Mesial Temporal Sclerosis: Accuracy of NeuroQuant versus Neuroradiologist

Neurofind: using deep learning to make individualised inferences in brain-based disorders

Within precision psychiatry, there is a growing interest in normative models given their ability to parse heterogeneity. While they are intuitive and informative, the technical expertise and resources required to develop normative models may not be accessible to most researchers. Here we present Neurofind, a new freely available tool that bridges this gap by wrapping sound and previously tested methods on data harmonisation and advanced normative models into a web-based platform that requires minimal input from the user. We explain how Neurofind was developed, how to use the Neurofind website in four simple steps ( www.neurofind.ai ), and provide exemplar applications. Neurofind takes as input structural MRI images and outputs two main metrics derived from independent normative models: (1) Outlier Index Score, a deviation score from the normative brain morphology, and (2) Brain Age, the predicted age based on an individual's brain morphometry. The tool was trained on 3362 images of healthy controls aged 20-80 from publicly available datasets. The volume of 101 cortical and subcortical regions was extracted and modelled with an adversarial autoencoder for the Outlier index model and a support vector regression for the Brain age model. To illustrate potential applications, we applied Neurofind to 364 images from three independent datasets of patients diagnosed with Alzheimer's disease and schizophrenia. In Alzheimer's disease, 55.2% of patients had very extreme Outlier Index Scores, mostly driven by larger deviations in temporal-limbic structures and ventricles. Patients were also homogeneous in how they deviated from the norm. Conversely, only 30.1% of schizophrenia patients were extreme outliers, due to deviations in the hippocampus and pallidum, and patients tended to be more heterogeneous than controls. Both groups showed signs of accelerated brain ageing.

Adding the third dimension: 3D convolutional neural network diagnosis of temporal lobe epilepsy

Convolutional neural networks (CNN) show great promise for translating decades of research on structural abnormalities in temporal lobe epilepsy into clinical practice. Three-dimensional CNNs typically outperform two-dimensional CNNs in medical imaging. Here we explore for the first time whether a three-dimensional CNN outperforms a two-dimensional CNN for identifying temporal lobe epilepsy-specific features on MRI. Using 1178 T1-weighted images (589 temporal lobe epilepsy, 589 healthy controls) from 12 surgical centres, we trained 3D and 2D CNNs for temporal lobe epilepsy versus healthy control classification, using feature visualization to identify important regions. The 3D CNN was compared to the 2D model and to a randomized model (comparison to chance). Further, we explored the effect of sample size with subsampling, examined model performance based on single-subject clinical characteristics, and tested the impact of image harmonization on model performance. Across 50 datapoints (10 runs with 5-folds each) the 3D CNN median accuracy was 86.4% (35.3% above chance) and the median F1-score was 86.1% (33.3% above chance). The 3D model yielded higher accuracy compared to the 2D model on 84% of datapoints (median 2D accuracy, 83.0%), a significant outperformance for the 3D model (binomial test: P < 0.001). This advantage of the 3D model was only apparent at the highest sample size. Saliency maps exhibited the importance of medial-ventral temporal, cerebellar, and midline subcortical regions across both models for classification. However, the 3D model had higher salience in the most important regions, the ventral-medial temporal and midline subcortical regions. Importantly, the model achieved high accuracy (82% accuracy) even in patients without MRI-identifiable hippocampal sclerosis. Finally, applying ComBat for harmonization did not improve performance. These findings highlight the value of 3D CNNs for identifying subtle structural abnormalities on MRI, especially in patients without clinically identified temporal lobe epilepsy lesions. Our findings also reveal that the advantage of 3D CNNs relies on large sample sizes for model training.

Radiologic Classification of Hippocampal Sclerosis in Epilepsy

Temporal lobe epilepsy is a common form of epilepsy that is often associated with hippocampal sclerosis (HS). Although HS is commonly considered a binary assessment in radiologic evaluation, it is known that histopathologic changes occur in distinct clusters. Some subtypes of HS only affect certain subfields, resulting in minimal changes to the overall volume of the hippocampus. This is likely a major reason why whole hippocampal volumetrics have underperformed versus expert readers in the diagnosis of HS. With recent advancements in MRI technology, it is now possible to characterize the substructure of the hippocampus more accurately. However, this is not consistently addressed in radiographic evaluations. The histologic subtype of HS is critical for prognosis and treatment decision-making, necessitating improved radiologic classification of HS. The International League Against Epilepsy (ILAE) has issued a consensus classification scheme for subtyping HS histopathologic changes. This review aims to explore how the ILAE subtypes of HS correlate with radiographic findings, introduce a grading system that integrates radiologic and pathologic reporting in HS, and outline an approach to detecting HS subtypes by using MRI. This framework will not only benefit current clinical evaluations, but also enhance future studies involving high-resolution MRI in temporal lobe epilepsy.

An ordinal clinical score predicts seizure freedom after minimally invasive epilepsy surgery

OBJECTIVE

To predict one-year seizure freedom, using a combination of relevant clinical variables, following stereotactic laser amygdalohippocampotomy for mesial temporal lobe epilepsy in a series of 101 patients.

METHODS

Eight predictors of seizure freedom were selected based on their association with medial temporal lobe epilepsy: (1) MRI evidence of mesial temporal sclerosis (MTS); (2) unitemporal interictal epileptiform discharges; (3) absence of generalized tonic-clonic seizures; (4) history of febrile seizures; (5) onset of epilepsy ≤16 years; (6) absence of an auditory, visual, or vertiginous aura; and (7) unitemporal ictal onset; (8) unitemporal PET hypometabolism. We compared four multivariate models: "MTS," using just evidence of MTS; "FULL," using all eight binary predictors; "AIC" using backwards selection of variables; and "SCORE," using a 0-to-8-point ordinal score awarding one point for each binary predictor.

RESULTS

In univariate analysis, significant predictors for seizure freedom were evidence of mesial temporal sclerosis (p = 0.011, Fisher exact) and unitemporal interictal discharges (p = 0.005). For multivariate prediction (using leave one-out cross-validation), the ordinal SCORE model had a significantly higher area under the curve (AUC 0.70) than the other three models: MTS (AUC 0.54, p = 0.002, Delong's test), FULL (AUC 0.62, p = 0.003), or AIC (AUC 0.53, p < 0.001).

INTERPRETATION

An ordinal score incorporating eight independent binary clinical variables predicted seizure freedom better on novel data than a model using MTS alone, a full multivariate model, or a backwards selected model. The ordinal score model represents a simple clinical heuristic to identify which patients should be offered minimally invasive laser surgery.

