Quantifying deep grey matter atrophy using automated segmentation approaches: A systematic review of structural MRI studies

Unsupervised model for structure segmentation applied to brain computed tomography

This article presents an unsupervised method for segmenting brain computed tomography scans. The proposed methodology involves image feature extraction and application of similarity and continuity constraints to generate segmentation maps of the anatomical head structures. Specifically designed for real-world datasets, this approach applies a spatial continuity scoring function tailored to the desired number of structures. The primary objective is to assist medical experts in diagnosis by identifying regions with specific abnormalities. Results indicate a simplified and accessible solution, reducing computational effort, training time, and financial costs. Moreover, the method presents potential for expediting the interpretation of abnormal scans, thereby impacting clinical practice. This proposed approach might serve as a practical tool for segmenting brain computed tomography scans, and make a significant contribution to the analysis of medical images in both research and clinical settings.

Alterations in subcortical magnetic susceptibility and disease-specific relationship with brain volume in major depressive disorder and schizophrenia

Quantitative susceptibility mapping is a magnetic resonance imaging technique that measures brain tissues' magnetic susceptibility, including iron deposition and myelination. This study examines the relationship between subcortical volume and magnetic susceptibility and determines specific differences in these measures among patients with major depressive disorder (MDD), patients with schizophrenia, and healthy controls (HCs). This was a cross-sectional study. Sex- and age- matched patients with MDD (n = 49), patients with schizophrenia (n = 24), and HCs (n = 50) were included. Magnetic resonance imaging was conducted using quantitative susceptibility mapping and T1-weighted imaging to measure subcortical susceptibility and volume. The acquired brain measurements were compared among groups using analyses of variance and post hoc comparisons. Finally, a general linear model examined the susceptibility-volume relationship. Significant group-level differences were found in the magnetic susceptibility of the nucleus accumbens and amygdala (p = 0.045). Post-hoc analyses indicated that the magnetic susceptibility of the nucleus accumbens and amygdala for the MDD group was significantly higher than that for the HC group (p = 0.0054, p = 0.0065, respectively). However, no significant differences in subcortical volume were found between the groups. The general linear model indicated a significant interaction between group and volume for the nucleus accumbens in MDD group but not schizophrenia or HC groups. This study showed susceptibility alterations in the nucleus accumbens and amygdala in MDD patients. A significant relationship was observed between subcortical susceptibility and volume in the MDD group's nucleus accumbens, which indicated abnormalities in myelination and the dopaminergic system related to iron deposition.

Quantitative susceptibility mapping using multi-channel convolutional neural networks with dipole-adaptive multi-frequency inputs

Quantitative susceptibility mapping (QSM) quantifies the distribution of magnetic susceptibility and shows great potential in assessing tissue contents such as iron, myelin, and calcium in numerous brain diseases. The accuracy of QSM reconstruction was challenged by an ill-posed field-to-susceptibility inversion problem, which is related to the impaired information near the zero-frequency response of the dipole kernel. Recently, deep learning methods demonstrated great capability in improving the accuracy and efficiency of QSM reconstruction. However, the construction of neural networks in most deep learning-based QSM methods did not take the intrinsic nature of the dipole kernel into account. In this study, we propose a dipole kernel-adaptive multi-channel convolutional neural network (DIAM-CNN) method for the dipole inversion problem in QSM. DIAM-CNN first divided the original tissue field into high-fidelity and low-fidelity components by thresholding the dipole kernel in the frequency domain, and it then inputs the two components as additional channels into a multichannel 3D Unet. QSM maps from the calculation of susceptibility through multiple orientation sampling (COSMOS) were used as training labels and evaluation reference. DIAM-CNN was compared with two conventional model-based methods [morphology enabled dipole inversion (MEDI) and improved sparse linear equation and least squares (iLSQR) and one deep learning method (QSMnet)]. High-frequency error norm (HFEN), peak signal-to-noise-ratio (PSNR), normalized root mean squared error (NRMSE), and the structural similarity index (SSIM) were reported for quantitative comparisons. Experiments on healthy volunteers demonstrated that the DIAM-CNN results had superior image quality to those of the MEDI, iLSQR, or QSMnet results. Experiments on data with simulated hemorrhagic lesions demonstrated that DIAM-CNN produced fewer shadow artifacts around the bleeding lesion than the compared methods. This study demonstrates that the incorporation of dipole-related knowledge into the network construction has a potential to improve deep learning-based QSM reconstruction.

