Reliable brain morphometry from contrast-enhanced T1w-MRI in patients with multiple sclerosis

Clinical applications of deep learning in neuroinflammatory diseases: A scoping review

BACKGROUND

Deep learning (DL) is an artificial intelligence technology that has aroused much excitement for predictive medicine due to its ability to process raw data modalities such as images, text, and time series of signals.

OBJECTIVES

Here, we intend to give the clinical reader elements to understand this technology, taking neuroinflammatory diseases as an illustrative use case of clinical translation efforts. We reviewed the scope of this rapidly evolving field to get quantitative insights about which clinical applications concentrate the efforts and which data modalities are most commonly used.

METHODS

We queried the PubMed database for articles reporting DL algorithms for clinical applications in neuroinflammatory diseases and the radiology.healthairegister.com website for commercial algorithms.

RESULTS

The review included 148 articles published between 2018 and 2024 and five commercial algorithms. The clinical applications could be grouped as computer-aided diagnosis, individual prognosis, functional assessment, the segmentation of radiological structures, and the optimization of data acquisition. Our review highlighted important discrepancies in efforts. The segmentation of radiological structures and computer-aided diagnosis currently concentrate most efforts with an overrepresentation of imaging. Various model architectures have addressed different applications, relatively low volume of data, and diverse data modalities. We report the high-level technical characteristics of the algorithms and synthesize narratively the clinical applications. Predictive performances and some common a priori on this topic are finally discussed.

CONCLUSION

The currently reported efforts position DL as an information processing technology, enhancing existing modalities of paraclinical investigations and bringing perspectives to make innovative ones actionable for healthcare.

Comparative analysis of brain volumetric measurements between contrast-enhanced and non-contrast MRI images

BACKGROUND

Clinical brain MRI scans, including contrast-enhanced (CE-MR) images, represent an underutilized resource for neuroscience research due to technical heterogeneity.

PURPOSE

To evaluate the reliability of morphometric measurements from CE-MR scans compared to non-contrast MR (NC-MR) scans in normal individuals.

METHODS

T1-weighted CE-MR and NC-MR scans from 59 normal participants (aged 21-73 years) were compared using CAT12 and SynthSeg+ segmentation tools. Volumetric measurements and age prediction efficacy were analyzed.

RESULTS

SynthSeg+ demonstrated high reliability (ICCs > 0.90) for most brain structures between CE-MR and NC-MR scans, with discrepancies in CSF and ventricular volumes. CAT12 showed inconsistent performance. Age prediction models using SynthSeg + yielded comparable results for both scan types.

CONCLUSION

Deep learning-based approaches like SynthSeg+ can reliably process CE-MR scans for morphometric analysis, potentially broadening the application of clinically acquired CE-MR images in neuroimaging research.

Diffeomorphic transformer-based abdomen MRI-CT deformable image registration

BACKGROUND

Stereotactic body radiotherapy (SBRT) is a well-established treatment modality for liver metastases in patients unsuitable for surgery. Both CT and MRI are useful during treatment planning for accurate target delineation and to reduce potential organs-at-risk (OAR) toxicity from radiation. MRI-CT deformable image registration (DIR) is required to propagate the contours defined on high-contrast MRI to CT images. An accurate DIR method could lead to more precisely defined treatment volumes and superior OAR sparing on the treatment plan. Therefore, it is beneficial to develop an accurate MRI-CT DIR for liver SBRT.

PURPOSE

To create a new deep learning model that can estimate the deformation vector field (DVF) for directly registering abdominal MRI-CT images.