Discriminant analysis using MRI asymmetry indices and cognitive scores of women with temporal lobe epilepsy or schizophrenia

PURPOSE

This study aims to assess the diagnostic power of brain asymmetry indices and neuropsychological tests for differentiating mesial temporal lobe epilepsy (MTLE) and schizophrenia (SCZ).

METHODS

We studied a total of 39 women including 13 MTLE, 13 SCZ, and 13 healthy individuals (HC). A neuropsychological test battery (NPT) was administered and scored by an experienced neuropsychologist, and NeuroQuant (CorTechs Labs Inc., San Diego, California) software was used to calculate brain asymmetry indices (ASI) for 71 different anatomical regions of all participants based on their 3D T1 MR imaging scans.

RESULTS

Asymmetry indices measured from 10 regions showed statistically significant differences between the three groups. In this study, a multi-class linear discriminant analysis (LDA) model was built based on a total of fifteen variables composed of the most five significantly informative NPT scores and ten significant asymmetry indices, and the model achieved an accuracy of 87.2%. In pairwise classification, the accuracy for distinguishing MTLE from either SCZ or HC was 94.8%, while the accuracy for distinguishing SCZ from either MTLE or HC was 92.3%.

CONCLUSION

The ability to differentiate MTLE from SCZ using neuroradiological and neuropsychological biomarkers, even within a limited patient cohort, could make a substantial contribution to research in larger patient groups using different machine learning techniques.

FDA-approved machine learning algorithms in neuroradiology: A systematic review of the current evidence for approval

Over the past decade, machine learning (ML) and artificial intelligence (AI) have become increasingly prevalent in the medical field. In the United States, the Food and Drug Administration (FDA) is responsible for regulating AI algorithms as "medical devices" to ensure patient safety. However, recent work has shown that the FDA approval process may be deficient. In this study, we evaluate the evidence supporting FDA-approved neuroalgorithms, the subset of machine learning algorithms with applications in the central nervous system (CNS), through a systematic review of the primary literature. Articles covering the 53 FDA-approved algorithms with applications in the CNS published in PubMed, EMBASE, Google Scholar and Scopus between database inception and January 25, 2022 were queried. Initial searches identified 1505 studies, of which 92 articles met the criteria for extraction and inclusion. Studies were identified for 26 of the 53 neuroalgorithms, of which 10 algorithms had only a single peer-reviewed publication. Performance metrics were available for 15 algorithms, external validation studies were available for 24 algorithms, and studies exploring the use of algorithms in clinical practice were available for 7 algorithms. Papers studying the clinical utility of these algorithms focused on three domains: workflow efficiency, cost savings, and clinical outcomes. Our analysis suggests that there is a meaningful gap between the FDA approval of machine learning algorithms and their clinical utilization. There appears to be room for process improvement by implementation of the following recommendations: the provision of compelling evidence that algorithms perform as intended, mandating minimum sample sizes, reporting of a predefined set of performance metrics for all algorithms and clinical application of algorithms prior to widespread use. This work will serve as a baseline for future research into the ideal regulatory framework for AI applications worldwide.

Convolutional Neural Network Algorithm to Determine Lateralization of Seizure Onset in Patients With Epilepsy: A Proof-of-Principle Study

BACKGROUND AND OBJECTIVES

A new frontier in diagnostic radiology is the inclusion of machine-assisted support tools that facilitate the identification of subtle lesions often not visible to the human eye. Structural neuroimaging plays an essential role in the identification of lesions in patients with epilepsy, which often coincide with the seizure focus. In this study, we explored the potential for a convolutional neural network (CNN) to determine lateralization of seizure onset in patients with epilepsy using T1-weighted structural MRI scans as input.

METHODS

Using a dataset of 359 patients with temporal lobe epilepsy (TLE) from 7 surgical centers, we tested whether a CNN based on T1-weighted images could classify seizure laterality concordant with clinical team consensus. This CNN was compared with a randomized model (comparison with chance) and a hippocampal volume logistic regression (comparison with current clinically available measures). Furthermore, we leveraged a CNN feature visualization technique to identify regions used to classify patients.

RESULTS

Across 100 runs, the CNN model was concordant with clinician lateralization on average 78% (SD = 5.1%) of runs with the best-performing model achieving 89% concordance. The CNN outperformed the randomized model (average concordance of 51.7%) on 100% of runs with an average improvement of 26.2% and outperformed the hippocampal volume model (average concordance of 71.7%) on 85% of runs with an average improvement of 6.25%. Feature visualization maps revealed that in addition to the medial temporal lobe, regions in the lateral temporal lobe, cingulate, and precentral gyrus aided in classification.

DISCUSSION

These extratemporal lobe features underscore the importance of whole-brain models to highlight areas worthy of clinician scrutiny during temporal lobe epilepsy lateralization. This proof-of-concept study illustrates that a CNN applied to structural MRI data can visually aid clinician-led localization of epileptogenic zone and identify extrahippocampal regions that may require additional radiologic attention.

CLASSIFICATION OF EVIDENCE

This study provides Class II evidence that in patients with drug-resistant unilateral temporal lobe epilepsy, a convolutional neural network algorithm derived from T1-weighted MRI can correctly classify seizure laterality.

Automated detection of hippocampal sclerosis using real-world clinical MRI images

Background

Hippocampal sclerosis (HS) is the most common pathological type of temporal lobe epilepsy (TLE) and one of the important surgical markers. Currently, HS is mainly diagnosed manually by radiologists based on visual inspection of MRI, which greatly relies on MRI quality and physician experience. In clinical practice, non-thin MRI scans are often used due to the time and efficiency needed for the acquisition. However, these scans can be difficult for junior physicians to interpret accurately. Thus, the rapid and accurate diagnosis of HS using real-world MRI images in clinical settings is a challenging task.

Objective

Our aim was to explore the feasibility of using computer vision methods to diagnose HS on real-world clinical MRI images and to provide a reference for future clinical applications of artificial intelligence methods to aid in detecting HS.

Methods

We proposed a deep learning algorithm called "HS-Net" to discriminate HS using real-world clinical MRI images. First, we delineated and segmented a region of interest (ROI) around the hippocampus. Then, we utilized the fractional differential (FD) method to enhance the textures of the ROIs. Finally, we used a small-sample image classification method based on transfer learning to fine-tune the feature extraction part of a pretrained model and added two fully connected layers and an output layer. In the study, 96 TLE patients with HS confirmed by postoperative pathology and 89 healthy controls were retrospectively enrolled. All subjects were cross-validated, and models were evaluated for performance, robustness, and clinical utility.

