Support vector machine-based classification of neuroimages in Alzheimer's disease: direct comparison of FDG-PET, rCBF-SPECT and MRI data acquired from the same individuals

Objective: To conduct the first support vector machine (SVM)-based study comparing the diagnostic accuracy of T1-weighted magnetic resonance imaging (T1-MRI), F-fluorodeoxyglucose-positron emission tomography (FDG-PET) and regional cerebral blood flow single-photon emission computed tomography (rCBF-SPECT) in Alzheimer's disease (AD). Method: Brain T1-MRI, FDG-PET and rCBF-SPECT scans were acquired from a sample of mild AD patients (n=20) and healthy elderly controls (n=18). SVM-based diagnostic accuracy indices were calculated using whole-brain information and leave-one-out cross-validation. Results: The accuracy obtained using PET and SPECT data were similar. PET accuracy was 68∼71% and area under curve (AUC) 0.77∼0.81; SPECT accuracy was 68∼74% and AUC 0.75∼0.79, and both had better performance than analysis with T1-MRI data (accuracy of 58%, AUC 0.67). The addition of PET or SPECT to MRI produced higher accuracy indices (68∼74%; AUC: 0.74∼0.82) than T1-MRI alone, but these were not clearly superior to the isolated neurofunctional modalities. Conclusion: In line with previous evidence, FDG-PET and rCBF-SPECT more accurately identified patients with AD than T1-MRI, and the addition of either PET or SPECT to T1-MRI data yielded increased accuracy. The comparable SPECT and PET performances, directly demonstrated for the first time in the present study, support the view that rCBF-SPECT still has a role to play in AD diagnosis.

Support vector machine-based classification of neuroimages in Alzheimer's disease: direct comparison of FDG-PET, rCBF-SPECT and MRI data acquired from the same individuals.

OBJECTIVE: To conduct the first support vector machine (SVM)-based study comparing the diagnostic accuracy of T1-weighted magnetic resonance imaging (T1-MRI), F-fluorodeoxyglucose-positron emission tomography (FDG-PET) and regional cerebral blood flow single-photon emission computed tomography (rCBF-SPECT) in Alzheimer's disease (AD). METHOD: Brain T1-MRI, FDG-PET and rCBF-SPECT scans were acquired from a sample of mild AD patients (n=20) and healthy elderly controls (n=18). SVM-based diagnostic accuracy indices were calculated using whole-brain information and leave-one-out cross-validation. RESULTS: The accuracy obtained using PET and SPECT data were similar. PET accuracy was 68∼71% and area under curve (AUC) 0.77∼0.81; SPECT accuracy was 68∼74% and AUC 0.75∼0.79, and both had better performance than analysis with T1-MRI data (accuracy of 58%, AUC 0.67). The addition of PET or SPECT to MRI produced higher accuracy indices (68∼74%; AUC: 0.74∼0.82) than T1-MRI alone, but these were not clearly superior to the isolated neurofunctional modalities. CONCLUSION: In line with previous evidence, FDG-PET and rCBF-SPECT more accurately identified patients with AD than T1-MRI, and the addition of either PET or SPECT to T1-MRI data yielded increased accuracy. The comparable SPECT and PET performances, directly demonstrated for the first time in the present study, support the view that rCBF-SPECT still has a role to play in AD diagnosis.

The link between cardiovascular risk, Alzheimer's disease, and mild cognitive impairment: support from recent functional neuroimaging studies

Objective: To review functional neuroimaging studies about the relationship between cardiovascular risk factors (CVRFs), Alzheimer's disease (AD), and mild cognitive impairment (MCI). Methods: We performed a comprehensive literature search to identify articles in the neuroimaging field addressing CVRF in AD and MCI. We included studies that used positron emission tomography (PET), single photon emission computerized tomography (SPECT), or functional magnetic resonance imaging (fMRI). Results: CVRFs have been considered risk factors for cognitive decline, MCI, and AD. Patterns of AD-like changes in brain function have been found in association with several CVRFs (both regarding individual risk factors and also composite CVRF measures). In vivo assessment of AD-related pathology with amyloid imaging techniques provided further evidence linking CVRFs and AD, but there is still limited information resulting from this new technology. Conclusion: There is a large body of evidence from functional neuroimaging studies supporting the hypothesis that CVRFs may play a causal role in the pathophysiology of AD. A major limitation of most studies is their cross-sectional design; future longitudinal studies using multiple imaging modalities are expected to better document changes in CVRF-related brain function patterns and provide a clearer picture of the complex relationship between aging, CVRFs, and AD. .

