T1-weighted Brain MRI Research Articles

Segmentation of intrinsically very low contrast magnetic resonance brain images using tensor-based DTI registration

BackgroundIn patients with hypomyelinating leukodystrophies, contrast of T1-weighted brain MRI is very low due to the lack of myelin, preventing a reliable segmentation. In diffusion tensor images the contrast is higher, thanks to anisotropy and orientation of white matter (WM) tracts. We aimed to develop and assess a tensor-guided atlas-based segmentation method suitable for segmentation of very low contrast images. Methods17 control subjects (mean age 8.0 yrs (SD 8.0)) and 27 subjects with hypomyelinating leukodystrophies (mean age 10.7 yrs (SD 10.2)) were included. DTI and 3D T1 images were segmented using a DTI-TK tensor-guided IIT-atlas-based segmentation method. For the control subjects, these segmentations were compared with a conventional segmentation of their 3D T1-weighted images. A qualitative visual assessment and a quantitative assessment using DTI metrics was performed to assess the patient segmentations. ResultsIn control subjects, the tensor-based method performed as can be expected for atlas-based segmentation methods, with Dice coefficients of 0.65, 0.72, 0.81 and 0.86 for cortical grey matter (GM), WM, deep grey matter (DGM), and thalamus, respectively. In patients with hypomyelination the visual assessment showed anatomically adequate segmentations. All tissue-specific DTI metrics differed between patients and controls. Patients with hypomyelination had reduced FA and increased mean, axial and radial diffusivities, not only in total WM, but also in the corticospinal tracts, optic radiations and thalamus. ConclusionEven in the absence of normal myelin, the presence and direction of axons allowed tensor-based registration and thereby atlas-based segmentation. We showed the applicability of the segmentation method in the context of quantitative MRI, allowing for whole-brain or regional tissue-specific and tract-specific analyses of very low contrast images.

Corpus callosum anatomical changes in Alzheimer patients and the effect of acetylcholinesterase inhibitors on corpus callosum morphometry.

The Corpus Callosum (CC) is an important structure that includes the majority of fibers connecting the two brain hemispheres. Several neurodegenerative diseases may alter CC size and morphology leading to its atrophy and malfunction which may play a role in the pathological manifestations found in these diseases. The purpose of the current study is to determine any possible changes in CC size in patients suffering from Alzheimer's disease. The Study also investigated the effect of acetylcholinesterase inhibitors (AChEIs) on the size of CC and its association with improvement in the Alzheimer disease severity scores. Midsagittal size of CC were recorded prospectively from 439 routine T1-weighted MRI brain images in normal individuals. The internal skull surface was measured to calculate CC/ internal skull surface ratio. Two groups of patients were studied: 300 (150 male / 150 female) were healthy subjects and 130 (55 males / 75 females) had Alzheimer disease. Out of the 130 Alzheimer disease pateints, 70 patients were treated with Donepezil or Rivastigmine or both. The size of the CC was measured based on T1-weighted MRI images after the treatment to investigate any possible improvement in CC size. The mean surface area of CC in controls was 6.53±1.105 cm2. There was no significant difference between males and females (P < 0.627), and CC/ internal skull surface ratio was 4.41±0.77%. Patients with mild or severe Alzheimer disease showed a significant reduction in CC size compared to healthy controls. Treating mild Alzheimer patients with either Donepezil or Rivastigmine exerts a comparable therapeutic effect in improving the CC size. There was more improvement in the size of CC in patients with severe Alzheimer disease by using combined therapy of Donepezil and Rivastigmine than using single a medication. we measured the mean size of the various portions of the corpus callosum in normal individuals and Alzheimer patients before and after taking Donepezil and Rivastigmine. Alzheimer patients have pronounced reduction in CC which is corrected after taking Donepezil and Rivastigmine leading to remarkable improvement in Alzheimer disease severity scores.

Deep transfer learning-based fully automated detection and classification of Alzheimer's disease on brain MRI.

