OASIS-3 is a retrospective compilation of data for 1378 participants that were collected across several ongoing projects through the WUSTL Knight ADRC over the course of 30years. Participants include 755 cognitively normal adults and 622 individuals at various stages of cognitive decline ranging in age from 42-95yrs. All participants were assigned a new random identifier and all dates were removed and normalized to reflect days from entry into study. The dataset contains 2842 MR sessions which include T1w, T2w, FLAIR, ASL, SWI, time of flight, resting-state BOLD, and DTI sequences. Many of the MR sessions are accompanied by volumetric segmentation files produced through FreeSurfer processing. PET imaging from different tracers, PIB, AV45, and FDG, totaling over 2157 raw imaging scans and the accompanying post-processed files from the Pet Unified Pipeline (PUP) are also available in OASIS-3.
OASIS-3 and OASIS-4 are the latest releases in the Open Access Series of Imaging Studies (OASIS) that is aimed at making neuroimaging datasets freely available to the scientific community. By compiling and freely distributing this multimodal dataset generated by the Knight ADRC and its affiliated studies, we hope to facilitate future discoveries in basic and clinical neuroscience. OASIS-4 contains MR, clinical, cognitive, and biomarker data for 663 individuals aged 21 to 94 that presented with memory complaints. This is a unique dataset and not an update to the OASIS-3 Longitudinal Multimodal Neuroimaging dataset.
The Open Access Series of Imaging Studies (OASIS) is a project aimed at making neuroimaging data sets of the brain freely available to the scientific community. By compiling and freely distributing neuroimaging data sets, we hope to facilitate future discoveries in basic and clinical neuroscience.
OASIS-1 set consists of a cross-sectional collection of 416 subjects aged 18 to 96. For each subject, 3 or 4 individual T1-weighted MRI scans obtained in single scan sessions are included. The subjects are all right-handed and include both men and women. 100 of the included subjects over the age of 60 have been clinically diagnosed with very mild to moderate Alzheimer’s disease (AD). Additionally, a reliability data set is included containing 20 nondemented subjects imaged on a subsequent visit within 90 days of their initial session.
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
BackgroundAccording to the World Health Organization (WHO), dementia is the seventh leading reason of death among all illnesses and one of the leading causes of disability among the world’s elderly people. Day by day the number of Alzheimer’s patients is rising. Considering the increasing rate and the dangers, Alzheimer’s disease should be diagnosed carefully. Machine learning is a potential technique for Alzheimer’s diagnosis but general users do not trust machine learning models due to the black-box nature. Even, some of those models do not provide the best performance because of using only neuroimaging data.ObjectiveTo solve these issues, this paper proposes a novel explainable Alzheimer’s disease prediction model using a multimodal dataset. This approach performs a data-level fusion using clinical data, MRI segmentation data, and psychological data. However, currently, there is very little understanding of multimodal five-class classification of Alzheimer’s disease.MethodFor predicting five class classifications, 9 most popular Machine Learning models are used. These models are Random Forest (RF), Logistic Regression (LR), Decision Tree (DT), Multi-Layer Perceptron (MLP), K-Nearest Neighbor (KNN), Gradient Boosting (GB), Adaptive Boosting (AdaB), Support Vector Machine (SVM), and Naive Bayes (NB). Among these models RF has scored the highest value. Besides for explainability, SHapley Additive exPlanation (SHAP) is used in this research work.Results and conclusionsThe performance evaluation demonstrates that the RF classifier has a 10-fold cross-validation accuracy of 98.81% for predicting Alzheimer’s disease, cognitively normal, non-Alzheimer’s dementia, uncertain dementia, and others. In addition, the study utilized Explainable Artificial Intelligence based on the SHAP model and analyzed the causes of prediction. To the best of our knowledge, we are the first to present this multimodal (Clinical, Psychological, and MRI segmentation data) five-class classification of Alzheimer’s disease using Open Access Series of Imaging Studies (OASIS-3) dataset. Besides, a novel Alzheimer’s patient management architecture is also proposed in this work.
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
Analysis of ‘MRI and Alzheimers’ provided by Analyst-2 (analyst-2.ai), based on source dataset retrieved from https://www.kaggle.com/jboysen/mri-and-alzheimers on 28 January 2022.
--- Dataset description provided by original source is as follows ---
The Open Access Series of Imaging Studies (OASIS) is a project aimed at making MRI data sets of the brain freely available to the scientific community. By compiling and freely distributing MRI data sets, we hope to facilitate future discoveries in basic and clinical neuroscience. OASIS is made available by the Washington University Alzheimer’s Disease Research Center, Dr. Randy Buckner at the Howard Hughes Medical Institute (HHMI)( at Harvard University, the Neuroinformatics Research Group (NRG) at Washington University School of Medicine, and the Biomedical Informatics Research Network (BIRN).
