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.

Reversal of cognitive decline in Alzheimer's disease.

Alzheimer's disease is one of the most significant healthcare problems nationally and globally. Recently, the first description of the reversal of cognitive decline in patients with early Alzheimer's disease or its precursors, MCI (mild cognitive impairment) and SCI (subjective cognitive impairment), was published [1]. The therapeutic approach used was programmatic and personalized rather than monotherapeutic and invariant, and was dubbed metabolic enhancement for neurodegeneration (MEND). Patients who had had to discontinue work were able to return to work, and those struggling at work were able to improve their performance. The patients, their spouses, and their co-workers all reported clear improvements. Here we report the results from quantitative MRI and neuropsychological testing in ten patients with cognitive decline, nine ApoE4+ (five homozygous and four heterozygous) and one ApoE4-, who were treated with the MEND protocol for 5-24 months. The magnitude of the improvement is unprecedented, providing additional objective evidence that this programmatic approach to cognitive decline is highly effective. These results have far-reaching implications for the treatment of Alzheimer's disease, MCI, and SCI; for personalized programs that may enhance pharmaceutical efficacy; and for personal identification of ApoE genotype.

Quantitative Neuroimaging Software for Clinical Assessment of Hippocampal Volumes on MR Imaging.

BACKGROUND: Multiple neurological disorders including Alzheimer's disease (AD), mesial temporal sclerosis, and mild traumatic brain injury manifest with volume loss on brain MRI. Subtle volume loss is particularly seen early in AD. While prior research has demonstrated the value of this additional information from quantitative neuroimaging, very few applications have been approved for clinical use. Here we describe a US FDA cleared software program, NeuroreaderTM, for assessment of clinical hippocampal volume on brain MRI. OBJECTIVE: To present the validation of hippocampal volumetrics on a clinical software program. METHOD: Subjects were drawn (n = 99) from the Alzheimer Disease Neuroimaging Initiative study. Volumetric brain MR imaging was acquired in both 1.5 T (n = 59) and 3.0 T (n = 40) scanners in participants with manual hippocampal segmentation. Fully automated hippocampal segmentation and measurement was done using a multiple atlas approach. The Dice Similarity Coefficient (DSC) measured the level of spatial overlap between NeuroreaderTM and gold standard manual segmentation from 0 to 1 with 0 denoting no overlap and 1 representing complete agreement. DSC comparisons between 1.5 T and 3.0 T scanners were done using standard independent samples T-tests. RESULTS: In the bilateral hippocampus, mean DSC was 0.87 with a range of 0.78-0.91 (right hippocampus) and 0.76-0.91 (left hippocampus). Automated segmentation agreement with manual segmentation was essentially equivalent at 1.5 T (DSC = 0.879) versus 3.0 T (DSC = 0.872). CONCLUSION: This work provides a description and validation of a software program that can be applied in measuring hippocampal volume, a biomarker that is frequently abnormal in AD and other neurological disorders.

Hippocampal volume and serotonin transporter polymorphism in major depressive disorder.

OBJECTIVE: The main aim of the present study was to replicate a previous finding in major depressive disorder (MDD) of association between reduced hippocampal volume and the long variant of the di- and triallelic serotonin transporter polymorphism in SLC6A4 on chromosome 17q11.2. Secondarily, we also hypothesised that 5-HTTLPR may be a risk factor for MDD. METHODS: Quantitative magnetic resonance imaging (MRI) of the hippocampus was studied in 23 inpatients suffering from MDD and in 33 healthy controls. Normalised volumetric MRI data of hippocampus were assessed with adjustment for total brain volume and tensor-based morphometry was used to elucidate structural brain differences. A triallelic genetic marker resulting from two SLC6A4 promoter region polymorphisms, 5-HTTLPR and rs25531, was analysed for association with MDD and quantitative traits. RESULTS: Healthy controls had a smaller relative hippocampal volume (relative to brain size) but a larger total brain volume compared with patients with MDD. For patients compared with healthy controls, atrophy was found in the right temporal lobe and pons medulla. Allele and genotype frequencies were strikingly different from the previous study that we aimed to replicate, and no significant associations with the serotonin transporter polymorphism were found. CONCLUSIONS: The present quantitative and morphometric MRI study was not able to replicate the previous finding of association between reduced hippocampal volume in depressed patients and the serotonin transporter polymorphism.