To employ different automated convolutional neural network (CNN)-based transfer learning (TL) methods for both binary and multiclass classification of Alzheimer's disease (AD) using brain MRI. Herein, we applied three popular pre-trained CNN models (ResNet101, Xception, and InceptionV3) using a fine-tuned approach of TL on 3D T1-weighted brain MRI from a subset of ADNI dataset (n = 305 subjects). To evaluate power of TL, the aforementioned networks were also trained from scratch for performance comparison. Initially, Unet network segmentedthe MRI scans into characteristic components of gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF). The proposed networks were trained and tested over the pre-processed and augmented segmented and whole images for both binary (NC/AD + progressive mild cognitive impairment (pMCI)+stable MCI (sMCI)) and 4-class (AD/pMCI/sMCI/NC) classification. Also, two independent test sets from the OASIS (n = 30) and AIBL (n = 60) datasets were used to externally assess the performance of the proposed algorithms. The proposed TL-based CNN models achieved better performance compared to the training CNN models from scratch. On the ADNI test set, InceptionV3-TL achieved the highest accuracy of 93.75% and AUC of 92.0% for binary classification, as well as the highest accuracy of 93.75% and AUC of 96.0% for multiclass classification of AD on the whole images. On the OASIS test set, InceptionV3-TL outperformed two other models by achieving 93.33% accuracy with 93.0% AUC in binary classification of AD on the whole images. On the AIBL test set, InceptionV3-TL also outperformed two other models in both binary and multiclass classification tasks on the whole MR images and achieved accuracy/AUC of 93.33%/95.0% and 90.0%/93.0%, respectively. The GM segment as input provided the highest performance in both binary and multiclass classification of AD, as compared to the WM and CSF segments. This study demonstrates the potential of applying deep TL approach for automated detection and classification of AD using brain MRI with high accuracy and robustness across internal and external test data, suggesting that these models can possibly be used as a supportive tool to assist clinicians in creating objective opinion and correct diagnosis. We used CNN-based TL approaches and the augmentation techniques to overcome the insufficient data problem. Our study provides evidence that deep TL algorithms can be used for both binary and multiclass classification of AD with high accuracy.

Associations of Vitamin B-6 status and Regional Brain Volumetric Measures in the Boston Puerto Rican Health Study

Abstract Objectives We quantified the associations of circulating vitamin B-6 concentration with regional brain volumes among Puerto Rican adults. In addition, associations with plasma vitamins B-12 and folate were investigated. Methods Data are from the Boston Puerto Rican Health Study (n = 1499), where a subset of participants from the original cohort volunteered for T1-weighted MRI brain scans (n = 193) (78% female and aged 55 ± 7 y at baseline) approximately 13 years from the baseline visit. Circulating B-6 (pyridoxal 5′-phosphate, PLP), folate, and B-12 were measured from fasting blood samples collected at baseline and ∼2 and 5 y from baseline. Mean concentrations of these B vitamins were calculated for participants with blood samples from at least 2 of the 3 visits (baseline, 2-y, and 5-y). Whole MRI brain volumetric measures (of cortical and subcortical grey matter) were quantified using the FreeSurfer processing pipeline. Volumetric measurements included the frontal, parietal, temporal, and occipital lobes, cingulate gyrus, thalamus, caudate nucleus, putamen, hippocampus, amygdala, cerebellar white matter, and cerebellar cortex. Multivariable linear regression was used to examine associations between mean circulating B-6 and z score transformed regional brain volumes at 13-y. Secondary exposures were circulating folate and B-12 concentrations. A log transformation was applied to B vitamin concentrations. Models were adjusted for age, sex, BMI, smoking status, and intracranial volume. Results Mean circulating PLP, folate, and B-12 were 64.5 ± 52 nmol/L, 19.3 ± 7.1 ng/mL, and 558 ± 242 pg/mL, respectively. We observed null associations between PLP and 13-y brain volumetric measures. Conversely, greater vitamin B-12 concentration was associated with greater parietal [β = 0.49 (95% CI: 0.02, 0.96), P = 0.04], putamen [0.88 (0.221, 1.54), P = 0.009], and cerebellar white matter volumes [0.71 (0.08, 1.33), P = 0.02]. Folate was positively associated with thalamus measurements [1.06 (0.34, 1.78), P = 0.004]. Results remained similar after accounting for a history of cardiovascular disease and type 2 diabetes. Conclusions These results suggest that, among older Puerto Rican adults, greater vitamin B-12 and folate, but not B-6, status may be related to greater volumetric measures of select brain structures. Funding Sources National Institute on Aging.