Results

The HS-Net model achieved an area under the curve (AUC) of 0.894, an accuracy of 82.88%, an F1-score of 84.08% in the test cohort based on real, routine, clinical T2-weighted fluid attenuated inversion recovery (FLAIR) sequence MRI images. Additionally, the AUC, accuracy and F1 scores of our model all increased by around 3 percentage points when the inputs were augmented with the ROIs of the textures enhanced using the FD method.

Conclusions

Our computational model has the potential to be used for the diagnosis of HS in real clinical MRI images, which could assist physicians, particularly junior physicians, in improving the accuracy of discrimination.

Epilepsy in Pediatric Patients—Evaluation of Brain Structures’ Volume Using VolBrain Software

Epilepsy is one of the most frequent serious brain disorders. Approximately 30,000 of the 150,000 children and adolescents who experience unprovoked seizures are diagnosed with epilepsy each year. Magnetic resonance imaging is the method of choice in diagnosing and monitoring patients with this condition. However, one very effective tool using MR images is volBrain software, which automatically generates information about the volume of brain structures. A total of 57 consecutive patients (study group) suffering from epilepsy and 34 healthy patients (control group) who underwent MR examination qualified for the study. Images were then evaluated by volBrain. Results showed atrophy of the brain and particular structures—GM, cerebrum, cerebellum, brainstem, putamen, thalamus, hippocampus and nucleus accumbens volume. Moreover, the statistically significant difference in the volume between the study and the control group was found for brain, lateral ventricle and putamen. A volumetric analysis of the CNS in children with epilepsy confirms a decrease in the volume of brain tissue. A volumetric assessment of brain structures based on MR data has the potential to be a useful diagnostic tool in children with epilepsy and can be implemented in clinical work; however, further studies are necessary to enhance the effectiveness of this software.

Detecting Primary Progressive Aphasia Atrophy Patterns: A Comparison of Visual Assessment and Quantitative Neuroimaging Techniques

Background: There are now clinically available automated MRI analysis software programs that compare brain volumes of patients to a normative sample and provide z-score data for various brain regions. These programs have yet to be validated in primary progressive aphasia (PPA). Objective: To address this gap in the literature, we examined Neuroreadertrademark z-scores in PPA, relative to visual MRI assessment. We predicted that Neuroreadertrademark 1) would be more sensitive for detecting left >  right atrophy in the cortical lobar regions in logopenic variant PPA clinical phenotype (lvPPA), and 2) would distinguish lvPPA (n = 11) from amnestic mild cognitive impairment (aMCI; n = 12). Methods: lvPPA or aMCI patients who underwent MRI with Neuroreadertrademark were included in this study. Two neuroradiologists rated 10 regions. Neuroreadertrademark lobar z-scores for those 10 regions, as well as a hippocampal asymmetry metric, were included in analyses. Results: Cohen’s Kappa coefficients were significant in 10 of the 28 computations (k = 0.351 to 0.593, p≤0.029). Neuroradiologists agreed 0% of the time that left asymmetry was present across regions. No significant differences emerged between aMCI and lvPPA in Neuroreadertrademark z-scores across left or right frontal, temporal, or parietal regions (ps >  0.10). There were significantly lower z-scores in the left compared to right for the hippocampus, as well as parietal, occipital, and temporal cortices in lvPPA. Conclusion: Overall, our results indicated moderate to low interrater reliability, and raters never agreed that left asymmetry was present. While lower z-scores in the left hemisphere regions emerged in lvPPA, Neuroreadertrademark failed to differentiate lvPPA from aMCI.

Updated Review of the Evidence Supporting the Medical and Legal Use of NeuroQuant® and NeuroGage® in Patients With Traumatic Brain Injury

Over 40 years of research have shown that traumatic brain injury affects brain volume. However, technical and practical limitations made it difficult to detect brain volume abnormalities in patients suffering from chronic effects of mild or moderate traumatic brain injury. This situation improved in 2006 with the FDA clearance of NeuroQuant®, a commercially available, computer-automated software program for measuring MRI brain volume in human subjects. More recent strides were made with the introduction of NeuroGage®, commercially available software that is based on NeuroQuant® and extends its utility in several ways. Studies using these and similar methods have found that most patients with chronic mild or moderate traumatic brain injury have brain volume abnormalities, and several of these studies found-surprisingly-more abnormal enlargement than atrophy. More generally, 102 peer-reviewed studies have supported the reliability and validity of NeuroQuant® and NeuroGage®. Furthermore, this updated version of a previous review addresses whether NeuroQuant® and NeuroGage® meet the Daubert standard for admissibility in court. It concludes that NeuroQuant® and NeuroGage® meet the Daubert standard based on their reliability, validity, and objectivity. Due to the improvements in technology over the years, these brain volumetric techniques are practical and readily available for clinical or forensic use, and thus they are important tools for detecting signs of brain injury.

Technical and clinical validation of commercial automated volumetric MRI tools for dementia diagnosis-a systematic review

Developments in neuroradiological MRI analysis offer promise in enhancing objectivity and consistency in dementia diagnosis through the use of quantitative volumetric reporting tools (QReports). Translation into clinical settings should follow a structured framework of development, including technical and clinical validation steps. However, published technical and clinical validation of the available commercial/proprietary tools is not always easy to find and pathways for successful integration into the clinical workflow are varied. The quantitative neuroradiology initiative (QNI) framework highlights six necessary steps for the development, validation and integration of quantitative tools in the clinic. In this paper, we reviewed the published evidence regarding regulatory-approved QReports for use in the memory clinic and to what extent this evidence fulfils the steps of the QNI framework. We summarize unbiased technical details of available products in order to increase the transparency of evidence and present the range of reporting tools on the market. Our intention is to assist neuroradiologists in making informed decisions regarding the adoption of these methods in the clinic. For the 17 products identified, 11 companies have published some form of technical validation on their methods, but only 4 have published clinical validation of their QReports in a dementia population. Upon systematically reviewing the published evidence for regulatory-approved QReports in dementia, we concluded that there is a significant evidence gap in the literature regarding clinical validation, workflow integration and in-use evaluation of these tools in dementia MRI diagnosis.

Accuracy of MRI Classification Algorithms in a Tertiary Memory Center Clinical Routine Cohort

BACKGROUND

Automated volumetry software (AVS) has recently become widely available to neuroradiologists. MRI volumetry with AVS may support the diagnosis of dementias by identifying regional atrophy. Moreover, automatic classifiers using machine learning techniques have recently emerged as promising approaches to assist diagnosis. However, the performance of both AVS and automatic classifiers have been evaluated mostly in the artificial setting of research datasets.