METHODS

The proposed method assumed a diffeomorphic deformation. By using topology-preserved deformation features extracted from the probabilistic diffeomorphic registration model, abdominal motion can be accurately obtained and utilized for DVF estimation. The model integrated Swin transformers, which have demonstrated superior performance in motion tracking, into the convolutional neural network (CNN) for deformation feature extraction. The model was optimized using a cross-modality image similarity loss and a surface matching loss. To compute the image loss, a modality-independent neighborhood descriptor (MIND) was used between the deformed MRI and CT images. The surface matching loss was determined by measuring the distance between the warped coordinates of the surfaces of contoured structures on the MRI and CT images. To evaluate the performance of the model, a retrospective study was carried out on a group of 50 liver cases that underwent rigid registration of MRI and CT scans. The deformed MRI image was assessed against the CT image using the target registration error (TRE), Dice similarity coefficient (DSC), and mean surface distance (MSD) between the deformed contours of the MRI image and manual contours of the CT image.

RESULTS

When compared to only rigid registration, DIR with the proposed method resulted in an increase of the mean DSC values of the liver and portal vein from 0.850 ± 0.102 and 0.628 ± 0.129 to 0.903 ± 0.044 and 0.763 ± 0.073, a decrease of the mean MSD of the liver from 7.216 ± 4.513 mm to 3.232 ± 1.483 mm, and a decrease of the TRE from 26.238 ± 2.769 mm to 8.492 ± 1.058 mm.

CONCLUSION

The proposed DIR method based on a diffeomorphic transformer provides an effective and efficient way to generate an accurate DVF from an MRI-CT image pair of the abdomen. It could be utilized in the current treatment planning workflow for liver SBRT.

Cortical thickness and grey-matter volume anomaly detection in individual MRI scans: Comparison of two methods

Over the past decades, morphometric analysis of brain MRI has contributed substantially to the understanding of healthy brain structure, development and aging as well as to improved characterisation of disease related pathologies. Certified commercial tools based on normative modeling of these metrics are meanwhile available for diagnostic purposes, but they are cost intensive and their clinical evaluation is still in its infancy. Here we have compared the performance of "ScanOMetrics", an open-source research-level tool for detection of statistical anomalies in individual MRI scans, depending on whether it is operated on the output of FreeSurfer or of the deep learning based brain morphometry tool DL + DiReCT. When applied to the public OASIS3 dataset, containing patients with Alzheimer's disease (AD) and healthy controls (HC), cortical thickness anomalies in patient scans were mainly detected in regions that are known as predilection areas of cortical atrophy in AD, regardless of the software used for extraction of the metrics. By contrast, anomaly detections in HCs were up to twenty-fold reduced and spatially unspecific using both DL + DiReCT and FreeSurfer. Progression of the atrophy pattern with clinical dementia rating (CDR) was clearly observable with both methods. DL + DiReCT provided results in less than 25 min, more than 15 times faster than FreeSurfer. This difference in computation time might be relevant when considering application of this or similar methodology as diagnostic decision support for neuroradiologists.

Diffeomorphic Transformer-based Abdomen MRI-CT Deformable Image Registration

Background

Stereotactic body radiotherapy (SBRT) is a well-established treatment modality for liver metastases in patients unsuitable for surgery. Both CT and MRI are useful during treatment planning for accurate target delineation and to reduce potential organs-at-risk (OAR) toxicity from radiation. MRI-CT deformable image registration (DIR) is required to propagate the contours defined on high-contrast MRI to CT images. An accurate DIR method could lead to more precisely defined treatment volumes and superior OAR sparing on the treatment plan. Therefore, it is beneficial to develop an accurate MRI-CT DIR for liver SBRT.

Purpose

To create a new deep learning model that can estimate the deformation vector field (DVF) for directly registering abdominal MRI-CT images.

Methods

The proposed method assumed a diffeomorphic deformation. By using topology-preserved deformation features extracted from the probabilistic diffeomorphic registration model, abdominal motion can be accurately obtained and utilized for DVF estimation. The model integrated Swin transformers, which have demonstrated superior performance in motion tracking, into the convolutional neural network (CNN) for deformation feature extraction. The model was optimized using a cross-modality image similarity loss and a surface matching loss. To compute the image loss, a modality-independent neighborhood descriptor (MIND) was used between the deformed MRI and CT images. The surface matching loss was determined by measuring the distance between the warped coordinates of the surfaces of contoured structures on the MRI and CT images. To evaluate the performance of the model, a retrospective study was carried out on a group of 50 liver cases that underwent rigid registration of MRI and CT scans. The deformed MRI image was assessed against the CT image using the target registration error (TRE), Dice similarity coefficient (DSC), and mean surface distance (MSD) between the deformed contours of the MRI image and manual contours of the CT image.

