Search

Abstract Artificial intelligence (AI) is revolutionizing the field of medical imaging, holding the potential to shift medicine from a reactive “sick-care” approach to a proactive focus on healthcare and prevention. The successful development of AI in this domain relies on access to large, comprehensive, and standardized real-world datasets that accurately represent diverse populations and diseases. However, images and data are sensitive, and as such, before using them in any way the data needs to be modified to protect the privacy of the patients. This paper explores the approaches in the domain of five EU projects working on the creation of ethically compliant and GDPR-regulated European medical imaging platforms, focused on cancer-related data. It presents the individual approaches to the de-identification of imaging data, and describes the problems and the solutions adopted in each case. Further, lessons learned are provided, enabling future projects to optimally handle the problem of data de-identification. Critical relevance statement This paper presents key approaches from five flagship EU projects for the de-identification of imaging and clinical data offering valuable insights and guidelines in the domain. Key Points ΑΙ models for health imaging require access to large amounts of data. Access to large imaging datasets requires an appropriate de-identification process. This paper provides de-identification guidelines from the AI for health imaging (AI4HI) projects.

Abstract Background The Multidomain Alzheimer Preventive Trial (MAPT) was designed to assess the efficacy of omega-3 fatty acid supplementation, multidomain intervention (MI), or a combination of both on cognition. Although the MAPT study was negative, an effect of MI in maintaining cognitive functions compared to placebo group was showed in positive amyloid subjects. A FDG PET study (MAPT-NI) was implemented to test the impact of MI on brain glucose metabolism. Methods MAPT-NI was a randomized, controlled parallel-group single-center study, exploring the effect of MI on brain glucose metabolism. Participants were non-demented and had memory complaints, limitation in one instrumental activity of daily living, or slow gait. Participants were randomly assigned (1:1) to “MI group” or “No MI group.” The MI consisted of group sessions focusing on 3 domains: cognitive stimulation, physical activity, nutrition, and a preventive consultation. [18F]FDG PET scans were performed at baseline, 6 months, and 12 months, and cerebral magnetic resonance imaging scans at baseline. The primary objective was to evaluate the MI effect on brain glucose metabolism assessed by [18F]FDG PET imaging at 6 months. The primary outcome was the quantification of regional metabolism rate for glucose in cerebral regions involved early in Alzheimer disease by relative semi-quantitative SUVr (FDG-based AD biomarker). An exploratory voxel-wise analysis was performed to assess the effect of MI on brain glucose metabolism without anatomical hypothesis. Results The intention-to-treat population included 67 subjects (34 in the MI group and 33 in the No MI group. No significant MI effect was observed on primary outcome at 6 months. In the exploratory voxel-wise analysis, we observed a difference in favor of MI group on the change of cerebral glucose metabolism in limbic lobe (right hippocampus, right posterior cingulate, left posterior parahippocampal gyrus) at 6 months. Conclusions MI failed to show an effect on metabolism in FDG-based AD biomarker, but exploratory analysis suggested positive effect on limbic system metabolism. This finding could suggest a delay effect of MI on AD progression. Trial registration ClinicalTrials.gov Identifier, NCT01513252 .

Abstract Background The range of onset ages within some PSEN1 families is wide, and a few cases of reduced penetrance of PSEN1 mutations have been reported. However, published data on reduced penetrance have been limited to clinical histories, often collected retrospectively and lacking biomarker information. We present a case of reduced penetrance of the PSEN1 H163Y mutation in a carrier prospectively followed for 22 years. Methods Two brothers (A and B), both carriers of the H163Y mutation, were followed between 1995 and 2017. They underwent repeated clinical evaluations, neuropsychological assessments, and cerebrospinal fluid analyses, as well as brain imaging examinations with structural magnetic resonance, [18F]fluorodeoxyglucose positron emission tomography, and [11C]Pittsburgh compound B positron emission tomography. Results Brother A was followed between 44 and 64 years of age. Cognitive symptoms due to Alzheimer’s disease set in at the age of 54. Gradual worsening of symptoms resulted in admittance to a nursing home owing to dependence on others for all activities of daily living. He showed a curvilinear decline in cognitive function on neuropsychological tests, and changes on magnetic resonance imaging, positron emission tomography, and biomarkers in the cerebrospinal fluid supported a clinical diagnosis of Alzheimer’s disease. Brother A died at the age of 64 and fulfilled the criteria for definitive Alzheimer’s disease according to neuropathological examination results. Brother B was followed between the ages of 43 and 65 and showed no cognitive deterioration on repeated neuropsychological test occasions. In addition, no biomarker evidence of Alzheimer’s disease pathology was detected, either on imaging examinations or in cerebrospinal fluid. Conclusions The average (SD) age of symptom onset for PSEN1 H163Y is 51 ± 7 years according to previous studies. However, we present a case of a biomarker-verified reduction in penetrance in a mutation carrier who was still symptom-free at the age of 65. This suggests that other genetic, epigenetic, and/or environmental factors modify the onset age.