OBJECTIVE

Our aim was to evaluate the performance of two AVS and an automatic classifier in the clinical routine condition of a memory clinic.

METHODS

We studied 239 patients with cognitive troubles from a single memory center cohort. Using clinical routine T1-weighted MRI, we evaluated the classification performance of: 1) univariate volumetry using two AVS (volBrain and Neuroreader™); 2) Support Vector Machine (SVM) automatic classifier, using either the AVS volumes (SVM-AVS), or whole gray matter (SVM-WGM); 3) reading by two neuroradiologists. The performance measure was the balanced diagnostic accuracy. The reference standard was consensus diagnosis by three neurologists using clinical, biological (cerebrospinal fluid) and imaging data and following international criteria.

RESULTS

Univariate AVS volumetry provided only moderate accuracies (46% to 71% with hippocampal volume). The accuracy improved when using SVM-AVS classifier (52% to 85%), becoming close to that of SVM-WGM (52 to 90%). Visual classification by neuroradiologists ranged between SVM-AVS and SVM-WGM.

CONCLUSION

In the routine practice of a memory clinic, the use of volumetric measures provided by AVS yields only moderate accuracy. Automatic classifiers can improve accuracy and could be a useful tool to assist diagnosis.

Automated detection of hippocampal sclerosis: Comparison of a composite MRI-based index with conventional MRI measures

PURPOSE

This study aims to compare the performance of an MRI-based composite index (HSI) with conventional MRI-based measures in hippocampal sclerosis (HS) detection and postoperative outcome estimation.

METHODS

Seventy-two temporal lobe epilepsy (TLE) patients with pathologically confirmed HS and fifteen TLE patients without HS were included retrospectively. The T1-weighted and FLAIR images of these patients were processed with AccuBrain to quantify the hippocampal volume (HV) and the hippocampal FLAIR signal. The HSI index that considered both HV and hippocampal FLAIR signal was also calculated. Two experienced neuropathologists rated the HS severity with the resected tissue and reached an agreement for all cases. The asymmetry indices of the MRI measures were used to lateralize the sclerotic side, and the original MRI measures were applied to detect HS vs. normal hippocampi. Operating characteristic curve (ROC) analyses were performed for these predictions. We also investigated the sensitivity of the ipsilateral MRI measures in characterizing the pathological severity of HS and the associations of the MRI measures with postoperative outcomes (Engel class categories).

RESULTS

With the optimal cutoffs, the asymmetry indices of HSI and HV both achieved excellent performance in differentiating left vs. right HS (accuracy = 100 %), and the absolute value of the asymmetry index of HSI performed best in differentiating unilateral vs. bilateral HS (accuracy = 91.7 %). Regarding the detection of HS, HSI performed better in sensitivity (94.4 % vs. 87.5 %) while HV performed better in specificity (93.6 % vs. 89.4 %) when the contralateral site of unilateral HS and both sides of non-HS patients were considered as the normal reference, and HSI performed even better than HV when only both sides of non-HS patients were considered as the normal reference (AUC: 0.956 vs. 0.934, p = 0.038). The ipsilateral HSI presented the strongest association with the pathological rating of HS severity (r = 0.405, p < 0.001). None of the ipsilateral or contralateral MRI measures was associated with the postoperative outcomes. Among the asymmetry indices, only the absolute value of the asymmetry index of HV presented a significant association with the Engel classifications for the Year 2∼3 visit (r = -0.466, p = 0.004) or the latest visit with >1 year follow-up (r = -0.374, p = 0.003) while controlling for disease duration and follow-up duration.

CONCLUSION

The HSI index and HV presented comparable good performance in HS detection, and HSI may have better sensitivity than HV in differentiating pathological HS severity. Higher magnitude of HV dissymmetry may indicate better post-surgical outcomes for HS patients.

Expert Opinions and Recommendations for the Clinical Use of Quantitative Analysis Software for MRI-Based Brain Volumetry

치매를 비롯한 퇴행성 신경 질환의 초기 진단에 자기공명영상을 이용한 뇌 위축 평가와 정량적 용적 분석이 중요하다. 뇌 위축의 시각적 평가는 주관적으로 평가자에 따라 다른 결과를 보여주기 때문에, 객관적인 결과를 제공하면서 임상 적용도 가능한 소프트웨어의 수요와 개발이 늘어나고 있다. 이러한 임상용 소프트웨어의 실제 임상 적용은 영상 검사의 표준화가 선행되어야 하고, 개발된 소프트웨어의 검증이 반드시 필요하다. 따라서 대한신경두경부영상의학회는 뇌용적 분석 임상용 소프트웨어의 임상적 활용에 대한 의견을 제시하기 위해 전문위원회를 구성하고 현재까지 발표된 연구를 정리하였다. 그리고, 정량화 분석을 위한 영상 검사의 표준화 및 소프트웨어의 임상 적용에 대한 전문가 의견을 제시하기 위하여 공동 작업을 수행하였다. 본 종설에서는 뇌 자기공명영상의 정량화 분석의 필요성 및 배경, 정량화 분석을 위한 임상용 소프트웨어의 소개 및 기존의 표준품(reference standard)과의 진단능 비교, 영상 획득의 표준화, 분석 및 평가의 표준화, 소프트웨어의 임상 적용에 대한 전문가 의견, 제한점 및 대처 방법 등 대한신경두경부영상의학회의 전문가 권고안을 소개하는 것이 목적이다.

Voxel-Based Morphometry-from Hype to Hope. A Study on Hippocampal Atrophy in Mesial Temporal Lobe Epilepsy

BACKGROUND AND PURPOSE

Automated volumetry of the hippocampus is considered useful to assist the diagnosis of hippocampal sclerosis in temporal lobe epilepsy. However, voxel-based morphometry is rarely used for individual subjects because of high rates of false-positives. We investigated whether an approach with high dimensional warping to the template and nonparametric statistics would be useful to detect hippocampal atrophy in patients with hippocampal sclerosis.

MATERIALS AND METHODS

We performed single-subject voxel-based morphometry with nonparametric statistics within the framework of Statistical Parametric Mapping to compare MRI from 26 well-characterized patients with temporal lobe epilepsy individually against a group of 110 healthy controls. The following statistical threshold was used: P < .05 corrected for multiple comparisons with family-wise error over the region of interest right and left hippocampus.

RESULTS

The sensitivity for the detection of atrophy related to hippocampal sclerosis was 0.92 (95% CI, 0.67-0.99) for the right hippocampus and 0.60 (0.31-0.83) for the left, and the specificity for volume changes was 0.98 (0.93-0.99). All clusters of decreased hippocampal volumes were correctly lateralized to the seizure focus. Hippocampal volume decrease was in accordance with neuronal cell loss on histology reports.