Age-dependent changes in brain iron deposition and volume in deep gray matter nuclei using quantitative susceptibility mapping

BACKGROUND

Microstructural changes in deep gray matter (DGM) nuclei are related to physiological behavior, cognition, and memory. Therefore, it is critical to study age-dependent trajectories of biomarkers in DGM nuclei for understanding brain development and aging, as well as predicting cognitive or neurodegenerative diseases.

OBJECTIVES

We aimed to (1) characterize age-dependent trajectories of mean susceptibility, adjusted volume, and total iron content simultaneously in DGM nuclei using quantitative susceptibility mapping (QSM); (2) examine potential contributions of sex related effects to the different age-dependence trajectories of volume and iron deposition; and (3) evaluate the ability of brain age prediction by combining mean magnetic susceptibility and volume of DGM nuclei.

METHODS

Magnetic susceptibilities and volumetric values of DGM nuclei were obtained from 220 healthy participants (aged 10-70 years) scanned on a 3T MRI system. Regions of interest (ROIs) were drawn manually on the QSM images. Univariate regression analysis between age and each of the MRI measurements in a single ROI was performed. Pearson correlation coefficients were calculated between magnetic susceptibility and adjusted volume in a single ROI. The statistical significance of sex differences in age-dependent trajectories of magnetic susceptibilities and adjusted volumes were determined using one-way ANCOVA. Multiple regression analysis was used to evaluate the ability to estimate brain age using a combination of the mean susceptibilities and adjusted volumes in multiple DGM nuclei.

RESULTS

Mean susceptibility and total iron content increased linearly, quadratically, or exponentially with age in all six DGM nuclei. Negative linear correlation was observed between adjusted volume and age in the head of the caudate nucleus (CN; R² = 0.196, p < 0.001). Quadratic relationships were found between adjusted volume and age in the putamen (PUT; R² = 0.335, p < 0.001), globus pallidus (GP; R² = 0.062, p = 0.001), and dentate nucleus (DN; R² = 0.077, p < 0.001). Males had higher mean magnetic susceptibility than females in the PUT (p = 0.001), red nucleus (RN; p = 0.002), and substantia nigra (SN; p < 0.001). Adjusted volumes of the CN (p < 0.001), PUT (p = 0.030), GP (p = 0.007), SN (p = 0.021), and DN (p < 0.001) were higher in females than those in males throughout the entire age range (10-70 years old). The total iron content of females was higher than that of males in the CN (p < 0.001), but lower than that of males in the PUT (p = 0.014) and RN (p = 0.043) throughout the entire age range (10-70 years old). Multiple regression analyses revealed that the combination of the mean susceptibility value of the PUT, and the volumes of the CN and PUT had the strongest associations with brain age (R² = 0.586).

CONCLUSIONS

QSM can be used to simultaneously investigate age- and sex- dependent changes in magnetic susceptibility and volume of DGM nuclei, thus enabling a comprehensive understanding of the developmental trajectories of iron accumulation and volume in DGM nuclei during brain development and aging.

Commercial volumetric MRI reporting tools in multiple sclerosis: a systematic review of the evidence

PURPOSE

MRI is integral to the diagnosis of multiple sclerosis (MS) and is important for clinical prognostication. Quantitative volumetric reporting tools (QReports) can improve the accuracy and objectivity of MRI-based assessments. Several QReports are commercially available; however, validation can be difficult to establish and does not currently follow a common pathway. To aid evidence-based clinical decision-making, we performed a systematic review of commercial QReports for use in MS including technical details and published reports of validation and in-use evaluation.

METHODS

We categorized studies into three types of testing: technical validation, for example, comparison to manual segmentation, clinical validation by clinicians or interpretation of results alongside clinician-rated variables, and in-use evaluation, such as health economic assessment.

RESULTS

We identified 10 companies, which provide MS lesion and brain segmentation and volume quantification, and 38 relevant publications. Tools received regulatory approval between 2006 and 2020, contextualize results to normative reference populations, ranging from 620 to 8000 subjects, and require T1- and T2-FLAIR-weighted input sequences for longitudinal assessment of whole-brain volume and lesions. In MS, six QReports provided evidence of technical validation, four companies have conducted clinical validation by correlating results with clinical variables, only one has tested their QReport by clinician end-users, and one has performed a simulated in-use socioeconomic evaluation.