Results

When compared to only rigid registration, DIR with the proposed method resulted in an increase of the mean DSC values of the liver and portal vein from 0.850±0.102 and 0.628±0.129 to 0.903±0.044 and 0.763±0.073, a decrease of the mean MSD of the liver from 7.216±4.513 mm to 3.232±1.483 mm, and a decrease of the TRE from 26.238±2.769 mm to 8.492±1.058 mm.

Conclusion

The proposed DIR method based on a diffeomorphic transformer provides an effective and efficient way to generate an accurate DVF from an MRI-CT image pair of the abdomen. It could be utilized in the current treatment planning workflow for liver SBRT.

Three-dimensional infrared scanning: an enhanced approach for spatial registration of probes for neuroimaging

Significance

Accurate spatial registration of probes (e.g., optodes and electrodes) for measurement of brain activity is a crucial aspect in many neuroimaging modalities. It may increase measurement precision and enable the transition from channel-based calculations to volumetric representations.

Aim

This technical note evaluates the efficacy of a commercially available infrared three-dimensional (3D) scanner under actual experimental (or clinical) conditions and provides guidelines for its use.

Method

We registered probe positions using an infrared 3D scanner and validated them against magnetic resonance imaging (MRI) scans on five volunteer participants.

Results

Our analysis showed that with standard cap fixation, the average Euclidean distance of probe position among subjects could reach up to 43 mm, with an average distance of 15.25 mm [standard deviation (SD) = 8.0]. By contrast, the average distance between the infrared 3D scanner and the MRI-acquired positions was 5.69 mm (SD = 1.73), while the average difference between consecutive infrared 3D scans was 3.43 mm (SD = 1.62). The inter-optode distance, which was fixed at 30 mm, was measured as 29.28 mm (SD = 1.12) on the MRI and 29.43 mm (SD = 1.96) on infrared 3D scans. Our results demonstrate the high accuracy and reproducibility of the proposed spatial registration method, making it suitable for both functional near-infrared spectroscopy and electroencephalogram studies.

Conclusions

The 3D infrared scanning technique for spatial registration of probes provides economic efficiency, simplicity, practicality, repeatability, and high accuracy, with potential benefits for a range of neuroimaging applications. We provide practical guidance on anonymization, labeling, and post-processing of acquired scans.

Clinical Evaluation of a Quantitative Imaging Biomarker Supporting Radiological Assessment of Hippocampal Sclerosis

OBJECTIVE

To evaluate the influence of quantitative reports (QReports) on the radiological assessment of hippocampal sclerosis (HS) from MRI of patients with epilepsy in a setting mimicking clinical reality.

METHODS

The study included 40 patients with epilepsy, among them 20 with structural abnormalities in the mesial temporal lobe (13 with HS). Six raters blinded to the diagnosis assessed the 3T MRI in two rounds, first using MRI only and later with both MRI and the QReport. Results were evaluated using inter-rater agreement (Fleiss' kappa [Formula: see text]) and comparison with a consensus of two radiological experts derived from clinical and imaging data, including 7T MRI.

RESULTS

For the primary outcome, diagnosis of HS, the mean accuracy of the raters improved from 77.5% with MRI only to 86.3% with the additional QReport (effect size [Formula: see text]). Inter-rater agreement increased from [Formula: see text] to [Formula: see text]. Five of the six raters reached higher accuracies, and all reported higher confidence when using the QReports.

CONCLUSION

In this pre-use clinical evaluation study, we demonstrated clinical feasibility and usefulness as well as the potential impact of a previously suggested imaging biomarker for radiological assessment of HS.