Computerized Classification Method for 1p/19q Codeletion in Low-Grade Glioma on Brain MRI Using Multi-Scale 3D-CNNs with Attention Mechanism

The purpose of this study was to develop a computerized classification method for low-grade gliomas (LGGs) with/without 1p/19q codeletion on brain MRI using multi-scale 3D-convolutional neural networks (Multi-scale 3D-CNNs) with an attention mechanism that analyzes only the tumor region. Our database consisted of brain T2-weighted MRI images for 159 patients (102 LGGs with 1p/19q codeletion and 57 LGGs without it) from The Cancer Imaging Archive. The proposed method was constructed from a feature extractor, an attention mechanism, and a perception branch. In the feature extractor, the feature maps were extracted from input images. The attention mechanism generated the attention maps focusing on a tumor region from those feature maps. The feature maps on the tumor region were then obtained using an attention pooling with the attention maps. In the perception branch, the likelihood of LGG with 1p/19q codeletion was evaluated based on the feature maps of the tumor region. The classification accuracy, the sensitivity, the specificity, and the area under the receiver operating characteristic curve for the proposed method were 78.0%, 82.4%, 70.2%, and 0.838, showing a significant improvement when compared with the multi-scale 3D-CNNs without the attention mechanism (69.8%, 75.5%, 59.6%, and 0.717; p = 0.001).

AUTOMATED SEGMENTATION OF CORPUS CALLOSUM IN BRAIN MR IMAGES IN ALZHEIMER’S CONDITIONS USING IMPROVED UNET++ MODEL

The Corpus Callosum (CC) is a large white matter bundle that connects the left and right cerebral hemispheres of the human brain. It is susceptible to atrophy as Alzheimer’s disease progresses. The robust segmentation of CC allows quantitative investigation of its structural changes. However, deep learning-based CC segmentation is less explored. In this work, an improved UNet model is proposed for CC segmentation from two-dimensional T1-weighted mid-sagittal brain MRI. For this, mid-sagittal scans (n = 184) from the publicly available Open Access Series of Imaging Studies (OASIS) brain MRI database are used. The images are fed to an improved UNet++ network. The architecture contains a fully convolutional network with two paths, contracting and extracting, that are connected in a U-shape to automatically extract spatial information. Leave one out Cross-Validation (LooCV) method is used to evaluate the robustness of the proposed method. Results show that the proposed approach is able to segment CC from MR images. The proposed method yields the Dice score of 98.43%, and Jaccard index of 98.53%. The improved UNet++ model obtained the highest sensitivity of 99.21% for AD conditions. Further, the performance of the proposed model has been validated against the state-of-the-art methods. Thus, the proposed approach could be useful for the segmentation of MR images in clinical condition.

Investigation of the Inter- and Intrascanner Reproducibility and Repeatability of Radiomics Features in T1-Weighted Brain MRI.

Radiomics is the high throughput analysis of medical images using computer algorithms, which specifically assess textural features. It has increasingly been proposed as a tool for the development of imaging biomarkers. However, an important acknowledged limitation of radiomics is the lack of reproducibility of features produced. To assess reproducibility and repeatability of radiomics variables in brain MRI through a multivisit, multicenter study. Retrospective. Fourteen individuals visiting three institutions twice, 10 males with the mean age of 36.3 years and age range 25-51. 3D T1W inversion recovery on three 1.5-T General Electric scanners. Radiomics analysis by a consultant radiologist performed on the T1W images of the whole brain on all visits. All possible radiomics features were generated. Concordance correlation coefficient (CCC) and dynamic range (DR) for all variables were calculated to assess the test-retest repeatability. Intraclass correlation coefficients (ICCs) were calculated to investigate the reproducibility of features across centers. Of 1596 features generated, 57 from center 1, 15 from center 2, and 22 from center 3 had a CCC > 0.9 and DR > 0.9. Eight variables had CCC > 0.9 and DR > 0.9 in all centers. Forty-one variables had an ICC of >0.9. No variables had CCC > 0.9, DR > 0.9, and ICC > 0.9. Repeatability and reproducibility of variables is a significant limitation of radiomics analysis in 3DT1W brain MRI. Careful selection of radiomic features is required. 4 TECHNICAL EFFICACY STAGE: 2.