CONCLUSION

We conclude that there is limited evidence in the literature regarding clinical validation and in-use evaluation of commercial MS QReports with a particular lack of clinician end-user testing. Our systematic review provides clinicians and institutions with the available evidence when considering adopting a quantitative reporting tool for MS.

Volumetric changes in gray matter after radiotherapy detected with longitudinal magnetic resonance imaging in glioma patients

BACKGROUND AND PURPOSE

We evaluated volumetric changes in the gray matter (GM) after radiotherapy (RT) and identified factors that were strongly associated with GM volume reduction.

MATERIALS AND METHODS

A total of 461 magnetic resonance imagings (MRI) from 105 glioma patients treated with postoperative RT was retrospectively analyzed. Study patients' MRIs were collected at five time points: before RT and 1 month, 6 months, 1 year, and 2 years after RT. Using the 'FastSurfer' platform, a deep learning-based neuroimaging pipeline, 73 regions were automatically segmented from longitudinal MRIs and their volumetric changes were calculated. Regions were grouped into 10 functional fields. A multivariable linear mixed-effects model was established to identify the potential predictors of significant volume reduction.

RESULTS

The median age was 50 years (range, 16-86 years). Forty-seven (44.8 %) patients were female and 68 (64.8 %) had glioblastoma. Postoperative RT was delivered at 54-60 Gy with or without concurrent chemotherapy. At 2 years after RT, the median volumetric changes in the overall, ipsilateral, and contralateral GM were -3.5%, -4.5%, and -2.4%, respectively. The functional fields of cognition and execution of movement showed the greatest volume reductions. In the multivariable linear mixed model, female sex (normalized coefficient = -0.14, P < 0.001) and the interaction between age at RT and days after RT (normalized coefficient = -6.48e-6, P < 0.001) were significantly associated with GM reduction. The older patients received RT, the greater volume reduction was seen over time. However, in patients with relatively younger age (e.g., 45, 50, and 60 years for hippocampus, Broca area, and Wernicke area, respectively), the volume was not significantly reduced.

CONCLUSIONS

GM volume reduction was identified after RT that could lead to long-term treatment sequelae. Particularly for susceptible patients, individualized treatment and prevention strategies are needed.

A Quantitative Imaging Biomarker Supporting Radiological Assessment of Hippocampal Sclerosis Derived From Deep Learning-Based Segmentation of T1w-MRI

Purpose

Hippocampal volumetry is an important biomarker to quantify atrophy in patients with mesial temporal lobe epilepsy. We investigate the sensitivity of automated segmentation methods to support radiological assessments of hippocampal sclerosis (HS). Results from FreeSurfer and FSL-FIRST are contrasted to a deep learning (DL)-based segmentation method.

Materials and Methods

We used T1-weighted MRI scans from 105 patients with epilepsy and 354 healthy controls. FreeSurfer, FSL, and a DL-based method were applied for brain anatomy segmentation. We calculated effect sizes (Cohen's d) between left/right HS and healthy controls based on the asymmetry of hippocampal volumes. Additionally, we derived 14 shape features from the segmentations and determined the most discriminating feature to identify patients with hippocampal sclerosis by a support vector machine (SVM).

Results

Deep learning-based segmentation of the hippocampus was the most sensitive to detecting HS. The effect sizes of the volume asymmetries were larger with the DL-based segmentations (HS left d= −4.2, right = 4.2) than with FreeSurfer (left= −3.1, right = 3.7) and FSL (left= −2.3, right = 2.5). For the classification based on the shape features, the surface-to-volume ratio was identified as the most important feature. Its absolute asymmetry yielded a higher area under the curve (AUC) for the deep learning-based segmentation (AUC = 0.87) than for FreeSurfer (0.85) and FSL (0.78) to dichotomize HS from other epilepsy cases. The robustness estimated from repeated scans was statistically significantly higher with DL than all other methods.

Conclusion

Our findings suggest that deep learning-based segmentation methods yield a higher sensitivity to quantify hippocampal sclerosis than atlas-based methods and derived shape features are more robust. We propose an increased asymmetry in the surface-to-volume ratio of the hippocampus as an easy-to-interpret quantitative imaging biomarker for HS.