Correlations between Stroop task performance and white matter lesion measures in late-onset major depression.

Cerebral white matter lesions (WMLs) are believed to play an important role in a subset of patients with late-onset depression by affecting the white matter connectivity in circuitries essential for mood and cognition. In this study we used diffusion tensor imaging-based (DTI-based) tractography to assess white matter fiber tracts affected by deep WMLs (DWMLs) in patients with late-onset major depression and age- and gender-matched controls. Tractography outcome, illustrated as pathways affected by DWMLs, was analyzed for associations with cognitive performance on the Stroop Test (ST). The patients (n=17) performed significantly worse on the ST than the controls (n=22). Poor performance on the ST correlated with higher lesion load. Regression analysis showed a significant correlation between poor performance on the ST and tracts affected by DWMLs in multiple brain areas in the control group, but very sparse correlation in the patient group. Our results suggest that DWMLs play an important role in the cognitive performance of controls,whereas their influence in depressed patients is overruled by additional, state-dependent factors. Future focus on the tract-specific localization of WMLs using DTI tractography may reveal important associations between neuroconnectivity and clinical measures.

Depression severity is correlated to the integrity of white matter fiber tracts in late-onset major depression.

Cerebral white matter lesions (WMLs) are believed to play an important role in a subset of major depression (MD). We aimed to describe the impact of WMLs on white matter pathways in MD using diffusion tensor imaging (DTI) and magnetization transfer imaging. As a novel approach, we used DTI tractography to assess pathways intersected by WMLs. We examined 22 patients with late-onset MD and 22 age- and gender-matched controls. Parametric maps of fractional anisotropy (FA), apparent diffusion coefficient (ADC), and magnetization transfer ratio (MTR) were obtained to describe tissue integrity. The association between depression severity and the tract-specific localization of WMLs was analyzed on a voxel-by-voxel basis. We showed a significant positive association between depression severity and fiber tracts intersected by WMLs in the left superior longitudinal fasciculus and the right uncinate fasciculus. In both groups, WMLs had significantly lower FA and MTR, and higher ADC than both the tracts they intersected and the normal-appearing white matter (NAWM). In turn, the tracts intersected by WMLs had significantly lower FA and higher ADC than the NAWM. In conclusion, depression severity correlates with the tract-specific localization of WMLs. WMLs have a pronounced effect on white matter integrity in the pathways they intersect.

Hippocampal visuospatial function and volume in remitted depressed patients: an 8-year follow-up study.

BACKGROUND: Several lines of evidence suggest hippocampal dysfunction in major depression, but the prevalence and nature of specific dysfunctions during the long-term course of major depression is yet to be assessed. A 3D virtual environment navigation task and measurements of hippocampal volume were assessed in remitted former inpatients with moderate to severe depression after an 8 year follow-up period to evaluate whether functional and structural differences existed in the hippocampus beyond depression. METHODS: Performance on a right hippocampus-dependent 3D virtual reality navigation task, memory tests and right and left hippocampal volumes were assessed in 31 remitted depressed (unipolar) patients and 37 healthy subjects. RESULTS: Remitted depressed patients did not differ significantly from healthy subjects in terms of either neuropsychological performance or hippocampal volume. LIMITATIONS: The sample consisted of remitted inpatients that had been treated with psychotropic drugs during the 8-year follow-up period. Moreover, 11 of the 42 patients included in the original study were excluded from the follow-up study due to persisting depressive illness and suicide. CONCLUSIONS: The study of visuospatial navigation ability and hippocampal volume in remitted depressed patients offers a specific way of assessing dysfunction in the hippocampus in major depression. Our findings do not support the notion that hippocampal impairment of visuospatial function exists beyond the depressive state, thus indicating that hippocampus-related cognitive dysfunction and previously reported reduced hippocampal volume might represent a state and not a permanent trait of the illness. Moreover, our study suggests that intensive drug treatment of the depressive episodes might prevent the deterioration of the hippocampus.