This dataset is a combination of the following three datasets : figshare, SARTAJ dataset and Br35H
This dataset contains 7022 images of human brain MRI images which are classified into 4 classes: glioma - meningioma - no tumor and pituitary.
Attribution-NonCommercial-NoDerivs 4.0 (CC BY-NC-ND 4.0)https://creativecommons.org/licenses/by-nc-nd/4.0/
License information was derived automatically
Brain Cancer MRI Object Detection & Segmentation Dataset
The dataset consists of .dcm files containing MRI scans of the brain of the person with a cancer. The images are labeled by the doctors and accompanied by report in PDF-format. The dataset includes 10 studies, made from the different angles which provide a comprehensive understanding of a brain tumor structure.
MRI study angles in the dataset
💴 For Commercial Usage: Full version of the dataset… See the full description on the dataset page: https://huggingface.co/datasets/TrainingDataPro/brain-mri-dataset.
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
The Open Big Healthy Brains (OpenBHB) dataset is a large (N>5000) multi-site 3D brain MRI dataset gathering 10 public datasets (IXI, ABIDE 1, ABIDE 2, CoRR, GSP, Localizer, MPI-Leipzig, NAR, NPC, RBP) of T1 images acquired across 93 different centers, spread worldwide (North America, Europe and China). Only healthy controls have been included in OpenBHB with age ranging from 6 to 88 years old, balanced between males and females. All T1 images have been uniformly pre-processed with CAT12 (SPM), FreeSurfer (FSL) and Quasi-Raw (in-house minimal pre-processing) and they all passed a visual quality check. Both Voxel-Based Morphometry and Surface-Based Morphometry measures are available for each T1 MRI. Participant's age and sex are provided as well as the acquisition site, MRI magnetic field and MRI scanner settings used for each image acquisition. Note: OpenBHB has been divided into an official train, validation and test split for the open challenge currently deployed on brain age prediction and site-effect removal (see below). To avoid any data leakage during this challenge, data in test are kept private on the submission servers to compute the challenge metrics. Only training and validation data are openly available for now.The OpenBHB ChallengesBrain age prediction and debiasing with site-effect removalOpenBHB has been designed for brain age prediction and debiasing with site-effect removal in current brain MRI datasets through representation learning. The challenge consists in developing new algorithms taking as input T1 MRI images available in OpenBHB and outputting representation vectors preserving the biological variability (age) and removingundesirable non-biological confounding variables (acquisition site/settings). The representation quality is evaluated through linear probing on brain age prediction and site debiasing with various metrics (e.g Mean Absolute Error). All algorithms can be submitted on RAMP (check out our webpage for more details) with a public recording of their performance and an official leaderboard. This challenge should promote reproducible research in neuroimaging and it tackles 2 hot topics in both computer vision and neuroimaging, namely representation learning and debiasing.
Attribution-NonCommercial 4.0 (CC BY-NC 4.0)https://creativecommons.org/licenses/by-nc/4.0/
License information was derived automatically
OCMR is an open-access repository that provides multi-coil k-space data for cardiac cine. The fully sampled MRI datasets are intended for quantitative comparison and evaluation of image reconstruction methods. The free-breathing, prospectively undersampled datasets are intended to evaluate their performance and generalizability qualitatively.
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
This data set contains anonymised clinical MRI study, or a set of scans, of 515 patients with symptomatic back pains. Each patient data can have one or more MRI studies associated with it. Each study contains slices, i.e., individual images taken from either sagittal or axial view, of the lowest three vertebrae and the lowest three IVDs. The axial view slices are mainly taken from the last three IVDs – including the one between the last vertebrae and the sacrum. The orientation of the slices of the last IVD are made to follow the spine curve whereas those of the other IVDs are usually made in blocks – i.e., parallel to each other. There are between four to five slices per IVD and they begin from the top of the IVD towards its bottom. Many of the top and bottom slices cut through the vertebrae leaving between one to three slices that cut the IVD cleanly and show purely the image of that IVD. In most cases, the total number of slices in axial view ranges from 12 to 15. However, in some cases, there may be up to 20 slices because the study contains slices of more than last three vertebrae. The scans in sagittal view also vary but all contain at least the last seven vertebrae and the sacrum. While the number of vertebrae varies, each scan always includes the first two sacral links.