Automated Segmentation of Midbrain Structures in High-Resolution Susceptibility Maps Based on Convolutional Neural Network and Transfer Learning

Background

Accurate delineation of the midbrain nuclei, the red nucleus (RN), substantia nigra (SN) and subthalamic nucleus (STN), is important in neuroimaging studies of neurodegenerative and other diseases. This study aims to segment midbrain structures in high-resolution susceptibility maps using a method based on a convolutional neural network (CNN).

Methods

The susceptibility maps of 75 subjects were acquired with a voxel size of 0.83 × 0.83 × 0.80 mm³ on a 3T MRI system to distinguish the RN, SN, and STN. A deeply supervised attention U-net was pre-trained with a dataset of 100 subjects containing susceptibility maps with a voxel size of 0.63 × 0.63 × 2.00 mm³ to provide initial weights for the target network. Five-fold cross-validation over the training cohort was used for all the models’ training and selection. The same test cohort was used for the final evaluation of all the models. Dice coefficients were used to assess spatial overlap agreement between manual delineations (ground truth) and automated segmentation. Volume and magnetic susceptibility values in the nuclei extracted with automated CNN delineation were compared to those extracted by manual tracing. Consistencies of volume and magnetic susceptibility values by different extraction strategies were assessed by Pearson correlation coefficients and Bland-Altman analyses.

Results

The automated CNN segmentation method achieved mean Dice scores of 0.903, 0.864, and 0.777 for the RN, SN, and STN, respectively. There were no significant differences between the achieved Dice scores and the inter-rater Dice scores (p > 0.05 for each nucleus). The overall volume and magnetic susceptibility values of the nuclei extracted by the automatic CNN method were significantly correlated with those by manual delineation (p < 0.01).

Conclusion

Midbrain structures can be precisely segmented in high-resolution susceptibility maps using a CNN-based method.

Deep grey matter injury in multiple sclerosis: a NAIMS consensus statement

Although multiple sclerosis has traditionally been considered a white matter disease, extensive research documents the presence and importance of grey matter injury including cortical and deep regions. The deep grey matter exhibits a broad range of pathology and is uniquely suited to study the mechanisms and clinical relevance of tissue injury in multiple sclerosis using magnetic resonance techniques. Deep grey matter injury has been associated with clinical and cognitive disability. Recently, MRI characterization of deep grey matter properties, such as thalamic volume, have been tested as potential clinical trial end points associated with neurodegenerative aspects of multiple sclerosis. Given this emerging area of interest and its potential clinical trial relevance, the North American Imaging in Multiple Sclerosis (NAIMS) Cooperative held a workshop and reached consensus on imaging topics related to deep grey matter. Herein, we review current knowledge regarding deep grey matter injury in multiple sclerosis from an imaging perspective, including insights from histopathology, image acquisition and post-processing for deep grey matter. We discuss the clinical relevance of deep grey matter injury and specific regions of interest within the deep grey matter. We highlight unanswered questions and propose future directions, with the aim of focusing research priorities towards better methods, analysis, and interpretation of results.

Whole brain and deep gray matter structure segmentation: Quantitative comparison between MPRAGE and MP2RAGE sequences

Objective

T1-weighted MRI images are commonly used for volumetric assessment of brain structures. Magnetization prepared 2 rapid gradient echo (MP2RAGE) sequence offers superior gray (GM) and white matter (WM) contrast. This study aimed to quantitatively assess the agreement of whole brain tissue and deep GM (DGM) volumes obtained from MP2RAGE compared to the widely used MP-RAGE sequence.

Methods

Twenty-nine healthy participants were included in this study. All subjects underwent a 3T MRI scan acquiring high-resolution 3D MP-RAGE and MP2RAGE images. Twelve participants were re-scanned after one year. The whole brain, as well as DGM segmentation, was performed using CAT12, volBrain, and FSL-FAST automatic segmentation tools based on the acquired images. Finally, contrast-to-noise ratio between WM and GM (CNR_WG), the agreement between the obtained tissue volumes, as well as scan-rescan variability of both sequences were explored.