When publishing findings that benefit from OASIS data, please include the following grant numbers in the acknowledgements section and in the associated Pubmed Central submission: P50 AG05681, P01 AG03991, R01 AG021910, P20 MH071616, U24 RR0213
Can you predict dementia? Alzheimer’s?
--- Original source retains full ownership of the source dataset ---
https://creativecommons.org/publicdomain/zero/1.0/https://creativecommons.org/publicdomain/zero/1.0/
The Open Access Series of Imaging Studies (OASIS) is a project aimed at making MRI data sets of the brain freely available to the scientific community. By compiling and freely distributing MRI data sets, we hope to facilitate future discoveries in basic and clinical neuroscience. OASIS is made available by the Washington University Alzheimer’s Disease Research Center, Dr. Randy Buckner at the Howard Hughes Medical Institute (HHMI)( at Harvard University, the Neuroinformatics Research Group (NRG) at Washington University School of Medicine, and the Biomedical Informatics Research Network (BIRN).
When publishing findings that benefit from OASIS data, please include the following grant numbers in the acknowledgements section and in the associated Pubmed Central submission: P50 AG05681, P01 AG03991, R01 AG021910, P20 MH071616, U24 RR0213
Can you predict dementia? Alzheimer’s?
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
IntroductionEarly studies have reported that APOE is strongly associated with brain atrophy and cognitive decline among healthy elders and Alzheimer’s disease (AD). However, previous research has not directly outlined the modulation of APOE on the trajectory of cerebral atrophy with aging during the conversion from cognitive normal (CN) to dementia (CN2D).MethodsThis study tried to elucidate this issue from a voxel-wise whole-brain perspective based on 416 qualified participants from a longitudinal OASIS-3 neuroimaging cohort. A voxel-wise linear mixed-effects model was applied for detecting cerebrum regions whose nonlinear atrophic trajectories were driven by AD conversion and to elucidate the effect of APOE variants on the cerebral atrophic trajectories during the process.ResultsWe found that CN2D participants had faster quadratically accelerated atrophy in bilateral hippocampi than persistent CN. Moreover, APOE ε4 carriers had faster-accelerated atrophy in the left hippocampus than ε4 noncarriers in both CN2D and persistent CN, and CN2D ε4 carriers an noncarriers presented a faster atrophic speed than CN ε4 carriers. These findings could be replicated in a sub-sample with a tough match in demographic information.DiscussionOur findings filled the gap that APOE ε4 accelerates hippocampal atrophy and the conversion from normal cognition to dementia.
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
BackgroundAccording to the World Health Organization (WHO), dementia is the seventh leading reason of death among all illnesses and one of the leading causes of disability among the world’s elderly people. Day by day the number of Alzheimer’s patients is rising. Considering the increasing rate and the dangers, Alzheimer’s disease should be diagnosed carefully. Machine learning is a potential technique for Alzheimer’s diagnosis but general users do not trust machine learning models due to the black-box nature. Even, some of those models do not provide the best performance because of using only neuroimaging data.ObjectiveTo solve these issues, this paper proposes a novel explainable Alzheimer’s disease prediction model using a multimodal dataset. This approach performs a data-level fusion using clinical data, MRI segmentation data, and psychological data. However, currently, there is very little understanding of multimodal five-class classification of Alzheimer’s disease.MethodFor predicting five class classifications, 9 most popular Machine Learning models are used. These models are Random Forest (RF), Logistic Regression (LR), Decision Tree (DT), Multi-Layer Perceptron (MLP), K-Nearest Neighbor (KNN), Gradient Boosting (GB), Adaptive Boosting (AdaB), Support Vector Machine (SVM), and Naive Bayes (NB). Among these models RF has scored the highest value. Besides for explainability, SHapley Additive exPlanation (SHAP) is used in this research work.Results and conclusionsThe performance evaluation demonstrates that the RF classifier has a 10-fold cross-validation accuracy of 98.81% for predicting Alzheimer’s disease, cognitively normal, non-Alzheimer’s dementia, uncertain dementia, and others. In addition, the study utilized Explainable Artificial Intelligence based on the SHAP model and analyzed the causes of prediction. To the best of our knowledge, we are the first to present this multimodal (Clinical, Psychological, and MRI segmentation data) five-class classification of Alzheimer’s disease using Open Access Series of Imaging Studies (OASIS-3) dataset. Besides, a novel Alzheimer’s patient management architecture is also proposed in this work.