The link between cardiovascular risk, Alzheimer's disease, and mild cognitive impairment: support from recent functional neuroimaging studies.

OBJECTIVE: To review functional neuroimaging studies about the relationship between cardiovascular risk factors (CVRFs), Alzheimer's disease (AD), and mild cognitive impairment (MCI). METHODS: We performed a comprehensive literature search to identify articles in the neuroimaging field addressing CVRF in AD and MCI. We included studies that used positron emission tomography (PET), single photon emission computerized tomography (SPECT), or functional magnetic resonance imaging (fMRI). RESULTS: CVRFs have been considered risk factors for cognitive decline, MCI, and AD. Patterns of AD-like changes in brain function have been found in association with several CVRFs (both regarding individual risk factors and also composite CVRF measures). In vivo assessment of AD-related pathology with amyloid imaging techniques provided further evidence linking CVRFs and AD, but there is still limited information resulting from this new technology. CONCLUSION: There is a large body of evidence from functional neuroimaging studies supporting the hypothesis that CVRFs may play a causal role in the pathophysiology of AD. A major limitation of most studies is their cross-sectional design; future longitudinal studies using multiple imaging modalities are expected to better document changes in CVRF-related brain function patterns and provide a clearer picture of the complex relationship between aging, CVRFs, and AD.

Neuroanatomical classification in a population-based sample of psychotic major depression and bipolar I disorder with 1 year of diagnostic stability.

The presence of psychotic features in the course of a depressive disorder is known to increase the risk for bipolarity, but the early identification of such cases remains challenging in clinical practice. In the present study, we evaluated the diagnostic performance of a neuroanatomical pattern classification method in the discrimination between psychotic major depressive disorder (MDD), bipolar I disorder (BD-I), and healthy controls (HC) using a homogenous sample of patients at an early course of their illness. Twenty-three cases of first-episode psychotic mania (BD-I) and 19 individuals with a first episode of psychotic MDD whose diagnosis remained stable during 1 year of followup underwent 1.5 T MRI at baseline. A previously validated multivariate classifier based on support vector machine (SVM) was employed and measures of diagnostic performance were obtained for the discrimination between each diagnostic group and subsamples of age- and gender-matched controls recruited in the same neighborhood of the patients. Based on T1-weighted images only, the SVM-classifier afforded poor discrimination in all 3 pairwise comparisons: BD-I versus HC; MDD versus HC; and BD-I versus MDD. Thus, at the population level and using structural MRI only, we failed to achieve good discrimination between BD-I, psychotic MDD, and HC in this proof of concept study.

Neuroanatomical pattern classification in a population-based sample of first-episode schizophrenia.

Recent neuroanatomical pattern classification studies have attempted to individually classify cases with psychotic disorders using morphometric MRI data in an automated fashion. However, this approach has not been tested in population-based samples, in which variable patterns of comorbidity and disease course are typically found. We aimed to evaluate the diagnostic accuracy (DA) of the above technique to discriminate between incident cases of first-episode schizophrenia identified in a circumscribed geographical region over a limited period of time, in comparison with next-door healthy controls. Sixty-two cases of first-episode schizophrenia or schizophreniform disorder and 62 age, gender and educationally-matched controls underwent 1.5 T MRI scanning at baseline, and were naturalistically followed-up over 1 year. T1-weighted images were used to train a high-dimensional multivariate classifier, and to generate both spatial maps of the discriminative morphological patterns between groups and ROC curves. The spatial map discriminating first-episode schizophrenia patients from healthy controls revealed a complex pattern of regional volumetric abnormalities in the former group, affecting fronto-temporal-occipital gray and white matter regions bilaterally, including the inferior fronto-occipital fasciculus, as well as the third and lateral ventricles. However, an overall modest DA (73.4%) was observed for the individual discrimination between first-episode schizophrenia patients and controls, and the classifier failed to predict 1-year prognosis (remitting versus non-remitting course) of first-episode schizophrenia (DA=58.3%). In conclusion, using a "real world" sample recruited with epidemiological methods, the application of a neuroanatomical pattern classifier afforded only modest DA to classify first-episode schizophrenia subjects and next-door healthy controls, and poor discriminative power to predict the 1-year prognosis of first-episode schizophrenia.

Neurostructural predictors of Alzheimer's disease: a meta-analysis of VBM studies.

