRI for Variant Pathology Associated with Prostate Adenocarcinoma.

Purpose - Implementation of multiparametric magnetic resonance imaging (mpMRI) for prostate adenocarcinoma's variant pathology requires awareness. The aim of this retrospective study was to investigate the discriminant efficacy of multiparametric magnetic resonance imaging modality for variant pathology associated with prostate adenocarcinoma. Methods - Consecutive 247 prostate cancer patients who underwent radical prostatectomy in our university-based hospital between October 2014 and October 2019, were retrospectively reviewed. Data of mpMRI-associated contrast enhancements, T2 signals, apparent diffusion coefficients (ADC), ages and PSA values were compared. Clinical and demographic data of patients were noted including associated variant pathologies and reports of preoperative mpMRI images. Results - Among the patients, 63 (26%) had variant pathology and 14 (22%) had mpMRI before primary prostate biopsy. The group with variant pathology and the control group had similar perfusion curves and increased contrast when compared for mpMRI parameters, but different ADC values for each of the adjusted b-values for 400, 800 and 1400. Conclusion - Our study demonstrates that mpMRI appears to have no role in distinguishing rare variant pathologies associated with prostate adenocarcinoma despite different ADC values.

An anatomy-aware framework for automatic segmentation of parotid tumor from multimodal MRI

Magnetic Resonance Imaging (MRI) plays an important role in diagnosing the parotid tumor, where accurate segmentation of tumors is highly desired for determining appropriate treatment plans and avoiding unnecessary surgery. However, the task remains nontrivial and challenging due to ambiguous boundaries and various sizes of the tumor, as well as the presence of a large number of anatomical structures around the parotid gland that are similar to the tumor. To overcome these problems, we propose a novel anatomy-aware framework for automatic segmentation of parotid tumors from multimodal MRI. First, a Transformer-based multimodal fusion network PT-Net is proposed in this paper. The encoder of PT-Net extracts and fuses contextual information from three modalities of MRI from coarse to fine, to obtain cross-modality and multi-scale tumor information. The decoder stacks the feature maps of different modalities and calibrates the multimodal information using the channel attention mechanism. Second, considering that the segmentation model is prone to be disturbed by similar anatomical structures and make wrong predictions, we design anatomy-aware loss. By calculating the distance between the activation regions of the prediction segmentation and the ground truth, our loss function forces the model to distinguish similar anatomical structures with the tumor and make correct predictions. Extensive experiments with MRI scans of the parotid tumor showed that our PT-Net achieved higher segmentation accuracy than existing networks. The anatomy-aware loss outperformed state-of-the-art loss functions for parotid tumor segmentation. Our framework can potentially improve the quality of preoperative diagnosis and surgery planning of parotid tumors.

A structural magnetic resonance imaging review of clinical motor outcomes from deep brain stimulation in movement disorders.

Patients with movement disorders treated by deep brain stimulation do not always achieve successful therapeutic alleviation of motor symptoms, even in cases where surgery is without complications. Magnetic resonance imaging (MRI) offers methods to investigate structural brain-related factors that may be predictive of clinical motor outcomes. This review aimed to identify features which have been associated with variability in clinical post-operative motor outcomes in patients with Parkinson's disease, dystonia, and essential tremor from structural MRI modalities. We performed a literature search for articles published between 1 January 2000 and 1 April 2022 and identified 5197 articles. Following screening through our inclusion criteria, we identified 60 total studies (39 = Parkinson's disease, 11 = dystonia syndromes and 10 = essential tremor). The review captured a range of structural MRI methods and analysis techniques used to identify factors related to clinical post-operative motor outcomes from deep brain stimulation. Morphometric markers, including volume and cortical thickness were commonly identified in studies focused on patients with Parkinson's disease and dystonia syndromes. Reduced metrics in basal ganglia, sensorimotor and frontal regions showed frequent associations with reduced motor outcomes. Increased structural connectivity to subcortical nuclei, sensorimotor and frontal regions was also associated with greater motor outcomes. In patients with tremor, increased structural connectivity to the cerebellum and cortical motor regions showed high prevalence across studies for greater clinical motor outcomes. In addition, we highlight conceptual issues for studies assessing clinical response with structural MRI and discuss future approaches towards optimizing individualized therapeutic benefits. Although quantitative MRI markers are in their infancy for clinical purposes in movement disorder treatments, structural features obtained from MRI offer the powerful potential to identify candidates who are more likely to benefit from deep brain stimulation and provide insight into the complexity of disorder pathophysiology.