From basic sciences and engineering to epileptology: A translational approach

Collaborative efforts between basic scientists, engineers, and clinicians are enabling translational epileptology. In this article, we summarize the recent advances presented at the International Conference for Technology and Analysis of Seizures (ICTALS 2022): (1) novel developments of structural magnetic resonance imaging; (2) latest electroencephalography signal-processing applications; (3) big data for the development of clinical tools; (4) the emerging field of hyperdimensional computing; (5) the new generation of artificial intelligence (AI)-enabled neuroprostheses; and (6) the use of collaborative platforms to facilitate epilepsy research translation. We highlight the promise of AI reported in recent investigations and the need for multicenter data-sharing initiatives.

Assessment of the Impact of Turbo Factor on Image Quality and Tissue Volumetrics in Brain Magnetic Resonance Imaging Using the Three-Dimensional T1-Weighted (3D T1W) Sequence

Background

The 3D T1W turbo field echo sequence is a standard imaging method for acquiring high-contrast images of the brain. However, the contrast-to-noise ratio (CNR) can be affected by the turbo factor, which could affect the delineation and segmentation of various structures in the brain and may consequently lead to misdiagnosis. This study is aimed at evaluating the effect of the turbo factor on image quality and volumetric measurement reproducibility in brain magnetic resonance imaging (MRI).

Methods

Brain images of five healthy volunteers with no history of neurological diseases were acquired on a 1.5 T MRI scanner with varying turbo factors of 50, 100, 150, 200, and 225. The images were processed and analyzed with FreeSurfer. The influence of the TFE factor on image quality and reproducibility of brain volume measurements was investigated. Image quality metrics assessed included the signal-to-noise ratio (SNR) of white matter (WM), CNR between gray matter/white matter (GM/WM) and gray matter/cerebrospinal fluid (GM/CSF), and Euler number (EN). Moreover, structural brain volume measurements of WM, GM, and CSF were conducted.

Results

Turbo factor 200 produced the best SNR (median = 17.01) and GM/WM CNR (median = 2.29), but turbo factor 100 offered the most reproducible SNR (IQR = 2.72) and GM/WM CNR (IQR = 0.14). Turbo factor 50 had the worst and the least reproducible SNR, whereas turbo factor 225 had the worst and the least reproducible GM/WM CNR. Turbo factor 200 again had the best GM/CSF CNR but offered the least reproducible GM/CSF CNR. Turbo factor 225 had the best performance on EN (-21), while turbo factor 200 was next to the most reproducible turbo factor on EN (11). The results showed that turbo factor 200 had the least data acquisition time, in addition to superior performance on SNR, GM/WM CNR, GM/CSF CNR, and good reproducibility characteristics on EN. Both image quality metrics and volumetric measurements did not vary significantly (p > 0.05) with the range of turbo factors used in the study by one-way ANOVA analysis.

Conclusion

Since no significant differences were observed in the performance of the turbo factors in terms of image quality and volume of brain structure, turbo factor 200 with a 74% acquisition time reduction was found to be optimal for brain MR imaging at 1.5 T.

Case report: Psychosis and catatonia in an adolescent patient with adipsic hypernatremia and autoantibodies against the subfornical organ

This is the first description of a patient in which adipsic hypernatremia, a rare autoimmune encephalitis, presented in combination with complex psychiatric symptomatology, including psychosis and catatonia. Adipsic hypernatremia is characterized by autoantibodies against the thirst center of the brain. These autoantibodies cause inflammation and apoptosis in key regions of water homeostasis, leading to lack of thirst and highly increased serum sodium. To date, the symptoms of weakness, fatigue and drowsiness have been associated with adipsic hypernatremia, but no psychiatric symptomatology. Here, we showcase the first description of an adolescent patient, in which severe and complex psychiatric symptoms presented along with adipsic hypernatremia. The patient experienced delusion, hallucinations, restlessness and pronounced depression. Further, he showed ritualized, aggressive, disinhibited and sexualized behavior, as well as self-harm and psychomotor symptoms. Due to his severe condition, he was hospitalized on the emergency unit of the child and adolescent psychiatry for 8 months. Key symptoms of the presented clinical picture are: childhood-onset complex and treatment-resistant psychosis/catatonia, pronounced behavioral problems, fatigue, absent thirst perception, hypernatremia and elevated prolactin levels. This case report renders first evidence speaking for a causal link between the autoimmune adipsic hypernatremia and the psychotic disorder. Moreover, it sheds light on a new form of autoimmune psychosis.

