This dataset is collected from Kaggle ( https://www.kaggle.com/datasets/masoudnickparvar/brain-tumor-mri-dataset ). This dataset is a combination of the following three datasets :figshareSARTAJ datasetBr35H

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 the readme file.The README file is updated:Add image acquisition protocolAdd MATLAB code to convert .mat file to jpg images

The Brain/MINDS Marmoset MRI NA216 and eNA91 datasets currently constitutes the largest public marmoset brain MRI resource (483 individuals), and includes in vivo and ex vivo data for large variety of image modalities covering a wide age range of marmoset subjects.
* The in vivo part corresponds to a total of 455 individuals, ranging in age from 0.6 to 12.7 years (mean age: 3.86 ± 2.63), and standard brain data (NA216) from 216 of these individuals (mean age: 4.46 ± 2.62).
T1WI, T2WI, T1WI/T2WI, DTI metrics (FA, FAc, MD, RD, AD), DWI, rs-fMRI in awake and anesthetized states, NIfTI files (.nii.gz) of label data, individual brain and population average connectome matrix (structural and functional) csv files are included.
* The ex vivo part is ex vivo data, mainly from a subset of 91 individuals with a mean age of 5.27 ± 2.39 years.
It includes NIfTI files (.nii.gz) of standard brain, T2WI, DTI metrics (FA, FAc, MD, RD, AD), DWI, and label data, and csv files of individual brain and population average structural connectome matrices.

meningiomas

This dataset was curated in collaboration between the Computer Science and Engineering Department, University of Dhaka and the National Institute of Neuroscience, Bangladesh. It comprise 5,285 T1-weighted contrast- enhanced brain MRI images belonging to 38 categories. This work is accompanied by a paper found here http://arxiv.org/abs/2106.07333

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

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F12421376%2F5939be1e93e8e0c9f1ff922f184f70fe%2FFrame%2079.png?generation=1707920286083259&alt=media" alt="">

💴 For Commercial Usage: Full version of the dataset includes 100,000 brain studies of people with different conditions, leave a request on TrainingData to buy the dataset

Types of diseases and conditions in the full dataset:

• Cancer
• Multiple sclerosis
• Metastatic lesion
• Arnold-Chiari malformation
• Focal gliosis of the brain
• AND MANY OTHER CONDITIONS

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F12421376%2F0f5a27b8872e85fe23bf742593dc4843%2F2.gif?generation=1707920414940375&alt=media" alt="">

The MRI scans provide high-resolution images of the anatomical structures, allowing medical professionals to visualize the tumor, its location, size, and surrounding tissues.

The dataset holds great value for researchers and medical professionals involved in oncology, radiology, and medical imaging. It can be used for a wide range of purposes, including developing and evaluating novel imaging techniques, training and validating machine learning algorithms for automated tumor detection and segmentation, analyzing tumor response to different treatments, and studying the relationship between imaging features and clinical outcomes.

OTHER MEDICAL BRAIN MRI DATASETS:

• Brain MRI - Multiple Sclerosis Dataset
• Brain Anomaly Detection Dataset
• Normal Brain MRI Dataset
• Fazekas Detection - MRI Dataset

💴 Buy the Dataset: This is just an example of the data. Leave a request on https://trainingdata.pro/datasets to discuss your requirements, learn about the price and buy the dataset

Content

The dataset includes:

• ST000001: includes subfolders with 10 studies. Each study includes MRI-scans in .dcm and .jpg formats,
• DICOMDIR: includes information about the patient's condition and links to access files,
• Brain_MRI_1.pdf: includes medical report, provided by the radiologist,
• .csv file: includes id of the studies and the number of files

Medical reports include the following data:

• Patient's demographic information,
• Description of the case,
• Preliminary diagnosis,
• Recommendations on the further actions

All patients consented to the publication of data

Medical data might be collected in accordance with your requirements.