Efficient Pairwise Neuroimage Analysis Using the Soft Jaccard Index and 3D Keypoint Sets.

We propose a novel pairwise distance measure between image keypoint sets, for the purpose of large-scale medical image indexing. Our measure generalizes the Jaccard index to account for soft set equivalence (SSE) between keypoint elements, via an adaptive kernel framework modeling uncertainty in keypoint appearance and geometry. A new kernel is proposed to quantify the variability of keypoint geometry in location and scale. Our distance measure may be estimated between O (N 2) image pairs in [Formula: see text] operations via keypoint indexing. Experiments report the first results for the task of predicting family relationships from medical images, using 1010 T1-weighted MRI brain volumes of 434 families including monozygotic and dizygotic twins, siblings and half-siblings sharing 100%-25% of their polymorphic genes. Soft set equivalence and the keypoint geometry kernel improve upon standard hard set equivalence (HSE) and appearance kernels alone in predicting family relationships. Monozygotic twin identification is near 100%, and three subjects with uncertain genotyping are automatically paired with their self-reported families, the first reported practical application of image-based family identification. Our distance measure can also be used to predict group categories, sex is predicted with an AUC = 0.97. Software is provided for efficient fine-grained curation of large, generic image datasets.

Hemispheric Cortical, Cerebellar and Caudate Atrophy Associated to Cognitive Impairment in Metropolitan Mexico City Young Adults Exposed to Fine Particulate Matter Air Pollution.

Exposures to fine particulate matter PM2.5 are associated with Alzheimer’s, Parkinson’s (AD, PD) and TDP-43 pathology in young Metropolitan Mexico City (MMC) residents. High-resolution structural T1-weighted brain MRI and/or Montreal Cognitive Assessment (MoCA) data were examined in 302 volunteers age 32.7 ± 6.0 years old. We used multivariate linear regressions to examine cortical surface area and thickness, subcortical and cerebellar volumes and MoCA in ≤30 vs. ≥31 years old. MMC residents were exposed to PM2.5 ~ 30.9 µg/m3. Robust hemispheric differences in frontal and temporal lobes, caudate and cerebellar gray and white matter and strong associations between MoCA total and index scores and caudate bilateral volumes, frontotemporal and cerebellar volumetric changes were documented. MoCA LIS scores are affected early and low pollution controls ≥ 31 years old have higher MoCA vs. MMC counterparts (p ≤ 0.0001). Residency in MMC is associated with cognitive impairment and overlapping targeted patterns of brain atrophy described for AD, PD and Fronto-Temporal Dementia (FTD). MMC children and young adult longitudinal studies are urgently needed to define brain development impact, cognitive impairment and brain atrophy related to air pollution. Identification of early AD, PD and FTD biomarkers and reductions on PM2.5 emissions, including poorly regulated heavy-duty diesel vehicles, should be prioritized to protect 21.8 million highly exposed MMC urbanites.

Differences in subcortical brain volumes among patients with schizophrenia and bipolar disorder and healthy controls.

