| 1. |
- Khan, Wasim, et al.
(författare)
-
A Multi-Cohort Study of ApoE epsilon 4 and Amyloid-beta Effects on the Hippocampus in Alzheimer's Disease
- 2017
-
Ingår i: Journal of Alzheimer's Disease. - 1387-2877 .- 1875-8908. ; 56:3, s. 1159-1174
-
Tidskriftsartikel (refereegranskat)abstract
- The apolipoprotein E (APOE) gene has been consistently shown to modulate the risk of Alzheimer's disease (AD). Here, using an AD and normal aging dataset primarily consisting of three AD multi-center studies (n = 1,781), we compared the effect of APOE and amyloid-beta (A beta) on baseline hippocampal volumes in AD patients, mild cognitive impairment (MCI) subjects, and healthy controls. A large sample of healthy adolescents (n = 1,387) was also used to compare hippocampal volumes between APOE groups. Subjects had undergone a magnetic resonance imaging (MRI) scan and APOE genotyping. Hippocampal volumes were processed using FreeSurfer. In the AD and normal aging dataset, hippocampal comparisons were performed in each APOE group and in epsilon 4 carriers with positron emission tomography (PET) A beta who were dichotomized (A beta+/A beta-) using previous cut-offs. We found a linear reduction in hippocampal volumes with epsilon 4 carriers possessing the smallest volumes, epsilon 3 carriers possessing intermediate volumes, and epsilon 2 carriers possessing the largest volumes. Moreover, AD and MCI epsilon 4 carriers possessed the smallest hippocampal volumes and control epsilon 2 carriers possessed the largest hippocampal volumes. Subjects with both APOE epsilon 4 and A beta positivity had the lowest hippocampal volumes when compared to A beta-epsilon 4 carriers, suggesting a synergistic relationship between APOE epsilon 4 and A beta. However, we found no hippocampal volume differences between APOE groups in healthy 14-year-old adolescents. Our findings suggest that the strongest neuroanatomic effect of APOE epsilon 4 on the hippocampus is observed in AD and groups most at risk of developing the disease, whereas hippocampi of old and young healthy individuals remain unaffected.
|
|
| 2. |
- Brusini, Irene, et al.
(författare)
-
Shape Information Improves the Cross-Cohort Performance of Deep Learning-Based Segmentation of the Hippocampus
- 2020
-
Ingår i: Frontiers in Neuroscience. - : Frontiers Media S.A.. - 1662-4548 .- 1662-453X. ; 14
-
Tidskriftsartikel (refereegranskat)abstract
- Performing an accurate segmentation of the hippocampus from brain magnetic resonance images is a crucial task in neuroimaging research, since its structural integrity is strongly related to several neurodegenerative disorders, including Alzheimer's disease (AD). Some automatic segmentation tools are already being used, but, in recent years, new deep learning (DL)-based methods have been proven to be much more accurate in various medical image segmentation tasks. In this work, we propose a DL-based hippocampus segmentation framework that embeds statistical shape of the hippocampus as context information into the deep neural network (DNN). The inclusion of shape information is achieved with three main steps: (1) a U-Net-based segmentation, (2) a shape model estimation, and (3) a second U-Net-based segmentation which uses both the original input data and the fitted shape model. The trained DL architectures were tested on image data of three diagnostic groups [AD patients, subjects with mild cognitive impairment (MCI) and controls] from two cohorts (ADNI and AddNeuroMed). Both intra-cohort validation and cross-cohort validation were performed and compared with the conventional U-net architecture and some variations with other types of context information (i.e., autocontext and tissue-class context). Our results suggest that adding shape information can improve the segmentation accuracy in cross-cohort validation, i.e., when DNNs are trained on one cohort and applied to another. However, no significant benefit is observed in intra-cohort validation, i.e., training and testing DNNs on images from the same cohort. Moreover, compared to other types of context information, the use of shape context was shown to be the most successful in increasing the accuracy, while keeping the computational time in the order of a few minutes.
|
|
| 3. |
- Cedres, Nira, et al.