TrainingData provides high-quality data annotation tailored to your needs

keywords: tumors, cloud, testing, glioma, related, pytorch, directories, science, improve, directory, malignant, classify, accuracy, level, classified, cancerous, magnetic, neural, resonance, mri brain scan, brain tumor, brain cancer, oncology, neuroimaging, radiology, brain metastasis, glioblastoma, meningioma, pituitary tumor, medulloblastoma, astrocytoma, oligodendroglioma, ependymoma, neuro-oncology, brain lesion, brain metastasis detection, brain tumor classification, brain tumor segmentation, brain tumor diagnosis, brain tumor prognosis, brain tumor treatment, brain tumor surgery, brain tumor radiation therapy, brain tumor chemotherapy, brain tumor clinical trials, brain tumor research, brain tumor awareness, brain tumor support, brain tumor survivor, neurosurgery, neurologist, neuroradiology, neuro-oncologist, neuroscientist, medical imaging, cancer detection, cancer segmentation, tumor, computed tomography, head, skull, brain scan, eye sockets, sinuses, computer vision, deep learning

The Bangladesh Brain Cancer MRI Dataset is a comprehensive collection of MRI images aimed at supporting research in medical diagnostics, particularly in the study of brain cancer. This dataset contains a total of 6056 images, systematically categorized into three distinct classes:

Brain_Glioma: 2004 images Brain_Menin: 2004 images Brain Tumor: 2048 images Each image in the dataset has been meticulously collected from various hospitals across Bangladesh, ensuring a diverse and representative sample. The images are uniformly resized to 512x512 pixels to facilitate compatibility with various image processing, machine learning, and deep learning algorithms.

The dataset is particularly valuable due to the rarity and difficulty in obtaining such medical imaging data, especially in the context of brain cancer. The collection process was made possible through the direct involvement of medical professionals, including experienced doctors who ensured the accuracy and relevance of the data. This collaboration underscores the dataset's potential utility in advancing modern medical science, offering a reliable resource for developing and testing diagnostic tools.

Researchers and practitioners can utilize this dataset for various applications, including but not limited to:

Image Processing: Enhancing and analyzing MRI images for better visualization and interpretation. Deep Learning: Training neural networks for automated classification and detection of brain cancer. Machine Learning: Developing predictive models to assist in early diagnosis and treatment planning. The dataset's focus on MRI images, a key diagnostic tool in oncology, makes it a crucial asset for anyone involved in the study or treatment of brain cancer.

Data Source

https://www.kaggle.com/datasets/navoneel/brain-mri-images-for-brain-tumor-detection

  Dataset Card Authors

Mahadi Hassan

  Dataset Card Contact





  mahadise01@gmail.com





  Linkdin: https://www.linkedin.com/in/mahadise01





  Github: https://github.com/Mahadih534

This Bangladeshi Brain Cancer MRI Dataset is a large dataset of Magnetic Resonance Imaging (MRI) images created to aid researchers in medical diagnosis, especially for brain cancer research. This collection contains a total of 1600 raw photos (every class have 400 raw images) after augmentation it contains total 6000 images, which are wisely divided into four main categories as:

Glioma -1500 images

Meningioma -1500 images

Pituitary-1500 images

No Tumor-1500 images

All the images in this dataset were collected from different hospitals around Bangladesh. It brought diversity and representation into the sample. To make the images compatible with various image processing, machine learning and deep-learning pipelines as possible they are then resized to a standardize size of 512×512.

This dataset is incredibly significant since high-quality data, such as medical imaging data, are few and difficult to obtain, particularly in the context of brain cancer. Assume that four prominent doctors collaborate on data collection in order to give more accurate and helpful content. It made it feasible. The cooperation emphasizes the dataset's potential to improve medical practice today by providing a dependable supply of diagnoses for use in diagnostic tool creation and testing within current medicine.

This dataset can be used by researchers and practitioners for a variety of applications such as Dense net 201, yolov8x/s, CNN, resnet50v2, VGG-16, MobilenetV2 etc.

Image Processing Details:

Images are randomly rotated within a range of 45 degrees. (rotation range=45)

Images are horizontally shifted by up to 20% of the width of the image. (width_shift_range=0.2)

Images are vertically shifted by up to 20% of the height of the image. (height_shift_range=0.2)

Shear transformation is applied to the image within a range of 20%. (shear range=0.2)

Images are randomly zoomed in or out by up to 20%. (zoom range=0.2)

Images are randomly flipped horizontally. (horizontal flip=True)

When transformations like rotations or shifts leave empty areas in the image, they are filled in by the nearest pixel values. (fill mode='nearest')

Hospital List(for Data Collection):