Background:Patients with schizophrenia and bipolar disorder have an overlapping polygenic architecture and clinical similarities, although the 2 disorders are distinct diagnoses with clinical dissimilarities. It remains unclear whether there are specific differences in subcortical volumes between schizophrenia and bipolar disorder, and whether the subcortical differences are affected by any clinical characteristics. We investigated differences in subcortical volumes bilaterally among patients with schizophrenia, patients with bipolar disorder and healthy controls. We also investigated the influences of clinical characteristics on specific subcortical volumes in these patient groups.Methods:We collected 3 T T1-weighted MRI brain scans from 413 participants (157 with schizophrenia, 51 with bipolar disorder and 205 controls) with a single scanner at a single institute. We used FreeSurfer version 6.0 for processing the T1-weighted images to segment the following subcortical brain volumes: thalamus, caudate, putamen, globus pallidus, hippocampus, amygdala and nucleus accumbens. Differences in the 7 subcortical volumes were investigated among the groups. We also evaluated correlations between subcortical volumes and clinical variables in these patient groups.Results:Of 7 subcortical regions, patients with schizophrenia had significantly smaller volumes in the left thalamus (Cohen d = −0.29, p = 5.83 × 10−3), bilateral hippocampi (left, d = −0.36, p = 8.85 × 10−4; right, d = −0.41, p = 1.15 × 10−4) and left amygdala (d = −0.31, p = 4.02 × 10−3) than controls. Compared with controls, patients with bipolar disorder had bilateral reductions only in the hippocampal volumes (left, d = −0.52, p = 1.12 × 10−3; right, d = −0.58, p = 0.30 × 10−4). We also found that patients with schizophrenia had significantly smaller volumes in the bilateral amygdalae (left, d = −0.43, p = 4.22 × 10−3; right, d = −0.45, p = 4.56 × 10−3) than patients with bipolar disorder. We did not find any significant volumetric differences in the other 6 subcortical structures between patient groups (p > 0.05). Smaller left amygdalar volumes were significantly correlated with younger onset age only in patients with schizophrenia (r = 0.22, p = 5.78 × 10−3).Limitations:We did not evaluate the differences in subcortical volumes between patients stratified based on clinical bipolar disorder subtype and a history of psychotic episodes because our sample size of patients with bipolar disorder was limited.Conclusion:Our findings suggest that volumetric differences in the amygdala between patients with schizophrenia and those with bipolar disorder may be a putative biomarker for distinguishing 2 clinically similar diagnoses.

Negative symptoms in First-Episode Schizophrenia related to morphometric alterations in orbitofrontal and superior temporal cortex: the OPTiMiSE study.

Negative symptoms are one of the most incapacitating features of Schizophrenia but their pathophysiology remains unclear. They have been linked to alterations in grey matter in several brain regions, but findings have been inconsistent. This may reflect the investigation of relatively small patient samples, and the confounding effects of chronic illness and exposure to antipsychotic medication. We sought to address these issues by investigating concurrently grey matter volumes (GMV) and cortical thickness (CTh) in a large sample of antipsychotic-naïve or minimally treated patients with First-Episode Schizophrenia (FES). T1-weighted structural MRI brain scans were acquired from 180 antipsychotic-naïve or minimally treated patients recruited as part of the OPTiMiSE study. The sample was stratified into subgroups with (N = 88) or without (N = 92) Prominent Negative Symptoms (PMN), based on PANSS ratings at presentation. Regional GMV and CTh in the two groups were compared using Voxel-Based Morphometry (VBM) and FreeSurfer (FS). Between-group differences were corrected for multiple comparisons via Family-Wise Error (FWE) and Monte Carlo z-field simulation respectively at p < 0.05 (2-tailed). The presence of PMN symptoms was associated with larger left inferior orbitofrontal volume (p = 0.03) and greater CTh in the left lateral orbitofrontal gyrus (p = 0.007), but reduced CTh in the left superior temporal gyrus (p = 0.009). The findings highlight the role of orbitofrontal and temporal cortices in the pathogenesis of negative symptoms of Schizophrenia. As they were evident in generally untreated FEP patients, the results are unlikely to be related to effects of previous treatment or illness chronicity.

Relationship between Anterior Pituitary Volume and IGF-1 Serum Levels in Soldiers with Mild Traumatic Brain Injury History.