There are a total 48,345 MRI slices in our dataset. The majority of the slices have an image resolution of 320x320 pixels, however, there are slices from three studies with 320x310 pixel resolution. The pixels in all slices have 12-bit per pixel precision which is higher than the standard 8-bit greyscale images. Specifically for all axial-view slices, the slice thickness are uniformly 4 mm with centre-to-centre distance between adjacent slices to be 4.4 mm. The horizontal and vertical pixel spacing is 0.6875 mm uniformly across all axial-view slices.
The majority of the MRI studies were taken with the patient in Head-First-Supine position with the rests were taken with the patient in in Feet-First-Supine position. Each study can last between 15 to 45 minutes and a patient may have one or more study associated with them taken at a different time or a few days apart.
You can download and read the research papers detailing our methodology on boundary delineation for lumbar spinal stenosis detection using the URLs provided in the Related Links at the end of this page. You can also check out other dataset and source code related to this program from that section.
We kindly request you to cite our papers when using our data or program in your research.
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
Magnetic resonance imaging (MRI) provides a significant key to diagnose and monitor the progression of Multiple Sclerosis (MS) disease. Manual MS-Lesion segmentation, Expanded Disability Status Scale (EDSS) and patient’s meta information can provide a gold standard for research in terms of automated MS-lesion quantification, automated EDSS prediction and identification of the correlation between MS-lesion and patient disability. In this dataset, we provide a novel multi-sequence MRI dataset of 60 MS patients with consensus manual lesion segmentation, EDSS, general patient information and clinical information. On this dataset, three radiologists and neurologist experts segmented and validated the manual MS-lesion segmentation for three MRI sequences T1-weighted, T2-weighted and fluid-attenuated inversion recovery (FLAIR). The dataset can be used to study the relationship between MS-lesion, EDSS and patient clinical information. Furthermore, it also can be used to development of automated MS-lesion segmentation, patient disability prediction using MRI and correlation analysis between patient disability and MRI brain abnormalities include MS lesion location, size, number and type.
CC0 1.0 Universal Public Domain Dedicationhttps://creativecommons.org/publicdomain/zero/1.0/
License information was derived automatically
Experiment Details Participants watched Disney Pixar’s “Partly Cloudy” while lying in the scanner. There was no task; participants were simply instructed to lie still and watch the movie. The movie began after 10s of rest (black screen; TRs 1-5). The first 10s of the movie are the opening credits (disney castle, pixar logo; TRs 6-10).
IPS = 168 TRs TR = 2s Experiment length: 5.6 minutes
Pixar Movie Reverse Correlation Events Events defined by conducting reverse correlation analysis in two separate adult samples, using the average response in ToM brain regions (ToM events) and in the pain matrix (Pain events). Events listed are those that replicated across the two samples. Onsets and Durations are noted in TRs (1 TR = 2s); scanner trigger = TR 1.
Event types: Theory of Mind (ToM), Physical Sensation/Pain (Pain) TRs identified by RC analysis, as reported in Richardson et al. 2018 ToM Event Onsets; Durations 46; 2 52; 3 63; 2 91; 8 122; 3 129; 4 153; 3
Pain Event Onsets; Durations 38; 2 49; 1 56; 2 71; 5 100; 2 108; 6 117; 3 134; 3 159; 2
TIMING OF EVENTS FOR MODELING (taking into account hemodynamic lag (4s), scanner trigger = 0): All timings assume 10s from trigger until movie begins to play.
In seconds: Mental Event Onsets; Durations 86; 4 98; 6 120; 4 176; 16 238; 6 252; 8 300; 6
Pain Event Onsets; Durations 70; 4 92; 2 106; 4 136; 10 194; 4 210; 12 228; 6 262; 6 312; 4
In TRs when TR=2: Mental Event Onsets; Durations 43; 2 49; 3 60; 2 88; 8 119; 3 126; 4 150; 3
Pain Event Onsets; Durations 35; 2 46; 1 53; 2 68; 5 97; 2 105; 6 114; 3 131; 3 156; 2
The fastMRI dataset includes two types of MRI scans: knee MRIs and the brain (neuro) MRIs, and containing training, validation, and masked test sets. The deidentified imaging dataset provided by NYU Langone comprises raw k-space data in several sub-dataset groups. Curation of these data are part of an IRB approved study. Raw and DICOM data have been deidentified via conversion to the vendor-neutral ISMRMD format and the RSNA clinical trial processor, respectively. Also, each DICOM image is manually inspected for the presence of any unexpected protected health information (PHI), with spot checking of both metadata and image content. Knee MRI: Data from more than 1,500 fully sampled knee MRIs obtained on 3 and 1.5 Tesla magnets and DICOM images from 10,000 clinical knee MRIs also obtained at 3 or 1.5 Tesla. The raw dataset includes coronal proton density-weighted images with and without fat suppression. The DICOM dataset contains coronal proton density-weighted with and without fat suppression, axial proton density-weighted with fat suppression, sagittal proton density, and sagittal T2-weighted with fat suppression. Brain MRI: Data from 6,970 fully sampled brain MRIs obtained on 3 and 1.5 Tesla magnets. The raw dataset includes axial T1 weighted, T2 weighted and FLAIR images. Some of the T1 weighted acquisitions included admissions of contrast agent.