Ibn Sina Medical College, Kollanpur, 1, 1-B Mirpur Rd, Dhaka 1207

Dhaka Medical College & Hospital, Secretariat Rd, Dhaka 1000

Cumilla Medical College, Kuchaitoli, Dr. Akhtar Hameed Khan Road, Cumilla 3500, Bangladesh

Supervisor & investigator:

Md. Mizanur Rahman

Lecturer,

Computer Science and Engineering

Daffodil International University

Dhaka, Bangladesh

mizanurrahman.cse@diu.edu.bd

Data Collectors:

Md Shahriar Mannan Prottoy

Mahtab Chowdhury

Redwan Rahman

Azim Ullah Tamim

Unidata’s Brain MRI dataset offers unique MRI scans and radiologist reports, aiding AI in detecting and diagnosing brain pathologies

LGG Segmentation Dataset

This dataset contains brain MR images together with manual FLAIR abnormality segmentation masks. The images were obtained from The Cancer Imaging Archive (TCIA). They correspond to 110 patients included in The Cancer Genome Atlas (TCGA) lower-grade glioma collection with at least fluid-attenuated inversion recovery (FLAIR) sequence and genomic cluster data available. Tumor genomic clusters and patient data is provided in data.csv file. All images are… See the full description on the dataset page: https://huggingface.co/datasets/yummy456/brain-mri-dataset.

GSP

1) Data Introduction • The Brain Tumor MRI Dataset is a collection of Magnetic Resonance Imaging (MRI) images curated for the classification of brain tumors. The dataset consists of MRI scans categorized into four classes: glioma, meningioma, pituitary tumor, and no tumor.

2) Data Utilization (1) Characteristics of the Brain Tumor MRI Dataset: • This dataset has been constructed as training data for artificial intelligence (AI) models aimed at the early detection and precise classification of brain tumors. It helps improve the accuracy and efficiency of medical diagnoses. • Each image is labeled with the tumor type, making the dataset well-suited for multiclass classification tasks.

(2) Applications of the Brain Tumor MRI Dataset: • Development of tumor classification models: The dataset can be used to develop AI systems that automatically classify the type of brain tumor. • Detection of tumor location and boundaries: The dataset can be utilized to train models that not only detect the presence of a tumor but also identify its location and size, contributing to effective pre-surgical planning.

Brain MRI image dataset - 2,000,000+ Studies

Dataset comprises 2,000,000+ medical studies featuring brain MRI scans paired with radiologists' reports, including detailed descriptions, conclusions, and recommendations. This large-scale dataset provides high-quality imaging data with 1 mm slice thickness and ≤5 mm interslice gap, averaging ~30 slices per scan. Designed for detection, classification, and segmentation tasks, it covers 50+ pathologies, including brain tumors, lesions… See the full description on the dataset page: https://huggingface.co/datasets/ud-medical/Brain-MRI-Dataset.

Abstract

A dataset of training and test images for the Brain Tumor Identification notebook found at: https://www.kaggle.com/code/faridtaghiyev/brain-tumor-detection-using-tensorflow-2-x/notebook

Methodology

The dataset comprises MRI images labeled for brain tumor presence. Images are split into training (70%), validation (15%), and test (15%) sets. Preprocessing includes resizing to 256x256 pixels, normalization, and augmentation (rotation, flipping). Models are trained using TensorFlow on a CNN architecture, optimized with Adam, and evaluated based on accuracy, precision, recall, and F1-score.

Usage

This public dataset is available for non-commercial use. Any publications or derivatives from these data must credit the original source. Please cite appropriately when using or referencing this dataset in any capacity.

This dataset from Taipei Veterans General Hospital represents the most comprehensive collection of brain metastases MRI data in the country. It includes axial SE T1WI+C images annotated according to the standard DICOM-RT structure set (RTSS) format, used in both clinical evaluations and Gamma Knife treatments of intracranial metastatic tumors. Each case in the dataset comprises T1-weighted images (T1W), T2-weighted images (T2W), and T1 post-contrast weighted images (T1W+C). The dataset is notable for the high number of cases and the exceptional completeness and precision of the annotations, making it one of the most extensive and detailed brain metastases datasets globally. This allows for a diverse range of AI research projects.