A high mild traumatic brain injury (mTBI) incidence rate exists in military and sport. Hypopituitarism is an mTBI sequela; however, few studies have examined this phenomenon in those with an mTBI history. This cross-sectional study of Special Operations Forces combat soldiers aimed 1) to relate anterior pituitary gland volumes (actual and normalized) to insulin-like growth factor 1 (IGF-1) concentrations, 2) to examine the effect of mTBI history on anterior pituitary gland volumes (actual and normalized) and IGF-1 concentrations, and 3) to measure the odds of demonstrating lower anterior pituitary gland volumes (actual and normalized) or IGF-1 concentrations if self-reporting mTBI history. Anterior pituitary gland volumes were manually segmented from T1-weighted 3D brain MRI sequences; IGF-1 serum concentrations were quantified using commercial enzyme-linked immunosorbent assays. Correlations and linear regression were used to determine the association between IGF-1 serum concentration and anterior pituitary gland volume (n = 74). Independent samples t-tests were used to compare outcomes between mTBI groups and logistic regression models were fit to test the odds of demonstrating IGF-1 concentration or anterior pituitary volume less than sample median based on mTBI group (n = 54). A significant linear relationship between the subjects' anterior pituitary gland volumes and IGF-1 concentrations (r72 = 0.35, P = 0.002) was observed. Soldiers with mTBI history had lower IGF-1 concentrations (P < 0.001) and lower anterior pituitary gland volumes (P = 0.037) and were at greater odds for IGF-1 serum concentrations less than the sample median (odds ratio = 5.73; 95% confidence interval = 1.77-18.55). Anterior pituitary gland volume was associated with IGF-1 serum concentrations. Mild TBI history may be adversely associated with anterior pituitary gland volumes and IGF-1 concentrations. Longitudinal IGF-1 and anterior pituitary gland monitoring may be indicated in those who report one or more mTBI.

Measuring axial length of the eye from magnetic resonance brain imaging

BackgroundMetrics derived from the human eye are increasingly used as biomarkers and endpoints in studies of cardiovascular, cerebrovascular and neurological disease. In this context, it is important to account for potential confounding that can arise from differences in ocular dimensions between individuals, for example, differences in globe size.MethodsWe measured axial length, a geometric parameter describing eye size from T2-weighted brain MRI scans using three different image analysis software packages (Mango, ITK and Carestream) and compared results to biometry measurements from a specialized ophthalmic instrument (IOLMaster 500) as the reference standard.ResultsNinety-three healthy research participants of mean age 51.0 ± SD 5.4 years were analyzed. The level of agreement between the MRI-derived measurements and the reference standard was described by mean differences as follows, Mango − 0.8 mm; ITK − 0.5 mm; and Carestream − 0.1 mm (upper/lower 95% limits of agreement across the three tools ranged from 0.9 mm to − 2.6 mm). Inter-rater reproducibility was between − 0.03 mm and 0.45 mm (ICC 0.65 to 0.93). Intra-rater repeatability was between 0.0 mm and − 0.2 mm (ICC 0.90 to 0.95).ConclusionsWe demonstrate that axial measurements of the eye derived from brain MRI are within 3.5% of the reference standard globe length of 24.1 mm. However, the limits of agreement could be considered clinically significant. Axial length of the eye obtained from MRI is not a replacement for the precision of biometry, but in the absence of biometry it could provide sufficient accuracy to act as a proxy. We recommend measuring eye axial length from MRI in studies that do not have biometry but use retinal imaging to study neurodegenerative changes so as to control for differing eye size across individuals.

Efficient Claustrum Segmentation in T2-weighted Neonatal Brain MRI Using Transfer Learning from Adult Scans

PurposeIntrauterine claustrum and subplate neuron development have been suggested to overlap. As premature birth typically impairs subplate neuron development, neonatal claustrum might indicate a specific prematurity impact; however, claustrum identification usually relies on expert knowledge due to its intricate structure. We established automated claustrum segmentation in newborns.MethodsWe applied a deep learning-based algorithm for segmenting the claustrum in 558 T2-weighted neonatal brain MRI of the developing Human Connectome Project (dHCP) with transfer learning from claustrum segmentation in T1-weighted scans of adults. The model was trained and evaluated on 30 manual bilateral claustrum annotations in neonates.ResultsWith only 20 annotated scans, the model yielded median volumetric similarity, robust Hausdorff distance and Dice score of 95.9%, 1.12 mm and 80.0%, respectively, representing an excellent agreement between the automatic and manual segmentations. In comparison with interrater reliability, the model achieved significantly superior volumetric similarity (p = 0.047) and Dice score (p < 0.005) indicating stable high-quality performance. Furthermore, the effectiveness of the transfer learning technique was demonstrated in comparison with nontransfer learning. The model can achieve satisfactory segmentation with only 12 annotated scans. Finally, the model’s applicability was verified on 528 scans and revealed reliable segmentations in 97.4%.ConclusionThe developed fast and accurate automated segmentation has great potential in large-scale study cohorts and to facilitate MRI-based connectome research of the neonatal claustrum. The easy to use models and codes are made publicly available.