CONCLUSIONS

Nonparametric voxel-based morphometry is sensitive and specific for hippocampal atrophy in patients with mesial temporal lobe epilepsy and may be useful in clinical practice.

Assessment of White Matter Integrity after Pediatric Traumatic Brain Injury

White matter (WM) abnormalities, such as atrophy and hyperintensities (WMH), can be accessed via magnetic resonance imaging (MRI) after pediatric traumatic brain injury (TBI). Several methods are available to classify WM abnormalities (i.e., total WM volumes and WMHs), but automated and manual volumes and clinical ratings have yet to be compared in pediatric TBI. In addition, WM integrity has been associated reliably with processing speed. Consequently, methods of assessing WM integrity should relate to processing speed to have clinical application. This study had two goals: (1) to compare Scheltens rating scale, manual tracing, FreeSurfer, and NeuroQuant® methods of assessing WM abnormalities, and (2) to relate WM methods to processing speed scores. We report findings from the Social Outcomes of Brain Injury in Kids (SOBIK) study, a multi-center study of 60 children with chronic TBI (65% male) from ages 8-13. Scheltens WMH ratings had good to excellent agreement with WMH volumes for both NeuroQuant (ICC = 0.62; r = 0.29, p = 0.005) and manual tracing (ICC = 0.82; r = 0.50, p = 0.000). NeuroQuant WMH volumes did not correlate with manually traced WMH volumes (r = 0.12, p = 0.21) and had poor agreement (ICC = 0.24). NeuroQuant and FreeSurfer total WM volumes correlated (r = 0.38, p = 0.004) and had fair agreement (ICC = 0.52). The WMH assessment methods, both ratings and volumes, were associated with processing speed scores. In contrast, total WM volume was not related to processing speed. Measures of WMH may hold clinical utility for predicting cognitive functioning after pediatric TBI.

Diagnosis of Hippocampal Sclerosis in Children: Comparison of Automated Brain MRI Volumetry and Readers of Varying Experience

BACKGROUND. Hippocampal sclerosis (HS) is a leading cause of medically refractory temporal lobe epilepsy in children. The diagnosis is clinically important because most patients with HS have good postsurgical outcomes. OBJECTIVE. This study aimed to compare the performance of a fully automated brain MRI volumetric tool and readers of varying experience in the diagnosis of pediatric HS. METHODS. This retrospective study included 22 children with HS diagnosed between January 2009 and January 2020 who underwent surgery and an age- and sex-matched control group of 44 patients with normal MRI findings and extratemporal epilepsy diagnosed between January 2009 and January 2020. Regional brain MRI volumes were calculated from a high-resolution 3D T1-weighted sequence using an automated volumetric tool. Four readers (two pediatric radiologists [experienced] and two radiology residents [inexperienced]) visually assessed each MRI examination to score the likelihood of HS. One inexperienced reader repeated the evaluations using the volumetric tool. The area under the ROC curve (AUROC), sensitivity, and specificity for HS were computed for the volumetric tool and the readers. Diagnostic performances were compared using McNemar tests. RESULTS. In the HS group, the hippocampal volume (affected vs unaffected, 3.54 vs 4.59 cm³) and temporal lobe volume (affected vs unaffected, 5.66 vs 6.89 cm³) on the affected side were significantly lower than on the unaffected side (p < .001) using the volu-metric tool. AUROCs of the volumetric tool were 0.813-0.842 in patients with left HS and 0.857-0.980 in patients with right HS (sensitivity, 81.8-90.9%; specificity, 70.5-95.5%). No significant difference (p = .63 to > .99) was observed between the performance of the volumetric tool and the performance of the two experienced readers as well as one inexperienced reader (AUROCs for these three readers, 0.968-0.999; sensitivity, 86.4-90.9%; specificity, 100.0%). The volumetric tool had better performance (p < .001) than the other inexperienced reader (AUROC, 0.806; sensitivity, 81.8%; specificity, 47.7%). With subsequent use of the tool, this inexperienced reader showed a nonsignificant increase (p = .10) in AUROC (0.912) as well as in sensitivity (86.4%) and specificity (84.1%). CONCLUSION. A fully automated volumetric brain MRI tool outperformed one of two inexperienced readers and performed as well as two experienced readers in identifying and lateralizing HS in pediatric patients. The tool improved the performance of an inexperienced reader. CLINICAL IMPACT. A fully automated volumetric tool facilitates diagnosis of HS in pediatric patients, especially for an inexperienced reader.

New MRI Finding in Migraineurs: Mesial Temporal Sclerosis

Background:

Based on our experience, a noticeable number of migraineurs without history of epilepsy disclose mesial temporal sclerosis (MTS) on their brain MRI.

Objective:

This prospective study was conducted to assess the frequency of MTS in migraineurs and also determine the ratio of unilateral and bilateral cases.

Material and Methods:

In this cross sectional study, the frequency of MTS in MRI of 84 migraine patients, who had symptoms for at least 2 years, assessed. Brain MRI was done with T1 and T2 weighted protocols. Two radiologists separately interpreted findings, defining MTS as presence of any of hippocampal atrophy, increased T2 signal of hippocampus, decreased T1 signal of hippocampus or loss of internal architecture. Patients who radiologists had not agreement on their diagnoses excluded. Stat analysis done using ‘N - 1’ chi squared test.

Results:

Eleven patients were excluded due to non-accordant interpretation of MRI findings by the two examining radiologists. MTS was detected in 14 out of 73 patients (19%). Bilateral involvement of mesial temporal lobe was seen in 6 (8%) patients (M 67%, F 33%). Five cases (7%) had unilateral left MTS (M 67%, F 33%) while 3 (4%) were affected with right-sided MTS (M 33%, F 67%). These findings highly suggest association of MTS and Migraine (P-value <0.0001).

Conclusion:

While MTS is a prevalent finding in migraineurs, incidental finding of MTS in MRI should suspect physicians of migraine as well as temporal lobe epilepsy. MTS can be proposed as an etiology of migraine but most likely, consequence of it.