Brain Tumors MRI Images - 2,000,000+ MRI studies

The dataset consists of MRI scans of human brains with medical reports and is designed to detection, classification, and segmentation of tumors in cancer patients. The data includes a variety of brain tumors such as gliomas, benign tumors, malignant tumors, and brain metastasis, along with clinical information for each patient - Get the data

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F22059654%2F5ba9523bd62469f31fa62990f808aca1%2FFrame%20132.png?generation=1726732995654454&alt=media" alt="">

The MRI scans provide detailed medical imaging of different tissues and tumor regions, facilitating tasks such as tumor segmentation, tumor identification, and classifying brain tumors. This dataset is particularly valuable for early detection, diagnosis, and treatment planning in clinical settings, focusing on accurate diagnosis of various cancer types.

💵 Buy the Dataset: This is a limited preview of the data. To access the full dataset, please contact us at https://unidata.pro to discuss your requirements and pricing options.

Content

The dataset includes: - ST000001: includes subfolders with 10 studies. Each study includes MRI-scans in .dcm and .jpg formats, - DICOMDIR: includes information about the patient's condition and links to access files, - Brain_MRI_tumor.pdf: includes medical report, provided by the radiologist, - .csv file: includes the number of studies by conditions and methods of study

Medical reports include the following data:

• Type of a study,
• MRI machine (mostly Philips Intera 1.5T),
• Patient's demographic information (age, sex, race),
• Brief anamnesis of the disease (complaints),
• Description of the case,
• Preliminary diagnosis,
• Recommendations on the further actions

All patients consented to the publication of data, data is unidentified

Researchers can utilize the dataset for a variety of deep learning tasks including tumor detection, classification, and segmentation, with a focus on improving validation accuracy in real-world clinical diagnosis scenarios. The dataset can also support the development of trained models for automatic detection and tumor typing, which is critical for both clinical diagnosis and treatment approaches.

🌐 UniData provides high-quality datasets, content moderation, data collection and annotation for your AI/ML projects

The dataset comprises 750+ Brain MRI images taken from different patients considering whether they have brain stroke or not. The Dataset consists of three subdirectories: - Normal _ Stroke Patient Details -> This subdirectory consists of 750+ raw Brain MRI images of patients. - Dataset_MRI_Folder -> This subdirectory consists of 3 more subdirectories called Haemorrhagic, Ischemic and Normal which store the relevant Brain MRI Images. - Stroke Classification -> This subdirectory is an updated version of Dataset_MRI_Folder as it contains preprocessed MRI scan images without the text over them.

This dataset was created to train an image classification model to detect whether an MRI Image of a human brain consists of** Ischemic** or Haemorrhagic stroke if present.

A brain MRI dataset to develop and test improved methods for detection and segmentation of brain metastases. The dataset includes 156 whole brain MRI studies, including high-resolution, multi-modal pre- and post-contrast sequences in patients with at least 1 brain metastasis accompanied by ground-truth segmentations by radiologists.

Abstract

We present a dataset of 11,892 longitudinal brain MRI studies from 1,430 patients with clinically confirmed brain metastases. T1-weighted pre-contrast, T1-weighted post-contrast, T2-weighted, and fluid-attenuated inversion recovery MRI sequence images are provided in NIfTI format. Additionally, an Excel spreadsheet with patient demographic information, scanner details, and image acquisition parameters are provided. This dataset will facilitate the development of AI models to assist in the long-term management of patients with brain metastasis.

Introduction

Brain metastases are associated with significant morbidity, (Achrol 2019, Sacks 2020, Lamba 2021) necessitating frequent radiologic assessment in collaboration with neuro-oncologists to evaluate treatment response and disease progression. Magnetic resonance imaging (MRI) is a cornerstone in the management of central nervous system metastases, (Brenner 2022, Lin 2015, Vogelbaum 2022, Le Rhun 2021, Patil 2017, Kraft 2019, Aldawsari 2023) providing critical insights over time. (Kang 2009, Friedman 2001, Lunsford 1998)

Artificial intelligence (AI) emerged as a valuable tool for prognosis and treatment planning in neuro-oncology. (Cassinelli Petersen 2022, Aneja 2019, Aboian 2022, Aboian 2022, Rudie 2021, Xue 2020) However, the creation of widely applicable clinical models is constrained by the scarcity of large-scale, heterogeneous datasets. (Aneja 2019, Rudie 2019) This underscores the need for a longitudinal imaging dataset that captures a diverse range of imaging patterns, scanner technologies, and acquisition techniques. In response to this gap, we introduce a dataset spanning nearly 20 years, including pre- and post-treatment imaging across four essential MRI sequences.