Automatic quality control of brain T1-weighted magnetic resonance images for a clinical data warehouse.

Many studies on machine learning (ML) for computer-aided diagnosis have so far been mostly restricted to high-quality research data. Clinical data warehouses, gathering routine examinations from hospitals, offer great promises for training and validation of ML models in a realistic setting. However, the use of such clinical data warehouses requires quality control (QC) tools. Visual QC by experts is time-consuming and does not scale to large datasets. In this paper, we propose a convolutional neural network (CNN) for the automatic QC of 3D T1-weighted brain MRI for a large heterogeneous clinical data warehouse. To that purpose, we used the data warehouse of the hospitals of the Greater Paris area (Assistance Publique-Hôpitaux de Paris [AP-HP]). Specifically, the objectives were: 1) to identify images which are not proper T1-weighted brain MRIs; 2) to identify acquisitions for which gadolinium was injected; 3) to rate the overall image quality. We used 5000 images for training and validation and a separate set of 500 images for testing. In order to train/validate the CNN, the data were annotated by two trained raters according to a visual QC protocol that we specifically designed for application in the setting of a data warehouse. For objectives 1 and 2, our approach achieved excellent accuracy (balanced accuracy and F1-score >90%), similar to the human raters. For objective 3, the performance was good but substantially lower than that of human raters. Nevertheless, the automatic approach accurately identified (balanced accuracy and F1-score >80%) low quality images, which would typically need to be excluded. Overall, our approach shall be useful for exploiting hospital data warehouses in medical image computing.

An Enlarged Perivascular Space: Clinical Relevance and the Role of Imaging in Aging and Neurologic Disorders

혈관주위공간(perivascular space; 이하 PVS)는 뇌 실질을 관통하는 세동맥 둘러싸고 있는 공간으로, 최근에는 별아교세포의 종족(astrocyte endfoot)에 의해 가장 바깥쪽이 경계지워지는, 체액, 세포, 결합조직으로 구성된 혈관벽내, 혈관벽 주위의 구획을 모두 아우르는 개념으로 이해하고 있다. 정상적으로는 현미경적 해부학 구조물이지만 이 구조물이 늘어나게 되면 MRI T1 혹은 T2 이미지에서 확인할 수 있게 된다. PVS의 명확한 실체나 임상적인 의의에 대해서는 아직 분명치 않은 부분이 많이 있지만 PVS의 확장(enlarged PVS; 이하 EPVS)은 다양한 퇴행성 뇌질환 뿐만 아니라 뇌출혈 및 외상성 뇌손상, 당뇨성 신질환 같은 다양한 질병과의 연관성이 있다는 연구 결과들이 발표되고 있다. 이번 종설에서는 PVS와 EPVS가 가지는 임상적 의의와 병태 생리에 대한 최근 문헌을 고찰하고, MRI를 이용한 정성적 평가 및 최적화에 대해 논의해 보고자 한다.

Nervus Intermedius Neuralgia With Vestibular Paroxysmia -A Rare Combination of Nerve Compression Syndromes

Introduction: Posterior cranial fossa nerve compressions in a rare combination are discussed here. Case Reports: 51 year old male with intractable vertigo, vomiting and left ear ache, had left spontaneous nystagmus. Another 25 year old female had recurrent ear ache and vertigo.Both MRI Brain showed compression of VII/VIII nerve complex in the cistern. They were given Ox carbamazepine with supportive therapy tapered with no recurrence in past 1 year. Discussion: The combination of the 7th and 8th cranial neuralgias presents with common symptomatology. The investigation of choice is HR T2 weighted MRI brain (CISS/FIESTA SPACE sequence), treated medically. Surgically, decompression or nerve sectioning are done. Conclusion: Though rare due to different positions of the nerve entry/exit zones of these nerves, this combination of posterior cranial fossa nerve compression syndromes can coexist. Diagnosis can help in the proper management of such patients and even open the hori-zon for surgical options in recalcitrant cases.