A dataset for single-image 3D in the wild consisting of annotations of detailed 3D geometry for 140,000 images.
Oasis: One Image is All You Need for Multimodal Instruction Data Synthesis
This dataset contains Oasis-500k dataset. [Read the Paper] | [Github Repo]
All images come from Cambrian-10M. Instructions and responses are generated by MLLM.
This set is a subset of OASIS-3 subjects that have also undergone longitudinal TAU (AV1451) PET imaging.
The Mindboggle-101 surface and volume brain atlases were generated as part of the Mindboggle project (http://mindboggle.info) and are licensed under a Creative Commons License. The anatomical labels are combined across individually labeled brain volumes or surfaces from Mindboggle-101 according to the Desikan-Killiany-Tourville (DKT) labeling protocol: "101 labeled brain images and a consistent human cortical labeling protocol" Arno Klein, Jason Tourville. Frontiers in Brain Imaging Methods. 6:171. DOI: 10.3389/fnins.2012.00171 Volume atlas construction The joint fusion algorithm (Hongzhi Wang, 2013; distributed with ANTs) was used to construct probabilistic labels of the 20 OASIS-TRT brains, including a single volume of probabilities corresponding to the winning labels. Joint fusion was performed on the 20 brains after antsRegistration warped them to the OASIS-30 Atropos template. Results are also given after affine transformation to the OASIS-30 Atropos template in MNI152 space, and after resampling to 2mm^3 resolution. Code and documentation: CHANGELOG.txt: log of changes make_jointfusion_atlas.txt: code to make a joint fusion atlas resample2mm.txt: code to resample a volume to 2mm^3 resolution make_freesurfer_classifier_atlas.txt: software to make a FreeSurfer classifier atlas Joint fusion volume atlases (2013) OASIS-TRT-20_jointfusion_DKT31_CMA_labels_in_OASIS-30_v2.nii.gz OASIS-TRT-20_jointfusion_DKT31_CMA_labels_in_MNI152_v2.nii.gz OASIS-TRT-20_jointfusion_DKT31_CMA_labels_in_MNI152_2mm_v2.nii.gz Joint fusion label probabilities (2013) OASIS-TRT-20_jointfusion_DKT31_CMA_label_probabilities_in_OASIS-30_v2.nii.gz OASIS-TRT-20_jointfusion_DKT31_CMA_label_probabilities_in_MNI152_v2.nii.gz OASIS-TRT-20_jointfusion_DKT31_CMA_label_probabilities_in_MNI152_2mm_v2.nii.gz Cortical surface atlases (FreeSurfer classifier .gcs file) freesurfer_atlas_DKT31labels101subjects.tar.gz: from all 101 participants (2016) DKTatlas40.tar.gz: from 40 participants (2012)
Objective: To develop and evaluate a model for staging cortical amyloid deposition using PET with high generalizability.
Methods: 3027 subjects (1763 Cognitively Unimpaired (CU), 658 Impaired, 467 Alzheimer’s disease (AD) dementia, 111 non-AD dementia, and 28 with missing diagnosis) from six cohorts (EMIF-AD, ALFA, ABIDE, ADC, OASIS-3, ADNI) who underwent amyloid PET were retrospectively included; 1049 subjects had follow-up scans. Applying dataset-specific cut-offs to global Standard Uptake Value ratio (SUVr) values from 27 regions, single-tracer and pooled multi-tracer regional rankings were constructed from the frequency of abnormality across 400 CU subjects (100 per tracer). The pooled multi-tracer ranking was used to create a staging model consisting of four clusters of regions as it displayed a high and consistent correlation with each single-tracer ranking. Relationships between amyloid stage, clinical variables and longitudinal cognitive decline were investigated.
Results: SUV...
https://whoisdatacenter.com/terms-of-use/https://whoisdatacenter.com/terms-of-use/
Explore historical ownership and registration records by performing a reverse Whois lookup for the email address oasis@oasis3.com..
Data files and R code for Kurdi, B., Lozano, S., & Banaji, M. R. (2017). Introducing the Open Affective Standardized Image Set (OASIS). Behavior Research Methods, 49(2), 457–470. http://doi.org/10.3758/s13428-016-0715-3
Curated T1w MRI and CT scans from diverse sources, including the CERMEP-iDB-MRXFDG, OASIS3, NeuroMorphometrics1, IXI 2, and an in-house dataset.
In addition to OASIS-3 data, we introduce ‘OASIS-3_AV1451’ a cross-sectional TAU PET dataset for 451 subjects including 451 PET sessions and post-processed PUP. This set is a subset of OASIS-3 subjects that have also undergone TAU (AV1451) PET imaging.