To our knowledge, this is the largest publicly available MRI dataset of patients with brain metastases. By providing open access to this resource, we hope to enable diverse research applications, from conventional radiologic investigations to state-of-the-art machine learning approaches, ultimately contributing to better patient outcomes and a more comprehensive understanding of brain metastases. The inclusion of both imaging and clinical data makes this dataset a valuable asset for researchers in oncology, neuroradiology, and data science.

Methods

The following subsections provide information about how the data were selected, acquired and prepared for publication, approximate date range of imaging studies.

Subject Inclusion and Exclusion Criteria

The electronic medical record (EMR) system at Yale New Haven Hospital was searched for MRI scans performed between 2004 and 2023 that evaluated brain metastases. This automated query initially retrieved 46,364 MRI studies from 7,111 patients with potential intracranial metastatic disease. A subsequent manual review of the electronic health record (EHR) excluded cases lacking radiologic or pathologic confirmation of brain metastases.

To ensure consistency, only MRI exams containing axial T1-weighted (T1W), contrast-enhanced T1-weighted (T1CE), T2-weighted (T2), or fluid-attenuated inversion recovery (FLAIR) sequences were selected. For patients who underwent treatments targeting brain metastases—such as stereotactic radiosurgery, whole-brain radiotherapy, or surgical resection—pre-treatment scans taken within 30 days before treatment initiation were retained, along with all follow-up imaging to enable longitudinal analysis of disease progression and treatment effects. After these refinements, the final dataset comprised 11,892 MRI studies from 1,430 patients with confirmed brain metastases.

This retrospective study was approved by the Institutional Review Board of Yale University on 10/01/2020, protocol 2000029055.

Data Acquisition

Radiology: Most of the MRI scans were obtained using 1.5T or 3T scanners manufactured by Siemens Healthineers or General Electric Healthcare. Image data and associated metadata were extracted through the application programming interface of Visage (Visage 7, Visage Imaging, Inc., San Diego, CA). DICOM metadata enabled the retrieval of key imaging parameters, including study location, scanner manufacturer, scanner model, magnetic field strength, acquisition type (2D vs. 3D), sequence designation, slice thickness, slice spacing, repetition time, echo time, and inversion time. A comprehensive breakdown of these acquisition parameters for each scan is available in the accompanying Excel file.

Clinical: Patient baseline information was extracted from the EMR for each study time point. The recorded data include the patient's age at the time of imaging, sex, study date. All data were retrieved as of December 2023.

Data Analysis

MRI Sequence Selection and Standardization: The MRI sequences T1W, T1CE, T2, and FLAIR were chosen for inclusion due to their essential role in evaluating brain metastases, as they provide complementary imaging characteristics critical for diagnosis and longitudinal assessment. To ensure consistency across the dataset, MRI sequence names were standardized to address variations in DICOM metadata arising from differences in scanners, radiology technicians, imaging sites, and longitudinal studies.

A manual review of studies guided the development of a rules-based image classifier and validation process. Images were filtered based on factors such as orientation, acquisition technique, contrast enhancement, and spin echo variations to retain only relevant sequences. Additionally, redundant sequence identifiers were removed to streamline naming conventions. This structured approach ensured precise inclusion and uniform labeling of MRI sequences, enhancing the dataset’s reliability for longitudinal analysis.

Anonymization

The selected studies were subsequently exported as NIfTI files to a secure external drive using the Visage application programming interface. Following sequence selection and standardization, HD-BET was applied to extract brain parenchyma from each image, ensuring the removal of identifiable facial features.

Usage Notes

MRI scans are accompanied by an Excel file containing separate sheets for clinical data and radiologic image acquisition parameters. Each brain metastasis study includes up to four files corresponding to T1W, T1CE, T2W, and/or FLAIR sequences. All imaging data were exported from the Visage AI Accelerator in NIfTI format and processed for brain extraction.

File names follow a standardized format, incorporating an anonymous patient identifier, anonymized study date-time, and sequence type, structured as caseID_date-time_sequence.nii.gz to ensure clarity and consistency across the dataset.