Results

Significantly higher CNR_WG was detected in MP2RAGE vs. MP-RAGE (Mean ± SD = 0.97 ± 0.04 vs. 0.8 ± 0.1 respectively; p<0.0001). Significantly higher total brain GM, and lower cerebrospinal fluid‏ volumes were obtained from MP2RAGE vs. MP-RAGE based on all segmentation methods (p<0.05 in all cases). Whole-brain voxel-wise comparisons revealed higher GM tissue probability in the thalamus, putamen, caudate, lingual gyrus, and precentral gyrus based on MP2RAGE compared with MP-RAGE. Moreover, significantly higher WM probability was observed in the cerebellum, corpus callosum, and frontal-and-temporal regions in MP2RAGE vs. MP-RAGE. Finally, MP2RAGE showed a higher mean percentage of change in total brain GM compared to MP-RAGE. On the other hand, MP-RAGE demonstrated a higher overtime percentage of change in WM and DGM volumes compared to MP2RAGE.

Conclusions

Due to its higher CNR, MP2RAGE resulted in reproducible brain tissue segmentation, and thus is a recommended method for volumetric imaging biomarkers for the monitoring of neurological diseases.

Alteration of Iron Concentration in Alzheimer's Disease as a Possible Diagnostic Biomarker Unveiling Ferroptosis

Proper functioning of all organs, including the brain, requires iron. It is present in different forms in biological fluids, and alterations in its distribution can induce oxidative stress and neurodegeneration. However, the clinical parameters normally used for monitoring iron concentration in biological fluids (i.e., serum and cerebrospinal fluid) can hardly detect the quantity of circulating iron, while indirect measurements, e.g., magnetic resonance imaging, require further validation. This review summarizes the mechanisms involved in brain iron metabolism, homeostasis, and iron imbalance caused by alterations detectable by standard and non-standard indicators of iron status. These indicators for iron transport, storage, and metabolism can help to understand which biomarkers can better detect iron imbalances responsible for neurodegenerative diseases.

Neuroimaging in Functional Neurological Disorder: State of the Field and Research Agenda

Functional neurological disorder (FND) was of great interest to early clinical neuroscience leaders. During the 20th century, neurology and psychiatry grew apart - leaving FND a borderland condition. Fortunately, a renaissance has occurred in the last two decades, fostered by increased recognition that FND is prevalent and diagnosed using "rule-in" examination signs. The parallel use of scientific tools to bridge brain structure - function relationships has helped refine an integrated biopsychosocial framework through which to conceptualize FND. In particular, a growing number of quality neuroimaging studies using a variety of methodologies have shed light on the emerging pathophysiology of FND. This renewed scientific interest has occurred in parallel with enhanced interdisciplinary collaborations, as illustrated by new care models combining psychological and physical therapies and the creation of a new multidisciplinary FND society supporting knowledge dissemination in the field. Within this context, this article summarizes the output of the first International FND Neuroimaging Workgroup meeting, held virtually, on June 17th, 2020 to appraise the state of neuroimaging research in the field and to catalyze large-scale collaborations. We first briefly summarize neural circuit models of FND, and then detail the research approaches used to date in FND within core content areas: cohort characterization; control group considerations; task-based functional neuroimaging; resting-state networks; structural neuroimaging; biomarkers of symptom severity and risk of illness; and predictors of treatment response and prognosis. Lastly, we outline a neuroimaging-focused research agenda to elucidate the pathophysiology of FND and aid the development of novel biologically and psychologically-informed treatments.

Magnetic resonance imaging manifestations of cerebral small vessel disease: automated quantification and clinical application

The common cerebral small vessel disease (CSVD) neuroimaging features visible on conventional structural magnetic resonance imaging include recent small subcortical infarcts, lacunes, white matter hyperintensities, perivascular spaces, microbleeds, and brain atrophy. The CSVD neuroimaging features have shared and distinct clinical consequences, and the automatic quantification methods for these features are increasingly used in research and clinical settings. This review article explores the recent progress in CSVD neuroimaging feature quantification and provides an overview of the clinical consequences of these CSVD features as well as the possibilities of using these features as endpoints in clinical trials. The added value of CSVD neuroimaging quantification is also discussed for researches focused on the mechanism of CSVD and the prognosis in subjects with CSVD.

Gray and white matter are both affected in classical galactosemia: An explorative study on the association between neuroimaging and clinical outcome

BACKGROUND

Classical Galactosemia (CG) is an inherited disorder of galactose metabolism caused by a deficiency of the galactose-1-phosphate uridylyltransferase (GALT) enzyme resulting in neurocognitive complications. As in many Inborn Errors of Metabolism, the metabolic pathway of CG is well-defined, but the pathophysiology and high variability in clinical outcome are poorly understood. The aim of this study was to investigate structural changes of the brain of CG patients on MRI and their association with clinical outcome.