Translating research findings into clinical practice: a systematic and critical review of neuroimaging-based clinical tools for brain disorders

A pivotal aim of psychiatric and neurological research is to promote the translation of the findings into clinical practice to improve diagnostic and prognostic assessment of individual patients. Structural neuroimaging holds much promise, with neuroanatomical measures accounting for up to 40% of the variance in clinical outcome. Building on these findings, a number of imaging-based clinical tools have been developed to make diagnostic and prognostic inferences about individual patients from their structural Magnetic Resonance Imaging scans. This systematic review describes and compares the technical characteristics of the available tools, with the aim to assess their translational potential into real-world clinical settings. The results reveal that a total of eight tools. All of these were specifically developed for neurological disorders, and as such are not suitable for application to psychiatric disorders. Furthermore, most of the tools were trained and validated in a single dataset, which can result in poor generalizability, or using a small number of individuals, which can cause overoptimistic results. In addition, all of the tools rely on two strategies to detect brain abnormalities in single individuals, one based on univariate comparison, and the other based on multivariate machine-learning algorithms. We discuss current barriers to the adoption of these tools in clinical practice and propose a checklist of pivotal characteristics that should be included in an "ideal" neuroimaging-based clinical tool for brain disorders.

Hippocampal Sclerosis Detection with NeuroQuant Compared with Neuroradiologists

BACKGROUND AND PURPOSE

NeuroQuant is an FDA-approved software that performs automated MR imaging quantitative volumetric analysis. This study aimed to compare the accuracy of NeuroQuant analysis with visual MR imaging analysis by neuroradiologists with expertise in epilepsy in identifying hippocampal sclerosis.

MATERIALS AND METHODS

We reviewed 144 adult patients who underwent presurgical evaluation for temporal lobe epilepsy. The reference standard for hippocampal sclerosis was defined by having hippocampal sclerosis on pathology (n = 61) or not having hippocampal sclerosis on pathology (n = 83). Sensitivities, specificities, positive predictive values, and negative predictive values were compared between NeuroQuant analysis and visual MR imaging analysis by using a McNemar paired test of proportions and the Bayes theorem.

RESULTS

NeuroQuant analysis had a similar specificity to neuroradiologist visual MR imaging analysis (90.4% versus 91.6%; P = .99) but a lower sensitivity (69.0% versus 93.0%, P < .001). The positive predictive value of NeuroQuant analysis was comparable with visual MR imaging analysis (84.0% versus 89.1%), whereas the negative predictive value was not comparable (79.8% versus 95.0%).

CONCLUSIONS

Visual MR imaging analysis by a neuroradiologist with expertise in epilepsy had a higher sensitivity than did NeuroQuant analysis, likely due to the inability of NeuroQuant to evaluate changes in hippocampal T2 signal or architecture. Given that there was no significant difference in specificity between NeuroQuant analysis and visual MR imaging analysis, NeuroQuant can be a valuable tool when the results are positive, particularly in centers that lack neuroradiologists with expertise in epilepsy, to help identify and refer candidates for temporal lobe epilepsy resection. In contrast, a negative test could justify a case referral for further evaluation to ensure that false-negatives are detected.

Prediction of Amyloid Positivity in Mild Cognitive Impairment Using Fully Automated Brain Segmentation Software

OBJECTIVE

To assess the predictive ability of regional volume information provided by fully automated brain segmentation software for cerebral amyloid positivity in mild cognitive impairment (MCI).

METHODS

This study included 130 subjects with amnestic MCI who participated in the Korean brain aging study of early diagnosis and prediction of Alzheimer's disease, an ongoing prospective cohort. All participants underwent comprehensive clinical assessment as well as ¹¹C-labeled Pittsburgh compound PET/MRI scans. The predictive ability of volumetric results provided by automated brain segmentation software was evaluated using binary logistic regression and receiver operating characteristic curve analysis.

RESULTS

Subjects were divided into two groups: one with Aβ deposition (58 subjects) and one without Aβ deposition (72 subjects). Among the varied volumetric information provided, the hippocampal volume percentage of intracranial volume (%HC/ICV), normative percentiles of hippocampal volume (HC_norm), and gray matter volume were associated with amyloid-β (Aβ) positivity (all P < 0.01). Multivariate analyses revealed that both %HC/ICV and HC_norm were independent significant predictors of Aβ positivity (all P < 0.001). In addition, prediction scores derived from %HC/ICV with age and HC_norm showed moderate accuracy in predicting Aβ positivity in MCI subjects (the areas under the curve: 0.739 and 0.723, respectively).

CONCLUSION

Relative hippocampal volume measures provided by automated brain segmentation software can be useful for screening cerebral Aβ positivity in clinical practice for patients with amnestic MCI. The information may also help clinicians interpret structural MRI to predict outcomes and determine early intervention for delaying the progression to Alzheimer's disease dementia.

Segmentation errors and intertest reliability in automated and manually traced hippocampal volumes

Objective

To rigorously compare automated atlas‐based and manual tracing hippocampal segmentation for accuracy, repeatability, and clinical acceptability given a relevant range of imaging abnormalities in clinical epilepsy.

Methods

Forty‐nine patients with hippocampal asymmetry were identified from our institutional radiology database, including two patients with significant anatomic deformations. Manual hippocampal tracing was performed by experienced technologists on 3T MPRAGE images, measuring hippocampal volume up to the tectal plate, excluding the hippocampal tail. The same images were processed using NeuroQuant and FreeSurfer software. Ten subjects underwent repeated manual hippocampal tracings by two additional technologists blinded to previous results to evaluate consistency. Ten patients with two clinical MRI studies had volume measurements repeated using NeuroQuant and FreeSurfer.

Results

FreeSurfer raw volumes were significantly lower than NeuroQuant (P < 0.001, right and left), and hippocampal asymmetry estimates were lower for both automatic methods than manual tracing (P < 0.0001). Differences remained significant after scaling volumes to age, gender, and scanner matched normative percentiles. Volume reproducibility was fair (0.4–0.59) for manual tracing, and excellent (>0.75) for both automated methods. Asymmetry index reproducibility was excellent (>0.75) for manual tracing and FreeSurfer segmentation and fair (0.4–0.59) for NeuroQuant segmentation. Both automatic segmentation methods failed on the two cases with anatomic deformations. Segmentation errors were visually identified in 25 NeuroQuant and 27 FreeSurfer segmentations, and nine (18%) NeuroQuant and six (12%) FreeSurfer errors were judged clinically significant.

Interpretation

Automated hippocampal volumes are more reproducible than hand‐traced hippocampal volumes. However, these methods fail in some cases, and significant segmentation errors can occur.

Psychometric Properties of the NIH Toolbox Cognition Battery in Healthy Older Adults: Reliability, Validity, and Agreement with Standard Neuropsychological Tests

OBJECTIVE

Few independent studies have examined the psychometric properties of the NIH Toolbox Cognition Battery (NIHTB-CB) in older adults, despite growing interest in its use for clinical purposes. In this paper we report the test-retest reliability and construct validity of the NIHTB-CB, as well as its agreement or concordance with traditional neuropsychological tests of the same construct to determine whether tests could be used interchangeably.

