Algorithms for computer-aided diagnosis of dementia based on structural MRI have demonstrated high performance in the literature, but are difficult to compare as different data sets and methodology were used for evaluation. In addition, it is unclear how the algorithms would perform on previously unseen data, and thus, how they would perform in clinical practice when there is no real opportunity to adapt the algorithm to the data at hand. To address these comparability, generalizability and clinical applicability issues, we organized a grand challenge that aimed to objectively compare algorithms based on a clinically representative multi-center data set. Using clinical practice as the starting point, the goal was to reproduce the clinical diagnosis. Therefore, we evaluated algorithms for multi-class classification of three diagnostic groups: patients with probable Alzheimer's disease, patients with mild cognitive impairment and healthy controls. The diagnosis based on clinical criteria was used as reference standard, as it was the best available reference despite its known limitations. For evaluation, a previously unseen test set was used consisting of 354 T1-weighted MRI scans with the diagnoses blinded. Fifteen research teams participated with a total of 29 algorithms. The algorithms were trained on a small training set (n=30) and optionally on data from other sources (e.g., the Alzheimer's Disease Neuroimaging Initiative, the Australian Imaging Biomarkers and Lifestyle flagship study of aging). The best performing algorithm yielded an accuracy of 63.0% and an area under the receiver-operating-characteristic curve (AUC) of 78.8%. In general, the best performances were achieved using feature extraction based on voxel-based morphometry or a combination of features that included volume, cortical thickness, shape and intensity. The challenge is open for new submissions via the web-based framework: http://caddementia.grand-challenge.org.

Alzheimer’s disease (AD) and frontotemporal dementia (FTD) are the most common neurodegenerative early-onset dementias. Despite the fact that both conditions have a very distinctive clinical pattern, they present with an overlap in their cognitive and behavioral features that may lead to misdiagnosis or delay in diagnosis. The current review intends to summarize briefly the main differences at the clinical, neuropsychological, and behavioral levels, in an attempt to suggest which aspects would facilitate an adequate diagnosis in a clinical setting, especially in Latin American and low- and middle-income countries, where the resources needed for a differential diagnosis (such as MRI or biomarkers) are not always available. A timely diagnosis of AD and FTD have significant implications for the medical management and quality of life of patients and careers.

To investigate arterial spin labeling (ASL)-MRI for the early diagnosis of and differentiation between the two most common types of presenile dementia: Alzheimer’s disease (AD) and frontotemporal dementia (FTD), and for distinguishing age-related from pathological perfusion changes.

For the development of minimally invasive brain-computer interfaces (BCIs), it is important to accurately localize the area of implantation. Using fMRI, we investigated which brain areas are involved in motor imagery. Twelve healthy subjects performed a motor execution and imagery task during separate fMRI and EEG measurements. fMRI results showed that during imagery, premotor and parietal areas were most robustly activated in individual subjects, but surprisingly, no activation was found in the primary motor cortex. EEG results showed that spectral power decreases in contralateral sensorimotor rhythms (8-24 Hz) during both movement and imagery. To further verify the involvement of the motor imagery areas found with fMRI, one epilepsy patient performed the same task during both fMRI and ECoG recordings. Significant ECoG low (8-24 Hz) and high (65-95 Hz) frequency power changes were observed selectively on premotor cortex and these co-localized with fMRI. During a subsequent BCI task, excellent performance (91%) was obtained based on ECoG power changes from the localized premotor area. These results indicate that other areas than the primary motor area may be more reliably activated during motor imagery. Specifically, the premotor cortex may be a better area to implant an invasive BCI.

Background: Semantic and Phonological fluency (SF and PF) are routinely evaluated in patients with Alzheimer’s disease (AD). There are disagreements in the literature regarding which fluency task is more affected while developing AD. Most studies focus on SF assessment, given its connection with the temporoparietal amnesic system. PF is less reported, it is related to working memory, which is also impaired in probable and diagnosed AD. Differentiating between performance on these tasks might be informative in early AD diagnosis, providing an accurate linguistic profile. Objective: Compare SF and PF performance in healthy volunteers, volunteers with probable AD, and patients with AD diagnosis, considering the heterogeneity of age, gender, and educational level variables. Methods: A total of 8 studies were included for meta-analysis, reaching a sample size of 1,270 individuals (568 patients diagnosed with AD, 340 with probable AD diagnosis, and 362 healthy volunteers). Results: The three groups consistently performed better on SF than PF. When progressing to a diagnosis of AD, we observed a significant difference in SF and PF performance across our 3 groups of interest ( p = 0.04). The age variable explained a proportion of this difference in task performance across the groups, and as age increases, both tasks equally worsen. Conclusion: The performance of SF and PF might play a differential role in early AD diagnosis. These tasks rely on partially different neural bases of language processing. They are thus worth exploring independently in diagnosing normal aging and its transition to pathological stages, including probable and diagnosed AD.

BACKGROUND AND PURPOSE: Determining language dominance with fMRI is challenging in patients with brain tumor, particularly in cases of suspected atypical language representation. Supratentorial activation patterns must be interpreted with great care when the tumor is in or near the presumed language areas, where tumor tissue or mass effect can lead to false-negative fMRI results. In this study, we assessed cerebrocerebellar language fMRI lateralization in healthy participants and in patients with brain tumors with a focus on atypical language representation. MATERIALS AND METHODS: Twenty healthy participants and 38 patients with a brain tumor underwent fMRI with a verb-generation task. Cerebral and cerebellar language lateralizations were separately classified as left-sided, right-sided, or symmetric. Electrocortical stimulation was performed in 19 patients. With the McNemar test, we evaluated the dependency between language lateralization in the cerebrum and cerebellum, and with Pearson correlation analysis, the relationship between the cerebral and cerebellar lateralization indices. RESULTS: There was a significant dependency between cerebral and cerebellar language activation, with moderate negative correlation (Pearson r = -0.69). Crossed cerebrocerebellar language activation was present in both healthy participants and patients, irrespective of handedness or typical or atypical language representation. There were no discordant findings between fMRI and electrocortical stimulation. CONCLUSIONS: Language lateralization in the cerebellum can be considered an additional diagnostic feature to determine language dominance in patients with brain tumor. This is particularly useful in cases of uncertainty, such as the interference of a brain tumor with cerebral language activation on fMRI and atypical language representation.