METHODS

In this prospective cohort study an MRI protocol was developed to evaluate gray matter (GM) and white matter (WM) volume of the cerebrum and cerebellum, WM hyperintensity volume, WM microstructure and myelin content with the use of conventional MRI techniques, diffusion tensor imaging (DTI) and quantitative T1 mapping. The association between several neuroimaging parameters and both neurological and intellectual outcome was investigated.

RESULTS

Twenty-one patients with CG (median age 22 years, range 8-47) and 24 controls (median age 30, range 16-52) were included. Compared to controls, the WM of CG patients was lower in volume and the microstructure of WM was impaired both in the whole brain and corticospinal tract (CST) and the lower R1 values of WM, GM and the CST were indicative of less myelin. The volume of WM lesions were comparable between patients and controls. The 9/16 patients with a poor neurological outcome (defined as the presence of a tremor and/or dystonia), demonstrated a lower WM volume, an impaired WM microstructure and lower R1 values of the WM indicative of less myelin content compared to 7/16 patients without movement disorders. In 15/21 patients with a poor intellectual outcome (defined as an IQ < 85) both GM and WM were affected with a lower cerebral and cerebellar WM and GM volume compared to 6/21 patients with an IQ ≥ 85. Both the severity of the tremor (as indicated by the Tremor Rating Scale) and IQ (as continuous measure) were associated with several neuroimaging parameters such as GM volume, WM volume, CSF volume, WM microstructure parameters and R1 values of GM and WM.

CONCLUSION

In this explorative study performed in patients with Classical Galactosemia, not only WM but also GM pathology was found, with more severe brain abnormalities on MRI in patients with a poor neurological and intellectual outcome. The finding that structural changes of the brain were associated with the severity of long-term complications indicates that quantitative MRI techniques could be of use to explain neurological and cognitive dysfunction as part of the disease spectrum. Based on the clinical outcome of patients, the absence of widespread WM lesions and the finding that both GM and WM are affected, CG could be primarily a GM disease with secondary damage to the WM as a result of neuronal degeneration. To investigate this further the course of GM and WM should be evaluated in longitudinal research, which could also clarify if CG is a neurodegenerative disease.

Dose-dependent volume loss in subcortical deep grey matter structures after cranial radiotherapy

•

Subcortical grey matter is susceptible to dose-dependent volume loss after RT.

•

Hippocampal age increases 1 year after radiotherapy, by a median of 11 years.

•

We may need to reconsider current sparing strategies in RT for brain tumours.

•

Future studies should examine the impact of deep GM volume loss on cognition.

Background and purpose

The relation between radiotherapy (RT) dose to the brain and morphological changes in healthy tissue has seen recent increased interest. There already is evidence for changes in the cerebral cortex and white matter, as well as selected subcortical grey matter (GM) structures. We studied this relation in all deep GM structures, to help understand the aetiology of post-RT neurocognitive symptoms.

Materials and methods

We selected 31 patients treated with RT for grade II-IV glioma. Pre-RT and 1 year post-RT 3D T1-weighted MRIs were automatically segmented, and the changes in volume of the following structures were assessed: amygdala, nucleus accumbens, caudate nucleus, hippocampus, globus pallidus, putamen, and thalamus. The volumetric changes were related to the mean RT dose received by each structure. Hippocampal volumes were entered into a population-based nomogram to estimate hippocampal age.

Results

A significant relation between RT dose and volume loss was seen in all examined structures, except the caudate nucleus. The volume loss rates ranged from 0.16 to 1.37%/Gy, corresponding to 4.9–41.2% per 30 Gy. Hippocampal age, as derived from the nomogram, was seen to increase by a median of 11 years.

Conclusion

Almost all subcortical GM structures are susceptible to radiation-induced volume loss, with higher volume loss being observed with increasing dose. Volume loss of these structures is associated with neurological deterioration, including cognitive decline, in neurodegenerative diseases. To support a causal relationship between radiation-induced deep GM loss and neurocognitive functioning in glioma patients, future studies are needed that directly correlate volumetrics to clinical outcomes.

Comparison and validation of seven white matter hyperintensities segmentation software in elderly patients

•

The comparison used 207 images from both research and clinical datasets.