Radiological Biomarkers for Brain Metastases Prognosis: Quantitative Magnetic Resonance Imaging (MRI) Modalities As Non-invasive Biomarkers for the Effect of Radiotherapy.

Radiotherapy effect is achieved by its ability to cause DNA damage and induce apoptosis. In contrast, radiation can induce tumor cells' proliferation, invasiveness, and epithelial-mesenchymal transition (EMT). Besides developing radioresistance, this paradoxical effect of radiotherapy is considered a challenging problem in the field of radiotherapy. This highlights the importance of developing new modalities to diagnose radioresistance early to avoid any unnecessary exposure to radiation and differentiate between metastases recurrence versus post-radiation changes. Quantitative magnetic resonance imaging (MRI) techniques including diffusion-weighted imaging (DWI), dynamic susceptibility contrast (DSC), arterial spin labeling (ASL), and dynamic contrast-enhanced (DCE) represent potential biomarkers to diagnose metastases recurrence and radioresistance. In this review, we will focus on recent studies discussing the possibility of using DWI, DSC, ASL, and DCE to diagnose radioresistance and recurrence in patients with brain metastases.

Artificial intelligence for diffusion MRI-based tissue microstructure estimation in the human brain: an overview.

Artificial intelligence (AI) has made significant advances in the field of diffusion magnetic resonance imaging (dMRI) and other neuroimaging modalities. These techniques have been applied to various areas such as image reconstruction, denoising, detecting and removing artifacts, segmentation, tissue microstructure modeling, brain connectivity analysis, and diagnosis support. State-of-the-art AI algorithms have the potential to leverage optimization techniques in dMRI to advance sensitivity and inference through biophysical models. While the use of AI in brain microstructures has the potential to revolutionize the way we study the brain and understand brain disorders, we need to be aware of the pitfalls and emerging best practices that can further advance this field. Additionally, since dMRI scans rely on sampling of the q-space geometry, it leaves room for creativity in data engineering in such a way that it maximizes the prior inference. Utilization of the inherent geometry has been shown to improve general inference quality and might be more reliable in identifying pathological differences. We acknowledge and classify AI-based approaches for dMRI using these unifying characteristics. This article also highlighted and reviewed general practices and pitfalls involving tissue microstructure estimation through data-driven techniques and provided directions for building on them.

Vision for Ratiometric Nanoprobes: In Vivo Noninvasive Visualization and Readout of Physiological Hallmarks.

Lesion areas are distinguished from normal tissues surrounding them by distinct physiological characteristics. These features serve as biological hallmarks with which targeted biomedical imaging of the lesion sites can be achieved. Although tremendous efforts have been devoted to providing smart imaging probes with the capability of visualizing the physiological hallmarks at the molecular level, the majority of them are merely able to derive anatomical information from the tissues of interest, and thus are not suitable for taking part in in vivo quantification of the biomarkers. Recent advances in chemical construction of advanced ratiometric nanoprobes (RNPs) have enabled a horizon for quantitatively monitoring the biological abnormalities in vivo. In contrast to the conventional probes whose dependency of output on single-signal profiles restricts them from taking part in quantitative practices, RNPs are designed to provide information in two channels, affording a self-calibration opportunity to exclude the analyte-independent factors from the outputs and address the issue. Most of the conventional RNPs have encountered several challenges regarding the reliability and sufficiency of the obtained data for high-performance imaging. In this Review, we have summarized the recent progresses in developing highly advanced RNPs with the capabilities of deriving maximized information from the lesion areas of interest as well as adapting themselves to the complex biological systems in order to minimize microenvironmental-induced falsified signals. To provide a better outlook on the current advanced RNPs, nanoprobes based on optical, photoacoustic, and magnetic resonance imaging modalities for visualizing a wide range of analytes such as pH, reactive species, and different derivations of amino acids have been included. Furthermore, the physicochemical properties of the RNPs, the major constituents of the nanosystems and the analyte recognition mechanisms have been introduced. Moreover, the alterations in the values of the ratiometric signal in response to the analyte of interest as well as the time at which the highest value is achieved, have been included for most of RNPs discussed in this Review. Finally, the challenges as well as future perspectives in the field are discussed.