Objective: Posterior Cortical Atrophy (PCA) is a neurodegenerative disease characterized predominantly by visual impairment. However, diagnosis of PCA remains complicated with an interval of several years between initial reporting of symptoms and diagnosis. The aim of the present study is to define if patients' visual and gestural complaints are consistent with their clinical profile.Method: An evaluation of daily visual problems as well as a full neuropsychological assessment and FDG-PET were performed in 15 PCA patients. We compared glucose metabolism between these PCA patients and 18 healthy controls. Correlation analyses were conducted in PCA patients between visual and gestural complaint, clinical impairments, and brain glucose metabolism.Results: Major impairment of cognitive functions was detected in PCA patients specifically in visual domains. Positive correlations were found between visual impairments and hypometabolism in the right temporo-parieto-occipital cortices. However, no correlation was found between complaint and visual impairment in PCA patients.Discussion: Our main results suggest a consistent relationship between clinical impairment and brain metabolism. However, the patient's complaint and visual performance are not linked. Combining the literature and our results, it seems that patients are generally aware of difficulties but misinterpret them. This misinterpretation may be responsible for the delayed diagnosis.

White matter tract alterations have been consistently described in Alzheimer's disease (AD). In particular, limbic fronto-temporal connections, which are critical to episodic memory function, may degenerate early in the course of the disease. However the relation between white matter tract degeneration, hippocampal atrophy and episodic memory impairment at the earliest stages of AD is still unclear. In this magnetic resonance imaging study, white matter integrity and hippocampal volumes were evaluated in patients with amnestic mild cognitive impairment due to AD (Albert et al., 2011) (n = 22) and healthy controls (n = 15). Performance in various episodic memory tasks was also evaluated in each participant. Relative to controls, patients showed a significant reduction of white matter fractional anisotropy (FA) and increase of radial diffusivity (RD) in the bilateral uncinate fasciculus, parahippocampal cingulum and fornix. Within the patient group, significant intra-hemispheric correlations were notably found between hippocampal grey matter volume and FA in the uncinate fasciculus, suggesting a relationship between atrophy and disconnection of the hippocampus. Moreover, episodic recognition scores were related with uncinate fasciculus FA across patients. These results indicate that fronto-hippocampal connectivity is reduced from the earliest pre-demential stages of AD. Disruption of fronto-hippocampal connections may occur progressively, in parallel with hippocampal atrophy, and may specifically contribute to early initial impairment in episodic memory.

BACKGROUND:Cognitive impairment seems to be frequent in intracerebral hemorrhage (ICH) survivors, but remains widely understudied. In this study, we investigated the frequency and patterns of vascular cognitive disorders (VCDs) in patients with cerebral amyloid angiopathy (CAA)-related and deep ICH compared to patients with mild cognitive impairment due to Alzheimer's disease (MCI-AD) and healthy controls. METHODS:We prospectively recruited 20 patients with CAA-related lobar ICH, 20 with deep ICH, 20 with MCI-AD and 17 healthy controls. Patients with cognitive decline pre-ICH were excluded from the analysis. Each participant underwent a comprehensive neuropsychological assessment and a structural brain MRI. Cognitive assessment was performed at a median delay of 4 months after the acute phase in ICH patients, and more than 6 months after the first complaint in MCI-AD patients. Cognitive profiles were compared between groups. The prevalence of VCDs in the ICH groups was estimated using the recent VASCOG criteria. RESULTS:"Mild" and "major VCDs" were respectively observed in 87.5% and 2.5% of all ICH patients. Every patient in the CAA group had mild VCDs. No significant difference was observed in cognitive functioning between CAA-related and deep ICH patients. The most impaired process in the CAA group was naming, with a mean (±standard deviation) z-score of -5.2 ±5.5, followed by processing speed (-4.1±3.3), executive functioning (-2.6 ±2.5), memory (-2.4 ±3.5) and attention (-0.9 ±1.3). This cognitive pattern was different from the MCI-AD patients, but the groups were only different in gestural praxis, and by construction, in memory processes. CONCLUSIONS:VCDs are frequent after ICH. Cognitive patterns of patients with deep or CAA-related ICH did not differ, but there was impaired performance in specific domains distinct from the effects of Alzheimer's disease. CLINICAL TRIAL REGISTRATION:URL: http://www.clinicaltrials.gov. Unique identifier: NCT01619709.