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
T2-weighted (T2w)
Open Government Licence - Canada 2.0https://open.canada.ca/en/open-government-licence-canada
License information was derived automatically
The Occupational and Skills Information System (OaSIS) provides a comprehensive framework of the skills and competencies that are usually required to work in different occupations. It also provides context for the work environment in which these occupations are performed. This dataset provides information on 900 occupations including ratings for over 240 descriptors belonging to one of the following categories: Skills, Abilities, Personal attributes, Knowledge, Interests, Work activities and Work context. Standardized dimensions and scales were established at the category level for all categories, except Work context, for which specific dimensions and scales were adopted. All the descriptors under Skills and Abilities have ratings attributed by proficiency level required by occupation on a scale of 1 to 5. Descriptors under Personal attributes are measured by Importance on a scale of 1 to 5. Descriptors under Knowledge are measured by the knowledge level on a scale of 1 to3. Descriptors under Interests are measured by predominance ranking of Holland Codes. Descriptors under Work activities are measured by complexity on a scale of 1 to 5. Descriptors under Work context are measured by one or two of the following dimensions: - Frequency (1-5 scale) - 1 - Once a year or more but not every month - 2 - Once a month or more but not every week - 3 - Once a week or more but not every day - 4 - Every day, a few times per day - 5 - Every day, many times per day - Duration (1-5 scale) - 1 - Very little time - 2 - Less than half the time - 3 - About half the time - 4 - More than half the time - 5 - All the time, or almost all the time - Degree of responsibility (1-5 scale) - Physical distance from others (1-5 scale) - Degree of consequence of error (1-5 scale) - Degree of impact (1-5 scale) - Degree of freedom to make decisions (1-5 scale) - Degree of freedom to determine tasks and priorities (1-5 scale) - Degree of competition (1-5 scale) - Degree of automation (1-3 scale) - Work schedule (1-3 scale) - Worked hours in a typical week (1-3 scale) This dataset is of national relevance.
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
Alzheimer’s disease (AD) is a progressive neurodegenerative disorder with memory loss and cognitive impairment. The white matter (WM) BOLD signal has recently been shown to provide an important role in understanding the intrinsic cerebral activity. Although the altered homotopic functional connectivity within gray matter (GM-HFC) has been examined in AD, the abnormal HFC to WM remains unknown. The present study sought to identify changes in the WM-HFC and anatomic characteristics by combining functional magnetic resonance imaging with diffusion tensor imaging (DTI). Resting-state and DTI magnetic resonance images were collected from the OASIS-3 dataset and consisted of 53 mild cognitive impairment (MCI) patients, 90 very MCI (VMCI), and 100 normal cognitive (NC) subjects. Voxel-mirrored HFC was adopted to examine whether WM-HFC was disrupted in VMCI and MCI participants. Moreover, the DTI technique was used to investigate whether specific alterations of WM-HFC were associated with anatomic characteristics. Support vector machine analyses were used to identify the MCI and VMCI participants using the abnormal WM-HFC as the features. Compared with NC, MCI, and VMCI participants showed significantly decreased GM-HFC in the middle occipital gyrus and inferior parietal gyrus and decreased WM-HFC in the bilateral middle occipital and parietal lobe-WM. In addition, specific WM-functional network alteration for the bilateral sub-lobar-WM was found in MCI subjects. MCI subjects showed abnormal anatomic characteristics for bilateral sub-lobar and parietal lobe-WM. Results of GM-HFC mainly showed common neuroimaging features for VMCI and MCI subjects, whereas analysis of WM-HFC showed specific clinical neuromarkers and effectively compensated for the lack of GM-HFC to distinguish NC, VMCI, and MCI subjects.
OASIS-3 is a retrospective compilation of data for 1378 participants that were collected across several ongoing projects through the WUSTL Knight ADRC over the course of 30years. Participants include 755 cognitively normal adults and 622 individuals at various stages of cognitive decline ranging in age from 42-95yrs. All participants were assigned a new random identifier and all dates were removed and normalized to reflect days from entry into study. The dataset contains 2842 MR sessions which include T1w, T2w, FLAIR, ASL, SWI, time of flight, resting-state BOLD, and DTI sequences. Many of the MR sessions are accompanied by volumetric segmentation files produced through FreeSurfer processing. PET imaging from different tracers, PIB, AV45, and FDG, totaling over 2157 raw imaging scans and the accompanying post-processed files from the Pet Unified Pipeline (PUP) are also available in OASIS-3.