Normative Modeling using Multimodal Variational Autoencoders to Identify Abnormal Brain Volume Deviations in Alzheimer's Disease.

Normative modelling is a method for understanding the underlying heterogeneity within brain disorders like Alzheimer Disease (AD), by quantifying how each patient deviates from the expected normative pattern that has been learned from a healthy control distribution. Existing deep learning based normative models have been applied on only single modality Magnetic Resonance Imaging (MRI) neuroimaging data. However, these do not take into account the complementary information offered by multimodal M RI, which is essential for understanding a multifactorial disease like AD. To address this limitation, we propose a multi-modal variational autoencoder (mmVAE) based normative modelling framework that can capture the joint distribution between different modalities to identify abnormal brain volume deviations due to AD. Our multi-modal framework takes as input Freesurfer processed brain region volumes from T1-weighted (cortical and subcortical) and T2-weighed (hippocampal) scans of cognitively normal participants to learn the morphological characteristics of the healthy brain. The estimated normative model is then applied on AD patients to quantify the deviation in brain volumes and identify abnormal brain pattern deviations due to the progressive stages of AD. We compared our proposed mmVAE with a baseline unimodal VAE having a single encoder and decoder and the two modalities concatenated as unimodal input. Our experimental results show that deviation maps generated by mmVAE are more sensitive to disease staging within AD, have a better correlation with patient cognition and result in higher number of brain regions with statistically significant deviations compared to the unimodal baseline model.

A review of multi-modal magnetic resonance imaging studies on perimenopausal brain: a hint towards neural heterogeneity.

The population ageing process worldwide is leading to an increasing number of women in the perimenopausal phase. Many of the perimenopausal symptoms, such as headache, depression, insomnia, and cognitive decline, are neurological in nature. Therefore, the study of the perimenopausal brain is of great importance. In addition, relevant studies can also provide an imaging basis for multiple therapies to treat perimenopausal symptoms. Because of its non-invasive nature, magnetic resonance imaging (MRI) has now been widely applied to the study of perimenopausal brains, revealing alterations in the brain associated with symptoms during the menopause transition. In this review, we collected papers and works of literature on the perimenopausal brain using MRI techniques in the Web of Science database. We firstly described the general principles and analysis methods of different MRI modalities briefly and then reviewed the structural, functional, perfusion, and metabolic compounds changes in the brain of perimenopausal women respectively, and described the latest advances inprobing the perimenopausal brain using MRI, resulting in summary diagrams and figures. Based on the summary of existing works of the literature, this review further provided a perspective on multi-modal MRI studies in the perimenopausal brain, suggesting that population-based, multi-center, and longitudinal studies will be beneficial to the comprehensive understanding of changes in the perimenopausal brain. In addition, we found a hint towards neural heterogeneity in the perimenopausal brain, which should be addressed by future MRI studies to provide more help for the precise diagnosis and personalized treatment of perimenopausal symptoms. KEY POINTS: • Perimenopause is not only a physiological transition but also a period of neurological transition. • Multi-modal MRI studies have revealed that perimenopause is accompanied by alterations in the brain, which is implicated in many perimenopausal symptoms. • The diversity in the multi-modal MRI findings may give a hint to neural heterogeneity in the perimenopausal brain.