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
This brain tumor dataset contains 3064 T1-weighted contrast-inhanced images with three kinds of brain tumor. Detailed information of the dataset can be found in readme file.
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
The dataset contains ungated free-breathing cardiac MRI scans with different image resolutions and slice thicknesses. Specifically, two low-resolution scans (2.27mm x 2.26mm resolution at 264 x 186 acquisition matrix size) are available with 10mm slice thickness and isotropic slice thickness, respectively, and a high-resolution scan (1.25mm x 1.26mm resolution at 480 x 334 acquisition matrix size) with 5mm slice thickness. The scans were taken of a single healthy volunteer using a 2D Cartesian partial-Fourier sampling pattern on a 3T Philips Elition X scanner and image a short-axis view of the beating heart. The raw k-space data, sampling trajectory, and coil sensitivity maps (estimated by the scanner) are provided, as well as the cardiac phase estimated by an electrocardiogram.
CC0 1.0 Universal Public Domain Dedicationhttps://creativecommons.org/publicdomain/zero/1.0/
License information was derived automatically
Dataset obtained from Open Neuro. 15 cases with segmentation of side ventricles on brain MRI T1W scans. Cases obtained from open neuro: https://openneuro.org/ Segmentations done by the MedSeg team Our site: MedSeg Our tool: MedSeg Segmentation More data here
CC0 1.0 Universal Public Domain Dedicationhttps://creativecommons.org/publicdomain/zero/1.0/
License information was derived automatically
We present an ultra-high resolution MRI dataset of an ex vivo human brain specimen. The brain specimen was donated by a 58-year-old woman who had no history of neurological disease and died of non-neurological causes. After fixation in 10% formalin, the specimen was imaged on a 7 Tesla MRI scanner at 100 µm isotropic resolution using a custom-built 31-channel receive array coil. Single-echo multi-flip Fast Low-Angle SHot (FLASH) data were acquired over 100 hours of scan time (25 hours per flip angle), allowing derivation of synthesized FLASH volumes. This dataset provides an unprecedented view of the three-dimensional neuroanatomy of the human brain. To optimize the utility of this resource, we warped the dataset into standard stereotactic space. We now distribute the dataset in both native space and stereotactic space to the academic community via multiple platforms. We envision that this dataset will have a broad range of investigational, educational, and clinical applications that will advance understanding of human brain anatomy in health and disease.
Among member countries of the Organization of Economic Co-operation and Development (OECD), Japan has the highest density of magnetic resonance imaging (MRI) units. Over 57 such units are available per every million of its population. The United States and Korea follow with rates of some 28 and 36 per million inhabitants. Compared to these countries, Mexico and Colombia, for example, have around three and 0.2 MRI units per every million, respectively. The density of diagnostic imaging units can be one measurement to define the quality of a country’s health care infrastructure.
Why and when MRI is used The invention of MRI scanners revolutionized diagnostic imaging as it doesn’t use radiation, but a magnetic field and radio waves. Since ionized radiation as used in CT-scans and X-rays is potentially harmful for the patient, this includes a significant advantage for MRIs. MRI scans are principally used for imaging organs, soft tissues, ligaments, and other parts of the body which are difficult to see. While on the other hand, computer tomography (CT) scanners are more frequently used to show bony structures. Among the global top manufacturers of MRI scanners are General Electric, Siemens, Hitachi, and Philips.
The costs of MRI A single scan per MRI could cost up to 4,000 U.S. dollars, and thus double the cost of a scan with CT. The purchase of an MRI scanner could be a major investment for a practice or a hospital, with prices ranging from 150 thousand dollars up to several million dollars. Of course, there are installation and maintenance costs to be taken into account as well. With nearly 40 million MRI scans performed annually in the United States, it’s clear that diagnostic imaging costs are substantial.