(författare)
-
The interplay between gray matter and white matter neurodegeneration in subjective cognitive decline
- 2021
-
Ingår i: Aging. - : Impact Journals, LLC. - 1945-4589 .- 1945-4589. ; 13:16, s. 19963-19977
-
Tidskriftsartikel (refereegranskat)abstract
- Aims: To investigate the interplay between gray matter (GM) and white matter (WM) neurodegeneration in subjective cognitive decline (SCD), including thickness across the whole cortical mantle, hippocampal volume, and integrity across the whole WM.Methods: We included 225 cognitively unimpaired individuals from a community-based cohort. Subjective cognitive complaints were assessed through 9 questions covering amnestic and non-amnestic cognitive domains. In our cohort, 123 individuals endorsed from one to six subjective cognitive complaints (i.e. they fulfilled the diagnostic criteria for SCD), while 102 individuals reported zero complaints. GM neurodegeneration was assessed through measures of cortical thickness across the whole mantle and hippocampal volume. WM neurodegeneration was assessed through measures of mean diffusivity (MD) across the whole WM skeleton. Mediation analysis and multiple linear regression were conducted to investigate the interplay between the measures of GM and WM neurodegeneration.Results: A higher number of complaints was associated with reduced hippocampal volume, cortical thinning in several frontal and temporal areas and the insula, and higher MD across the WM skeleton, with a tendency to spare the occipital lobe. SCD-related cortical thinning and increased MD were associated with each other and jointly contributed to complaints, but the contribution of cortical thinning to the number of complaints was stronger.Conclusions: Neurodegeneration processes affecting the GM and WM seem to be associated with each other in SCD and include brain areas other than those typically targeted by Alzheimer's disease. Our findings suggest that SCD may be a sensitive behavioral marker of heterogeneous brain pathologies in individuals recruited from the community.
|
|
| 4. |
- Dartora, Caroline, et al.
(författare)
-
A deep learning model for brain age prediction using minimally preprocessed T1w images as input
- 2023
-
Ingår i: Frontiers in Aging Neuroscience. - : Frontiers Media SA. - 1663-4365 .- 1663-4365. ; 15
-
Tidskriftsartikel (refereegranskat)abstract
- Introduction: In the last few years, several models trying to calculate the biological brain age have been proposed based on structural magnetic resonance imaging scans (T1-weighted MRIs, T1w) using multivariate methods and machine learning. We developed and validated a convolutional neural network (CNN)-based biological brain age prediction model that uses one T1w MRI preprocessing step when applying the model to external datasets to simplify implementation and increase accessibility in research settings. Our model only requires rigid image registration to the MNI space, which is an advantage compared to previous methods that require more preprocessing steps, such as feature extraction. Methods: We used a multicohort dataset of cognitively healthy individuals (age range = 32.0–95.7 years) comprising 17,296 MRIs for training and evaluation. We compared our model using hold-out (CNN1) and cross-validation (CNN2–4) approaches. To verify generalisability, we used two external datasets with different populations and MRI scan characteristics to evaluate the model. To demonstrate its usability, we included the external dataset’s images in the cross-validation training (CNN3). To ensure that our model used only the brain signal on the image, we also predicted brain age using skull-stripped images (CNN4). Results: The trained models achieved a mean absolute error of 2.99, 2.67, 2.67, and 3.08 years for CNN1–4, respectively. The model’s performance in the external dataset was in the typical range of mean absolute error (MAE) found in the literature for testing sets. Adding the external dataset to the training set (CNN3), overall, MAE is unaffected, but individual cohort MAE improves (5.63–2.25 years). Salience maps of predictions reveal that periventricular, temporal, and insular regions are the most important for age prediction. Discussion: We provide indicators for using biological (predicted) brain age as a metric for age correction in neuroimaging studies as an alternative to the traditional chronological age. In conclusion, using different approaches, our CNN-based model showed good performance using one T1w brain MRI preprocessing step. The proposed CNN model is made publicly available for the research community to be easily implemented and used to study ageing and age-related disorders.
|
|
| 5. |
- Ekman, Urban, et al.