The identification of biological markers at early stages of Alzheimer's disease (AD) contributes to diagnostic accuracy and adds prognostic value. However, in spite of recent developments, results of neurostructural imaging studies on predicting conversion to AD are not uniform. We conducted a systematic review of voxel-based morphometry (VBM) studies about the neurostructural predictors of conversion to AD. Ten studies met inclusion criteria and nine reported baseline regional gray matter (GM) atrophy in mild cognitive impairment (MCI) or healthy subjects who progressed to AD. Using the method of Activation Likelihood Estimation, we meta-analyzed the coordinates from the six longitudinal VBM studies that enrolled subjects with amnestic MCI (aMCI) at baseline. These comprised a total of 429 aMCI subjects, of which 142 converted to AD. Meta-analysis yielded one significant cluster of GM volumetric reduction in aMCI patients who converted to AD, located in the left hippocampus and parahippocampal gyrus. In conclusion, left medial temporal lobe atrophy is the most consistent neurostructural biomarker to predict conversion from aMCI to AD.

Volume reduction of the corpus callosum and its relationship with deficits in interhemispheric transfer of information in recent-onset psychosis.

The present study aimed to investigate the presence of corpus callosum (CC) volume deficits in a population-based recent-onset psychosis (ROP) sample, and whether CC volume relates to interhemispheric communication deficits. For this purpose, we used voxel-based morphometry comparisons of magnetic resonance imaging data between ROP (n =122) and healthy control (n = 94) subjects. Subgroups (38 ROP and 39 controls) were investigated for correlations between CC volumes and performance on the Crossed Finger Localization Test (CFLT). Significant CC volume reductions in ROP subjects versus controls emerged after excluding substance misuse and non-right-handedness. CC reductions retained significance in the schizophrenia subgroup but not in affective psychoses subjects. There were significant positive correlations between CC volumes and CFLT scores in ROP subjects, specifically in subtasks involving interhemispheric communication. From these results, we can conclude that CC volume reductions are present in association with ROP. The relationship between such deficits and CFLT performance suggests that interhemispheric communication impairments are directly linked to CC abnormalities in ROP.

Vascular diseases and old age mental disorders: an update of neuroimaging findings.

PURPOSE OF REVIEW: To review neuroimaging findings that have been reported in samples of patients with cardiovascular disorders and their association with the onset of Alzheimer's disease, vascular dementia, depression and bipolar disorder in the elderly and to highlight the implications of these findings to the knowledge about the pathophysiology of psychiatric disorders in old age, as well as their potential clinical implications. RECENT FINDINGS: Vascular risk factors, such as hypertension, diabetes, dyslipidemia, smoking habits and heart failure, have all been associated with signs of cerebrovascular dysfunction, including structural MRI findings of signal hyperintensities, lacunes and stroke and functional imaging findings of brain regional hypoperfusion and hypometabolism. Such brain abnormalities have been found to increase the risk of onset of psychiatric disorder (depression, bipolar and dementia) in old age. SUMMARY: As vascular risk factors are potentially modifiable when detected in midlife, the early characterization of brain changes associated with the presence of cardiovascular diseases holds promise to afford clinical applications in psychiatry, providing new perspectives for the prevention of old age psychiatric disorders.

Epilepsy syndromes associated with hypothalamic hamartomas.

PURPOSE: Hypothalamic hamartoma (HH) related epilepsy presents with gelastic seizures (GS), other seizure types and cognitive deterioration. Although seizure origin in GS has been well established, non-GS are poorly characterized. Their relationship with the HH and cognitive deterioration remains poorly understood. We analyzed seizure type, spread pattern in non-GS and their relationship with the epileptic syndrome in HH. METHODS: We documented all current seizure types in six adult patients with HH-epilepsy with video-EEG monitoring, characterized clinical-electrographic features of gelastic and non-gelastic seizures and correlated these findings with cognitive profile, as well as MRI and ictal SPECT data. RESULTS: Only four seizure types were seen: GS, complex partial (CPS), tonic seizures (TS) and secondarily generalized tonic-clonic seizures (sGTC). An individual patient presented either CPS or TS, but not both. GS progressed to CPS or TS, but not both. Ictal patterns in GS/TS and in GS/CPS overlapped, suggesting ictal spread from the HH to other cortical regions. Ictal SPECT patterns also showed GS/TS overlap. Patients with GS-CPS presented a more benign profile with preserved cognition and clinical-EEG features of temporal lobe epilepsy. Patients with GS-TS had clinical-EEG features of symptomatic generalized epilepsy, including mental deterioration. CONCLUSIONS: Video-EEG and ictal SPECT findings suggest that all seizures in HH-related epilepsy originate in the HH, with two clinical epilepsy syndromes: one resembling temporal lobe epilepsy and a more catastrophic syndrome, with features of a symptomatic generalized epilepsy. The epilepsy syndrome may be determined by HH size or by seizure spread pattern.