Anti-neurochondrin antibody as a biomarker in primary autoimmune cerebellar ataxia-a case report and review of the literature

BACKGROUND AND PURPOSE

Neuronal autoantibodies can support the diagnosis of primary autoimmune cerebellar ataxia (PACA). Knowledge of PACA is still sparce. This article aims to highlight the relevance of anti-neurochondrin antibodies and possible therapeutical consequences in people with PACA.

METHODS

This is a case presentation and literature review of PACA associated with anti-neurochondrin antibodies.

RESULTS

A 33-year-old man noticed reduced control of the right leg in May 2020. During his first clinic appointment at our institution in September 2021, he complained about gait imbalance, fine motor disorders, tremor, intermittent diplopia and slurred speech. He presented a pancerebellar syndrome with stance, gait and limb ataxia, scanning speech and oculomotor dysfunction. Within 3 months the symptoms progressed. An initial cerebral magnetic resonance imaging, June 2020, was normal, but follow-up imaging in October 2021 and July 2022 revealed marked cerebellar atrophy (29% volume loss). Cerebrospinal fluid analysis showed lymphocytic pleocytosis of 11 x 10³ /L (normal range 0-4) and oligoclonal bands type II. Anti-neurochondrin antibodies (immunoglobulin G) were detected in serum (1:10,000) and cerebrospinal fluid (1:320, by cell-based indirect immunofluorescence assay and immunoblot, analysed by the EUROIMMUN laboratory). After ruling out alternative causes and neoplasia, diagnosis of PACA was given and immunotherapy (steroids and cyclophosphamide) was started in January 2022. In March 2022 a stabilization of disease was observed.

CONCLUSION

Cerebellar ataxia associated with anti-neurochondrin antibodies has only been described in 19 cases; however, the number of unrecognized PACAs may be higher. As anti-neurochondrin antibodies target an intracellular antigen and exhibit a mainly cytotoxic T-cell-mediated pathogenesis, important therapeutic implications may result. Because of the severe and rapid clinical progression, aggressive immunotherapy was warranted. This case highlights the need for rapid diagnosis and therapy in PACA, as stabilization and even improvement of symptoms are attainable.

Distinct and shared patterns of brain plasticity during electroconvulsive therapy and treatment as usual in depression: an observational multimodal MRI-study

Electroconvulsive therapy (ECT) is a highly effective treatment for depression. Previous studies point to ECT-induced volume increase in the hippocampi and amygdalae, and to increase in cortical thickness. However, it is unclear if these neuroplastic changes are associated with treatment response. This observational study aimed to address this research question by comparing neuroplasticity between patients with depression receiving ECT and patients with depression that respond to treatment as usual (TAU-responders). Twenty ECT-patients (16 major depressive disorder (MDD), 4 depressed bipolar disorder), 20 TAU-responders (20 MDD) and 20 healthy controls (HC) were scanned twice with multimodal magnetic resonance imaging (structure: MP2RAGE; perfusion: arterial spin labeling). ECT-patients were scanned before and after an ECT-index series (ECT-group). TAU-responders were scanned during a depressive episode and following remission or treatment response. Volumes and cerebral blood flow (CBF) of the hippocampi and amygdalae, and global mean cortical thickness were compared between groups. There was a significant group × time interaction for hippocampal and amygdalar volumes, CBF in the hippocampi and global mean cortical thickness. Hippocampal and amygdalar enlargements and CBF increase in the hippocampi were observed in the ECT-group but neither in TAU-responders nor in HC. Increase in global mean cortical thickness was observed in the ECT-group and in TAU-responders but not in HC. The co-occurrence of increase in global mean cortical thickness in both TAU-responders and in ECT-patients may point to a shared mechanism of antidepressant response. This was not the case for subcortical volume and CBF increase.