METHODS

Sixty-one cognitively healthy adults ages 60-80 completed "gold standard" (GS) neuropsychological tests, NIHTB-CB, and brain MRI. Test-retest reliability, convergent/discriminant validity, and agreement statistics were calculated using Pearson's correlations, concordance correlation coefficients (CCC), and root mean square deviations.

RESULTS

Test-retest reliability was acceptable (CCC = .73 Fluid; CCC = .85 Crystallized). The NIHTB-CB Fluid Composite correlated significantly with cerebral volumes (r's = |.35-.41|), and both composites correlated highly with their respective GS composites (r's = .58-.84), although this was more variable for individual tests. Absolute agreement was generally lower (CCC = .55 Fluid; CCC = .70 Crystallized) due to lower precision in fluid scores and systematic overestimation of crystallized composite scores on the NIHTB-CB.

CONCLUSIONS

These results support the reliability and validity of the NIHTB-CB in healthy older adults and suggest that the fluid composite tests are at least as sensitive as standard neuropsychological tests to medial temporal atrophy and ventricular expansion. However, the NIHTB-CB may generate different estimates of performance and should not be treated as interchangeable with established neuropsychological tests.

Improved Detection of Subtle Mesial Temporal Sclerosis: Validation of a Commercially Available Software for Automated Segmentation of Hippocampal Volume

BACKGROUND AND PURPOSE

Identification of mesial temporal sclerosis is critical in the evaluation of individuals with temporal lobe epilepsy. Our aim was to assess the performance of FDA-approved software measures of hippocampal volume to identify mesial temporal sclerosis in patients with medically refractory temporal lobe epilepsy compared with the initial clinical interpretation of a neuroradiologist.

MATERIALS AND METHODS

Preoperative MRIs of 75 consecutive patients who underwent a temporal resection for temporal lobe epilepsy from 2011 to 2016 were retrospectively reviewed, and 71 were analyzed using Neuroreader, a commercially available automated segmentation and volumetric analysis package. Volume measures, including hippocampal volume as a percentage of total intracranial volume and the Neuroreader Index, were calculated. Radiologic interpretations of the MR imaging and pathology from subsequent resections were classified as either mesial temporal sclerosis or other, including normal findings. These measures of hippocampal volume were evaluated by receiver operating characteristic curves on the basis of pathologic confirmation of mesial temporal sclerosis in the resected temporal lobe. Sensitivity and specificity were calculated for each method and compared by means of the McNemar test using the optimal threshold as determined by the Youden J point.

RESULTS

Optimized thresholds of hippocampal percentage of a structural volume relative to total intracranial volume (<0.19%) and the Neuroreader Index (≤-3.8) were selected to optimize sensitivity and specificity (89%/71% and 89%/78%, respectively) for the identification of mesial temporal sclerosis in temporal lobe epilepsy compared with the initial clinical interpretation of the neuroradiologist (50% and 87%). Automated measures of hippocampal volume predicted mesial temporal sclerosis more accurately than radiologic interpretation (McNemar test, P < .0001).

CONCLUSIONS

Commercially available automated segmentation and volume analysis of the hippocampus accurately identifies mesial temporal sclerosis and performs significantly better than the interpretation of the radiologist.

Amygdala enlargement in mesial temporal lobe epilepsy: an alternative imaging presentation of limbic epilepsy

PURPOSE

To assess imaging, clinical, and pathological features of mesial temporal lobe epilepsy (mTLE) patients with amygdala enlargement (AE) in comparison with those with mesial temporal sclerosis (MTS).

METHODS

Clinical, imaging, and pathologic features were retrospectively reviewed in 40 mTLE patients with postoperative follow-up (10 with AE and 30 with MTS). The volumes and signal intensity of the amygdala and hippocampus were assessed in 10 AE, 10 age- and sex-matched MTS patients, and 12 controls (HC).

RESULTS

AE patients had a lower rate of concordant FDG PET (p < 0.05) and required more frequently intracerebral electrodes compared to MTS patients (p < 0.05). AE had larger ipsilateral amygdala (p < 0.0001) and hippocampus volumes (p < 0.0001) compared to MTS and to HC, with no significant differences for other brain structures. Normalized FLAIR signal was higher in the ipsilateral than contralateral amygdala in both AE and MTS (p < 0.001 and p < 0.05, respectively) and higher in the ipsilateral amygdala compared to HC (p < 0.05). In MTS, ADC in the ipsilateral amygdala (867 mm²/s) was higher compared to the contralateral one (804.8 × 10^-6 mm²/s, p < 0.01), compared to HC (773 × 10^-6 mm²/s, p < 0.01) and compared to the ipsilateral amygdala in AE (813.7 × 10^-6 mm²/s, p < 0.05). AE patients had dysplasia (50%) or astrocytic gliosis (50%) of the amygdala extending to the hippocampus and temporal isocortex, and only 2/10 cases had pathologic findings of MTS.

CONCLUSION

AE patients have distinct imaging and pathologic features compared to MTS, and require more extensive preoperative workup. Recognition of AE may improve preoperative assessment in TLE surgical candidates.

Enhancing contrast to noise ratio of hippocampi affected with mesial temporal sclerosis: A case-control study in children undergoing epilepsy surgeries

OBJECTIVE

Detection of mesial temporal sclerosis (MTS) in children with epilepsy is important. We assessed whether an image-processing algorithm (Correlative Image Enhancement, CIE) could facilitate recognition of hippocampal signal abnormality in the presence of MTS by increasing contrast to noise ratio between affected hippocampus and normal gray matter.

PATIENTS AND METHODS

Baseline coronal FLAIR images from brain MRIs of 27 children with epilepsy who underwent hippocampal resection were processed using CIE. These included 19 hippocampi with biopsy proven MTS and 8 biopsy proven normal hippocampi resected in conjunction with hemispherotomy. We assessed the effect of processing on contrast to noise ratio (CNR) between hippocampus and normal insular gray matter, and on assessment of hippocampal signal abnormality by two masked neuroradiologists.

RESULTS

Processing resulted in a significant increase in mean CNR (from 3.9 ± 5.3 to 25.3 ± 25.8; P < 0.01) for hippocampi with MTS, with a substantial (>100%) increase from baseline seen in 15/19 (78.9%) cases. Baseline CNR of 1.7 ± 5.3 for normal hippocampi did not change significantly after processing (1.8 ± 5.3; P = 1.00). For one reader, baseline sensitivity (14/19; 73.6%) was unaffected but the specificity improved from 62.5% (5/8) to 100%. An increase in both sensitivity (from 73.6% to 78.9%) and specificity (from 62.5% to 75%) was seen for the second reader.