•

When retrained, NicMSlesion, a convolutional network, was the most accurate.

•

Performance of this deep learning method severely dropped on clinical routine data.

•

On clinical routine data, regression and clustering methods were the top-ranked methods.

•

SLS was the most robust to artifacted images, and BIANCA to scanners variability.

Background

Manual segmentation is currently the gold standard to assess white matter hyperintensities (WMH), but it is time consuming and subject to intra and inter-operator variability.

Purpose

To compare automatic methods to segment white matter hyperintensities (WMH) in the elderly in order to assist radiologist and researchers in selecting the most relevant method for application on clinical or research data.

Material and Methods

We studied a research dataset composed of 147 patients, including 97 patients from the Alzheimer's Disease Neuroimaging Initiative (ADNI) 2 database and 50 patients from ADNI 3 and a clinical routine dataset comprising 60 patients referred for cognitive impairment at the Pitié-Salpêtrière hospital (imaged using four different MRI machines). We used manual segmentation as the gold standard reference. Both manual and automatic segmentations were performed using FLAIR MRI. We compared seven freely available methods that produce segmentation mask and are usable by a radiologist without a strong knowledge of computer programming: LGA (Schmidt et al., 2012), LPA (Schmidt, 2017), BIANCA (Griffanti et al., 2016), UBO detector (Jiang et al., 2018), W2MHS (Ithapu et al., 2014), nicMSlesion (with and without retraining) (Valverde et al., 2019, Valverde et al., 2017). The primary outcome for assessing segmentation accuracy was the Dice similarity coefficient (DSC) between the manual and the automatic segmentation software. Secondary outcomes included five other metrics.

Results

A deep learning approach, NicMSlesion, retrained on data from the research dataset ADNI, performed best on this research dataset (DSC: 0.595) and its DSC was significantly higher than that of all others. However, it ranked fifth on the clinical routine dataset and its performance severely dropped on data with artifacts. On the clinical routine dataset, the three top-ranked methods were LPA, SLS and BIANCA. Their performance did not differ significantly but was significantly higher than that of other methods.

Conclusion

This work provides an objective comparison of methods for WMH segmentation. Results can be used by radiologists to select a tool.

Elevated plasma levels of exosomal BACE1‑AS combined with the volume and thickness of the right entorhinal cortex may serve as a biomarker for the detection of Alzheimer's disease

Long non-coding RNA (lncRNA) and exosomes are involved in the pathological process of Alzheimer's disease (AD), the pathological changes of which are usually first observed in the entorhinal cortex and hippocampus. The aim of the present study was to determine whether the measurement of plasma exosomal lncRNA combined with image data of the entorhinal cortex and hippocampus could be used as a biomarker of AD. A total of 72 patients with AD and 62 controls were recruited, and the expression levels of several lncRNAs were assessed. Of the recruited participants, 22 patients and 26 controls received brain 3D-BRAVO sequence magnetic resonance imaging (MRI) scans, which were analyzed using an automated analysis tool. The plasma exosomal β-site amyloid precursor protein cleaving enzyme-1-antisense transcript (BACE1-AS) levels in patients with AD were significantly higher compared with the controls (P<0.005). Receiver operating characteristic curve analysis revealed that the area under the curve (AUC) was 0.761 for BACE1-AS, the sensitivity was 87.5%, and the specificity was 61.3%. Analysis of MRI images indicated that the right entorhinal cortex volume (P=0.015) and thickness (P=0.022) in patients with AD were significantly smaller. The AUC was 0.688 for the right entorhinal cortex volume, with a sensitivity of 59.1%, and the specificity was 84.6%. The AUC was 0.689 for right entorhinal cortex thickness, with a sensitivity of 80.8%, and the specificity was 59.1%. A series-parallel test which integrated the BACE1-AS with the right entorhinal cortex volume and thickness, raised the specificity and sensitivity to 96.15 and 90.91%, respectively. A logistic regression model demonstrated that combination of the 3 indices provided improved sensitivity and specificity simultaneously, particularly when adjusting for age and sex (AUC, 0.819; sensitivity, 81%; specificity, 73.1%). The results of the present study demonstrated that detection of plasma exosomal BACE1-AS levels combined with the volume and thickness of the right entorhinal cortex may be used as a novel biomarker of AD.