Position of Tonsillar Tip in Relation to Foramen Magnum in Children with Structurally Normal MRI Brain Imaging

Introduction: The position of the tonsillar tip in relation to the foramen magnum varies from individual to individual, even after excluding all predisposing factors that might alter the tonsillar tip position; the mere presence of the tonsillar ectopia should not be misinterpreted as Chiari malformation. Aim: Our aim is to establish the normal range of the tonsillar tip position and the incidence of tonsillar ectopia and its relation to age and sex in asymptomatic Indian children with structurally normal MRI brain imaging. Materials and Methods: We have conducted a retrospective data collection comprising 301 structurally normal MRI brain images done for children younger than 14 years, in which we measured the level of the tonsillar tip from the foramen magnum by taking the Mc Rae line as constant. Measurements were taken in the right and left parasagittal sections of T1-weighted MRI brain images by using pre-existing software. Statistical Analysis Used: Data analysis was done by SPSS v 25.0; all P values &lt;0.05 were considered statistically significant. Results and Conclusion: The incidence of tonsillar ectopia in Indian children was about 13.79%, and the median tonsillar position was 3.2 mm above the foramen magnum with a median range of 5.2 mm above to the level of the foramen magnum (0).

A homozygous ABHD16A variant causes a complex hereditary spastic paraplegia with developmental delay, absent speech, and characteristic face

Hereditary spastic paraplegia (HSP) is a genetically and clinically heterogeneous genetic disease characterized by progressive weakness and spasticity predominantly affecting the lower limbs. Complex HSP is a subset of HSP presenting with additional neuronal and/or non-neuronal phenotypes. Here, we identify a homozygous ABHD16A nonsense variant in two affected children in a Chilean family. Very recently, two groups reported patients with biallelic ABHD16A whose clinical presentation was similar to that of our patients. By reviewing the clinical features of these reports and our patients, ABHD16A-related HSP can be characterized by early childhood onset, developmental delay, intellectual disability, speech disturbance, extrapyramidal signs, psychiatric features, no sphincter control, skeletal involvement, thin corpus callosum, and high-intensity signals in white matter on T2-weighted brain MRI. In addition, our affected siblings showed a characteristic face, sleep disturbance, and nodular and hyperpigmented skin lesions, which have not previously been reported in this condition.

Case Report: A Case of Encephalopathy Presenting the Lentiform Fork Sign on MRI in a Diabetic Dialysis Patient

Basal ganglia lesions showing an expansile high signal intensity on T2-weighted MRI are termed the lentiform fork sign. This specific finding is mainly observed in diabetic patients with uremic encephalopathy with metabolic acidosis, although there are also reports in patients with ketoacidosis, dialysis disequilibrium syndrome, intoxication, and following drug treatment (e.g., metformin). A 57-year-old Japanese man on chronic hemodialysis for 4 years because of diabetic nephropathy was admitted to our hospital for relatively rapid-onset gait disturbance, severe dysarthria, and consciousness disturbance. Brain T2-weighted MRI showed the lentiform fork sign. Hemodialysis was performed the day before admission, and laboratory tests showed mild metabolic (lactic) acidosis, but no uremia. Surprisingly, metformin, which is contraindicated for patients with end-stage kidney disease, had been prescribed for 6 months in his medication record, and his sluggish speaking and dysarthria appeared gradually after metformin treatment was started. Thus, the encephalopathy was considered to be related to metformin treatment. He received hemodialysis treatment for 6 consecutive days, and his consciousness disturbance and dysarthria improved in 1 week. At the 8-month follow-up, the size of the hyperintensity area on MRI had decreased, while the mild gait disturbance remained. Considering the rapid onset of gait and consciousness disturbance immediately before admission, diabetic uremic syndrome may also have occurred with metformin-related encephalopathy, and resulted in the lentiform fork sign, despite the patient showing no evidence of severe uremia on laboratory data.