CONCLUSION

By enhancing CNR for diseased hippocampi while leaving normal hippocampi relatively unaffected, CIE may improve the diagnostic accuracies of radiologists in detecting MTS-related signal alteration within the affected hippocampus.

Comparison of automated volumetry of the hippocampus using NeuroQuant® and visual assessment of the medial temporal lobe in Alzheimer's disease

Background Different clinically feasible methods for evaluation of medial temporal lobe atrophy exists and are useful in diagnostic work-up of Alzheimer's disease (AD). Purpose To compare the diagnostic properties of two clinically available magnetic resonance imaging (MRI)-based methods-an automated volumetric software, NeuroQuant® (NQ) (evaluation of hippocampus volume) and the Scheltens scale (visual evaluation of medial temporal lobe atrophy [MTA])-in patients with AD dementia, and subjective and mild cognitive impairment (non-dementia). Material and Methods MRIs from 56 patients (31 AD, 25 non-dementia) were assessed with both methods. Correlations between the methods were calculated and receiver operating curve (ROC) analyses that yield area under the curve (AUC) statistics were conducted. Results High correlations were found between the two MRI assessments for the total hippocampal volume measured with NQ and mean MTA score (-0.753, P < 0.001), for the right (-0.767, P < 0.001), and for the left (-0.675, P < 0.001) sides. The NQ total measure yielded somewhat higher AUC (0.88, "good") compared to the MTA mean measure (0.80, "good") in the comparison of patients with AD and non-dementia, but the accuracy was in favor of the MTA scale. Conclusion The two methods correlated highly and both methods reached equally "good" power.

Automated volumetry of hippocampus is useful to confirm unilateral mesial temporal sclerosis in patients with radiologically positive findings

Background and purpose We evaluated two methods to identify mesial temporal sclerosis (MTS): visual inspection by experienced epilepsy neuroradiologists based on structural magnetic resonance imaging sequences and automated hippocampal volumetry provided by a processing pipeline based on the FMRIB Software Library. Methods This retrospective study included patients from the epilepsy monitoring unit database of our institution. All patients underwent brain magnetic resonance imaging in 1.5T and 3T scanners with protocols that included thin coronal T2, T1 and fluid-attenuated inversion recovery and isometric T1 acquisitions. Two neuroradiologists with experience in epilepsy and blinded to clinical data evaluated magnetic resonance images for the diagnosis of MTS. The diagnosis of MTS based on an automated method included the calculation of a volumetric asymmetry index between the two hippocampi of each patient and a threshold value to define the presence of MTS obtained through statistical tests (receiver operating characteristics curve). Hippocampi were segmented for volumetric quantification using the FIRST tool and fslstats from the FMRIB Software Library. Results The final cohort included 19 patients with unilateral MTS (14 left side): 14 women and a mean age of 43.4 ± 10.4 years. Neuroradiologists had a sensitivity of 100% and specificity of 73.3% to detect MTS (gold standard, k = 0.755). Automated hippocampal volumetry had a sensitivity of 84.2% and specificity of 86.7% (k = 0.704). Combined, these methods had a sensitivity of 84.2% and a specificity of 100% (k = 0.825). Conclusions Automated volumetry of the hippocampus could play an important role in temporal lobe epilepsy evaluation, namely on confirmation of unilateral MTS diagnosis in patients with radiological suggestive findings.

Automated volumetry for unilateral hippocampal sclerosis detection in patients with temporal lobe epilepsy

Hippocampal sclerosis (HS) is the most common cause of temporal lobe epilepsy (TLE) and can be identified in magnetic resonance imaging as hippocampal atrophy and subsequent volume loss. Detecting this kind of abnormalities through simple radiological assessment could be difficult, even for experienced radiologists. For that reason, hippocampal volumetry is generally used to support this kind of diagnosis. Manual volumetry is the traditional approach but it is time consuming and requires the physician to be familiar with neuroimaging software tools. In this paper, we propose an automated method, written as a script that uses FSL-FIRST, to perform hippocampal segmentation and compute an index to quantify hippocampi asymmetry (HAI). We compared the automated detection of HS (left or right) based on the HAI with the agreement of two experts in a group of 19 patients and 15 controls, achieving 84.2% sensitivity, 86.7% specificity and a Cohen's kappa coefficient of 0.704. The proposed method is integrated in the "Advanced Brain Imaging Lab" (ABrIL) cloud neurocomputing platform. The automated procedure is 77% (on average) faster to compute vs. the manual volumetry segmentation performed by an experienced physician.

Diagnostic Efficacy of Structural MRI in Patients With Mild-to-Moderate Alzheimer Disease: Automated Volumetric Assessment Versus Visual Assessment

OBJECTIVE

The purpose of this study was to compare the diagnostic efficacies of an automated volumetric assessment tool and visual assessment in the evaluation of medial temporal lobar atrophy in mild-to-moderate Alzheimer disease (AD).

MATERIALS AND METHODS

This retrospective study included 30 patients with mild-to-moderate AD and 25 age-matched healthy control subjects undergoing MRI with a 3D fast spoiled gradient recalled-echo sequence at 3 T. The images were processed with fully automated volumetric analysis software. To assess medial temporal lobe (MTL) atrophy, two MTL indexes, which took into account the volumes of the hippocampus and the inferior lateral ventricle, were calculated with the automated volumetric assessment software. In addition, two neuroradiologists assessed MTL atrophy visually using the Scheltens scale. ROC curve analysis was used to compare the diagnostic performances of the two methods. The weighted kappa statistic was used to assess the intrarater and interrater reliability of visual inspection.

RESULTS

The automated volumetric assessment tool had moderate sensitivity (63.3%) and high specificity (100%) in differentiating patients with mild-to-moderate AD from control subjects. Visual inspection showed sensitivity of 63.3% and specificity of 92.0%. The diagnostic performance was not significantly different between the two methods (p = 0.536-0.906). Intraobserver reliability for visual inspection was 0.858 and 0.902 for the two reviewers, and interobserver reliability was 0.692-0.780.

CONCLUSION

Both the automated volumetric assessment tool and visual inspection can be used to evaluate MTL atrophy and differentiate patients with AD from healthy individuals with good diagnostic accuracy. Thus, the automated tool can be a useful and efficient adjunct in clinical practice for evaluating MTL atrophy in the diagnosis of AD.