RU-Net: skull stripping in rat brain MR images after ischemic stroke with rat U-Net

BackgroundExperimental ischemic stroke models play a fundamental role in interpreting the mechanism of cerebral ischemia and appraising the development of pathological extent. An accurate and automatic skull stripping tool for rat brain image volumes with magnetic resonance imaging (MRI) are crucial in experimental stroke analysis. Due to the deficiency of reliable rat brain segmentation methods and motivated by the demand for preclinical studies, this paper develops a new skull stripping algorithm to extract the rat brain region in MR images after stroke, which is named Rat U-Net (RU-Net).MethodsBased on a U-shape like deep learning architecture, the proposed framework integrates batch normalization with the residual network to achieve efficient end-to-end segmentation. A pooling index transmission mechanism between the encoder and decoder is exploited to reinforce the spatial correlation. Two different modalities of diffusion-weighted imaging (DWI) and T2-weighted MRI (T2WI) corresponding to two in-house datasets with each consisting of 55 subjects were employed to evaluate the performance of the proposed RU-Net.ResultsExtensive experiments indicated great segmentation accuracy across diversified rat brain MR images. It was suggested that our rat skull stripping network outperformed several state-of-the-art methods and achieved the highest average Dice scores of 98.04% (p < 0.001) and 97.67% (p < 0.001) in the DWI and T2WI image datasets, respectively.ConclusionThe proposed RU-Net is believed to be potential for advancing preclinical stroke investigation and providing an efficient tool for pathological rat brain image extraction, where accurate segmentation of the rat brain region is fundamental.

Alzheimer's disease classification using competitive swarm multi‐verse optimizer‐based deep neuro‐fuzzy network

SummaryClassification of Alzheimer's disease (AD) from neuroimaging, like magnetic resonance imaging (MRI) through deep learning classifier has been increasing in research in recent decades. However, it is required for enhancing the accuracy of the AD classification for effective treatment. In this work, an efficient model termed competitive swarm multi‐verse optimizer + deep neuro‐fuzzy network (CSMVO + DNFN) is designed to accurately classify stages of AD. Preprocessing is done with a median filter. Then, the resulting image is segmented to find the interested regions by channel‐wise feature pyramid network module (CFPNet‐M). Some features obtained from the segmented image are haralick, convolutional neural network, and texture features. The devised method is more efficient in classifying different stages of AD with MRI modality. Furthermore, the developed model attained higher performance using metrics like the accuracy of 89.9%, sensitivity of 89.6%, and specificity of 87.0% based on the k‐fold value.

Machine Learning for Brain MRI Data Harmonisation: A Systematic Review.

Magnetic Resonance Imaging (MRI) data collected from multiple centres can be heterogeneous due to factors such as the scanner used and the site location. To reduce this heterogeneity, the data needs to be harmonised. In recent years, machine learning (ML) has been used to solve different types of problems related to MRI data, showing great promise. This study explores how well various ML algorithms perform in harmonising MRI data, both implicitly and explicitly, by summarising the findings in relevant peer-reviewed articles. Furthermore, it provides guidelines for the use of current methods and identifies potential future research directions. This review covers articles published through PubMed, Web of Science, and IEEE databases through June 2022. Data from studies were analysed based on the criteria of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). Quality assessment questions were derived to assess the quality of the included publications. a total of 41 articles published between 2015 and 2022 were identified and analysed. In the review, MRI data has been found to be harmonised either in an implicit (n = 21) or an explicit (n = 20) way. Three MRI modalities were identified: structural MRI (n = 28), diffusion MRI (n = 7) and functional MRI (n = 6). Various ML techniques have been employed to harmonise different types of MRI data. There is currently a lack of consistent evaluation methods and metrics used across studies, and it is recommended that the issue be addressed in future studies. Harmonisation of MRI data using ML shows promises in improving performance for ML downstream tasks, while caution should be exercised when using ML-harmonised data for direct interpretation.