Large-scale transient peri-ictal perfusion magnetic resonance imaging abnormalities detected by quantitative image analysis

Epileptic seizures require a rapid and safe diagnosis to minimize the time from onset to adequate treatment. Some epileptic seizures can be diagnosed clinically with the respective expertise. For more subtle seizures, imaging is mandatory to rule out treatable structural lesions and potentially life-threatening conditions. MRI perfusion abnormalities associated with epileptic seizures have been reported in CT and MRI studies. However, the interpretation of transient peri-ictal MRI abnormalities is routinely based on qualitative visual analysis and therefore reader dependent. In this retrospective study, we investigated the diagnostic yield of visual analysis of perfusion MRI during ictal and postictal states based on comparative expert ratings in 51 patients. We further propose an automated semi-quantitative method for perfusion analysis to determine perfusion abnormalities observed during ictal and postictal MRI using dynamic susceptibility contrast MRI, which we validated on a subcohort of 27 patients. The semi-quantitative method provides a parcellation of 3D T₁-weighted images into 32 standardized cortical regions of interests and subcortical grey matter structures based on a recently proposed method, direct cortical thickness estimation using deep learning-based anatomy segmentation and cortex parcellation for brain anatomy segmentation. Standard perfusion maps from a Food and Drug Administration-approved image analysis tool (Olea Sphere 3.0) were co-registered and investigated for region-wise differences between ictal and postictal states. These results were compared against the visual analysis of two readers experienced in functional image analysis in epilepsy. In the ictal group, cortical hyperperfusion was present in 17/18 patients (94% sensitivity), whereas in the postictal cohort, cortical hypoperfusion was present only in 9/33 (27%) patients while 24/33 (73%) showed normal perfusion. The (semi-)quantitative dynamic susceptibility contrast MRI perfusion analysis indicated increased thalamic perfusion in the ictal cohort and hypoperfusion in the postictal cohort. Visual ratings between expert readers performed well on the patient level, but visual rating agreement was low for analysis of subregions of the brain. The asymmetry of the automated image analysis correlated significantly with the visual consensus ratings of both readers. We conclude that expert analysis of dynamic susceptibility contrast MRI effectively discriminates ictal versus postictal perfusion patterns. Automated perfusion evaluation revealed favourable interpretability and correlated well with the classification of the visual ratings. It may therefore be employed for high-throughput, large-scale perfusion analysis in extended cohorts, especially for research questions with limited expert rater capacity.

Multiple sclerosis as a model to investigate SARS-CoV-2 effect on brain atrophy

INTRODUCTION

Data on structural brain changes after infection with SARS-CoV-2 is sparse. We postulate multiple sclerosis as a model to study the effects of SARS-CoV-2 on brain atrophy due to the unique availability of longitudinal imaging data in this patient group, enabling assessment of intraindividual brain atrophy rates.

METHODS

Global and regional cortical gray matter volumes were derived from structural MRIs using FreeSurfer. A linear model was fitted to the measures of the matching pre-SARS-CoV-2 images with age as an explanatory variable. The residuals were used to determine whether the post-SARS-CoV-2 volumes differed significantly from the baseline.

RESULTS

Fourteen RRMS patients with a total of 113 longitudinal magnetic resonance images were retrospectively analyzed. We found no acceleration of brain atrophy after infection with SARS-CoV-2 for global gray matter volume (p = 0.17). However, on the regional level, parahippocampal gyri showed a tendency toward volume reduction (p = 0.0076), suggesting accelerated atrophy during or after infection.

CONCLUSIONS

Our results illustrate the opportunity of using longitudinal MRIs from existing MS registries to study brain changes associated with SARS-CoV-2 infections. We would like to address the global MS community with a call for action to use the available cohorts, reproduce the proposed analysis, and pool the results.