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
This dataset was originally created by Yuanyu Anpei. To see the current project, which may have been updated since this version, please go here: https://universe.roboflow.com/yuanyuanpei7/5-8w.
This dataset is part of RF100, an Intel-sponsored initiative to create a new object detection benchmark for model generalizability.
Access the RF100 Github repo: https://github.com/roboflow-ai/roboflow-100-benchmark
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
Brain MR images along with the ground truths of WM, GM and CSF regions.For each case, brain masks for six 2D slices (150, 175, 200, 210, 225, 250) are also given.
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
Calgary Preschool MRI Dataset: The DTI dataset here comprises 396 unprocessed b750 diffusion weighted MRI scans from 120 participants aged 2-8 years.
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
Participants: six pediatric patients with resections to the visual cortex and two patients with resections outside the visual cortex, and 15 age-matched typically-developing controls. Images were acquired on a Siemens Verio 3T scanner with a 32-channel head coil at Carnegie Mellon University. For all participants: a skull-stripped T1-weighted anatomical image and one set of diffusion spectrum images are included here. See Maallo et al, "Effects of unilateral cortical resection of the visual cortex on bilateral human white matter," NeuroImage (in press), doi: 10.1016/j.neuroimage.2019.116345
EPISURG is a clinical dataset of $T_1$-weighted magnetic resonance images (MRI) from 430 epileptic patients who underwent resective brain surgery at the National Hospital of Neurology and Neurosurgery (Queen Square, London, United Kingdom) between 1990 and 2018.
The NIfTI files are anonymised and the images have been defaced to further protect the patients' identity.
The dataset comprises 430 postoperative MRI. The corresponding preoperative MRI is present for 269 subjects.
Three human raters segmented the resection cavity on partially overlapping subsets of EPISURG:
Rater 1: 133 subjects (researcher in neuroimaging) Rater 2: 34 subjects (clinical research fellow) Rater 3: 33 subjects (neurologist)
Acknowledgements If you use this dataset for your research please cite the following publications:
PĂ©rez-GarcĂa F., Rodionov R., Alim-Marvasti A., Sparks R., Duncan J.S., Ourselin S. (2020) Simulation of Brain Resection for Cavity Segmentation Using Self-supervised and Semi-supervised Learning. In: Martel A.L. et al. (eds) Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. Lecture Notes in Computer Science, vol 12263. Springer, Cham. https://doi.org/10.1007/978-3-030-59716-0_12
PĂ©rez-GarcĂa F., Rodionov R., Alim-Marvasti A., Sparks R., Duncan J.S., Ourselin S. EPISURG: MRI dataset for quantitative analysis of resective neurosurgery for refractory epilepsy. University College London (2020). DOI 10.5522/04/9996158.v1
Graphical user interface (GUI) The 3D Slicer extension EPISURG may be used to visualise the dataset.
Data use agreement The EPISURG data are distributed to the greater scientific community under the following terms:
You will not attempt to establish the identity or to make contact with any of the included subjects. You will acknowledge the use of EPISURG data and data derived from EPISURG data when publicly presenting any results or algorithms that benefitted from their use. Papers, book chapters, books, posters, oral presentations, and all other printed and digital presentations of results derived from EPISURG data should cite the publications listed above. You will not further disclose these data beyond the uses outlined in this agreement and understand that redistribution of data in any manner is prohibited. You will require anyone on your team who uses these data, or anyone with whom you share these data to comply with this data use agreement.
Attribution-NonCommercial-NoDerivs 4.0 (CC BY-NC-ND 4.0)https://creativecommons.org/licenses/by-nc-nd/4.0/
License information was derived automatically
Spine MRI Dataset, Anomaly Detection & Segmentation
The dataset consists of .dcm files containing MRI scans of the spine of the person with several dystrophic changes, such as degeneration of discs, osteophytes, dorsal disk extrusion, spondylitis and asymmetry of B2 segments of vertebral arteries. The images are labeled by the doctors and accompanied by report in PDF-format. The dataset includes 5 studies, made from the different angles which provide a comprehensive… See the full description on the dataset page: https://huggingface.co/datasets/TrainingDataPro/lumbar-spine-mri-dataset.
Breast MRI scans of 922 cancer patients from Duke University, with tumor bounding box annotations, clinical, imaging, and many other features, and more.
This dataset is a combination of the following three datasets : figshare, SARTAJ dataset and Br35H
This dataset contains 7022 images of human brain MRI images which are classified into 4 classes: glioma - meningioma - no tumor and pituitary.