(författare)
-
The MemClin project : a prospective multi memory clinics study targeting early stages of cognitive impairment
- 2020
-
Ingår i: BMC Geriatrics. - : BMC. - 1471-2318 .- 1471-2318. ; 20
-
Tidskriftsartikel (refereegranskat)abstract
- Background: There remains a lack of large-scale clinical studies of cognitive impairment that aim to increase diagnostic and prognostic accuracy as well as validate previous research findings. The MemClin project will amass large quantities of cross-disciplinary data allowing for the construction of robust models to improve diagnostic accuracy, expand our knowledge on differential diagnostics, strengthen longitudinal prognosis, and harmonise examination protocols across centres. The current article describes the Memory Clinic (MemClin) project's study-design, materials and methods, and patient characteristics. In addition, we present preliminary descriptive data from the ongoing data collection.Methods: Nine out of ten memory clinics in the greater Stockholm area, which largely use the same examination methods, are included. The data collection of patients with different stages of cognitive impairment and dementia is coordinated centrally allowing for efficient and secure large-scale database construction. The MemClin project rest directly on the memory clinics examinations with cognitive measures, health parameters, and biomarkers.Results: Currently, the MemClin project has informed consent from 1543 patients. Herein, we present preliminary data from 835 patients with confirmed cognitive diagnosis and neuropsychological test data available. Of those, 239 had dementia, 487 mild cognitive impairment (MCI), and 104 subjective cognitive impairment (SCI). In addition, we present descriptive data on visual ratings of brain atrophy and cerebrospinal fluid markers.Conclusions: Based on our current progress and preliminary data, the MemClin project has a high potential to provide a large-scale database of 1200-1500 new patients annually. This coordinated data collection will allow for the construction of improved diagnostic and prognostic models for neurodegenerative disorders and other cognitive conditions in their naturalistic setting.
|
|
| 6. |
- Ferreira, Daniel, et al.
(författare)
-
The interactive effect of demographic and clinical factors on hippocampal volume : A multicohort study on 1958 cognitively normal individuals
- 2017
-
Ingår i: Hippocampus. - : Wiley. - 1050-9631 .- 1098-1063. ; 27:6, s. 653-667
-
Tidskriftsartikel (refereegranskat)abstract
- Alzheimer's disease is characterized by hippocampal atrophy. Other factors also influence the hippocampal volume, but their interactive effect has not been investigated before in cognitively healthy individuals. The aim of this study is to evaluate the interactive effect of key demographic and clinical factors on hippocampal volume, in contrast to previous studies frequently investigating these factors in a separate manner. Also, to investigate how comparable the control groups from ADNI, AIBL, and AddNeuroMed are with five population-based cohorts. In this study, 1958 participants were included (100 AddNeuroMed, 226 ADNI, 155 AIBL, 59 BRC, 295 GENIC, 279 BioFiNDER, 398 PIVUS, and 446 SNAC-K). ANOVA and random forest were used for testing between-cohort differences in demographic-clinical variables. Multiple regression was used to study the influence of demographic-clinical variables on hippocampal volume. ANCOVA was used to analyze whether between-cohort differences in demographic-clinical variables explained between-cohort differences in hippocampal volume. Age and global brain atrophy were the most important variables in explaining variability in hippocampal volume. These variables were not only important themselves but also in interaction with gender, education, MMSE, and total intracranial volume. AddNeuroMed, ADNI, and AIBL differed from the population-based cohorts in several demographic-clinical variables that had a significant effect on hippocampal volume. Variability in hippocampal volume in individuals with normal cognition is high. Differences that previously tended to be related to disease mechanisms could also be partly explained by demographic and clinical factors independent from the disease. Furthermore, cognitively normal individuals especially from ADNI and AIBL are not representative of the general population. These findings may have important implications for future research and clinical trials, translating imaging biomarkers to the general population, and validating current diagnostic criteria for Alzheimer's disease and predementia stages.
|
|
| 7. |
- Mårtensson, Gustav, et al.
(författare)
-
AVRA : Automatic visual ratings of atrophy from MRI images using recurrent convolutional neural networks
- 2019
-
Ingår i: NeuroImage. - : ELSEVIER SCI LTD. - 2213-1582. ; 23
-
Tidskriftsartikel (refereegranskat)abstract
- Quantifying the degree of atrophy is done clinically by neuroradiologists following established visual rating scales. For these assessments to be reliable the rater requires substantial training and experience, and even then the rating agreement between two radiologists is not perfect. We have developed a model we call AVRA (Automatic Visual Ratings of Atrophy) based on machine learning methods and trained on 2350 visual ratings made by an experienced neuroradiologist. It provides fast and automatic ratings for Scheltens' scale of medial temporal atrophy (MTA), the frontal subscale of Pasquier's Global Cortical Atrophy (GCA-F) scale, and Koedam's scale of Posterior Atrophy (PA). We demonstrate substantial inter-rater agreement between AVRA's and a neuroradiologist ratings with Cohen's weighted kappa values of kappa(w) = 0.74/0.72 (MTA left/right), kappa(w) = 0.62 (GCA-F) and kappa(w) = 0.74 (PA). We conclude that automatic visual ratings of atrophy can potentially have great scientific value, and aim to present AVRA as a freely available toolbox.
|
|
