4.7 Review

A Survey of Publicly Available MRI Datasets for Potential Use in Artificial Intelligence Research

Related references

Note: Only part of the references are listed.
Review Medicine, General & Internal

The Systematic Review of Artificial Intelligence Applications in Breast Cancer Diagnosis

Dilber Uzun Ozsahin et al.

Summary: This study provides detailed knowledge on the applications of AI in the diagnosis of breast cancer through citation analysis. The majority of AI applications use classification models for breast cancer prediction, with accuracy being the highest performance metric followed by specificity and area under the curve. Convolutional Neural Network is the most commonly used model. The study suggests that the quantity and quality of AI applications in breast cancer diagnosis will continue to increase, aiming to supplement doctors' clinical reasoning and provide accessible healthcare worldwide.

DIAGNOSTICS (2023)

Article Cardiac & Cardiovascular Systems

MITEA: A dataset for machine learning segmentation of the left ventricle in 3D echocardiography using subject-specific labels from cardiac magnetic resonance imaging

Debbie Zhao et al.

Summary: Segmentation of the left ventricle in echocardiography is important for volume and mass quantification in heart disease. Analyzing 3D echocardiography poses challenges due to limited resolution, poor contrast, complex noise, and image anisotropy. To address the lack of labeled data, the researchers used high-resolution cardiac magnetic resonance imaging to provide ground truth labels and created a dataset of 536 3DE images. A deep learning network trained on this dataset achieved better accuracy and reproducibility compared to manual analysis.

FRONTIERS IN CARDIOVASCULAR MEDICINE (2023)

Article Computer Science, Interdisciplinary Applications

Towards Automated Brain Aneurysm Detection in TOF-MRA: Open Data, Weak Labels, and Anatomical Knowledge

Tommaso Di Noto et al.

Summary: Brain aneurysm detection in Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) has been significantly improved with the use of Deep Learning (DL). The study presents a DL model that overcomes the challenge of obtaining expensive labeled samples by using oversized annotations. The model also leverages anatomical knowledge to focus on plausible locations for aneurysm occurrence. The model achieved high sensitivity in both internal dataset evaluation and a public challenge.

NEUROINFORMATICS (2023)

Article Multidisciplinary Sciences

Biventricular shape modes discriminate pulmonary valve replacement in tetralogy of Fallot better than imaging indices

Sachin Govil et al.

Summary: The indications for pulmonary valve replacement (PVR) in repaired tetralogy of Fallot (rTOF) are inconsistent and remain debated. This study aimed to determine if specific markers of biventricular shape can better discriminate between rTOF patients who do and do not require PVR compared to standard imaging indices. The results showed that these regional features of cardiac morphology may provide insight into an improved patient-specific assessment tool for clinical use in determining the need for PVR.

SCIENTIFIC REPORTS (2023)

Article Multidisciplinary Sciences

A comprehensive dataset of annotated brain metastasis MR images with clinical and radiomic data

Beatriz Ocana-Tienda et al.

Summary: Brain metastasis is a common complication of many cancers, and artificial intelligence has the potential to assist in disease management. However, there is a lack of available datasets for AI methods. This paper provides a large dataset of high-resolution imaging studies, including segmentations and clinical data, which can facilitate research and evaluation of automatic detection and treatment planning methods for brain metastasis.

SCIENTIFIC DATA (2023)

Article Multidisciplinary Sciences

M4Raw: A multi-contrast, multi-repetition, multi-channel MRI k-space dataset for low-field MRI research

Mengye Lyu et al.

Summary: This study introduces the M4Raw dataset to facilitate methodology development and reproducible research in low-field magnetic resonance imaging (MRI). The dataset includes multi-channel brain k-space data collected from 183 healthy volunteers using a 0.3 Tesla whole-body MRI system, with T1-weighted, T2-weighted, and FLAIR images. It can be used for advanced data-driven methods in low-field MRI and as a benchmark dataset for general MRI reconstruction algorithms.

SCIENTIFIC DATA (2023)

Article Multidisciplinary Sciences

The Queensland Twin Adolescent Brain Project, a longitudinal study of adolescent brain development

Lachlan T. Strike et al.

Summary: The QTAB dataset includes multimodal neuroimaging, cognitive, and mental health data of adolescent twins. It provides a detailed methodology and technical validation for data usage. The project aims to promote health-related research in adolescence.

SCIENTIFIC DATA (2023)

Article Radiology, Nuclear Medicine & Medical Imaging

Effect of Human- AI Interaction on Detection of Malignant Lung Nodules on Chest Radiographs

Jong Hyuk Lee et al.

Summary: This study assessed the impact of AI diagnostic performance and reader characteristics on the detection of malignant lung nodules during AI-assisted reading of chest radiographs. The use of a high accuracy AI model improved readers' detection performance to a greater extent than a low accuracy AI model, and readers using the high accuracy AI showed a higher susceptibility to changing their diagnosis based on AI suggestions.

RADIOLOGY (2023)

Review Pediatrics

How does artificial intelligence in radiology improve efficiency and health outcomes?

Kicky G. van Leeuwen et al.

Summary: The potential benefits of AI in radiology include improving workflow efficiency, reducing reading time, minimizing doses, earlier disease detection, enhanced diagnostic accuracy, and personalized diagnostics. However, the market is still evolving, and there is limited understanding of AI's value and contribution to clinical practice.

PEDIATRIC RADIOLOGY (2022)

Article Multidisciplinary Sciences

The Mexican magnetic resonance imaging dataset of patients with cocaine use disorder: SUDMEX CONN

Diego Angeles-Valdez et al.

Summary: Cocaine use disorder (CUD) is a serious substance use disorder with significant impacts on patients, families, and society. The SUDMEX CONN dataset provides valuable data, including MRI, for researchers to study CUD and other substance use disorders.

SCIENTIFIC DATA (2022)

Article Multidisciplinary Sciences

Neurocognitive aging data release with behavioral, structural and multi-echo functional MRI measures

R. Nathan Spreng et al.

Summary: This article provides two 10-minute multi-echo functional MRI (ME-fMRI) runs and structural MRI (T1-MPRAGE) data, as well as a large amount of behavioral assessment data, including cognition, personality, and socioemotional functioning. These data are valuable for scientists studying BOLD signal, brain-behavior associations, and aging effects in healthy adults.

SCIENTIFIC DATA (2022)

Article Multidisciplinary Sciences

Multi-scanner and multi-modal lumbar vertebral body and intervertebral disc segmentation database

Yasmina Al Khalil et al.

Summary: MRI is widely used for diagnosing and monitoring spinal disorders. Manual segmentation of examined structures is time-consuming and prone to errors. This study presents a manually segmented lumbar spine MRI database for developing and testing automated lumbar spine segmentation algorithms in multi-domain scenarios.

SCIENTIFIC DATA (2022)

Article Multidisciplinary Sciences

ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation dataset

Moritz R. Hernandez Petzsche et al.

Summary: Magnetic resonance imaging (MRI) is a crucial imaging modality for stroke diagnosis, and computer-assisted automated medical image processing is becoming more prevalent in clinical practice. The ISLES challenge aims to develop benchmark methods for the segmentation of acute and sub-acute ischemic stroke lesions. We introduce an expert annotated, multicenter MRI dataset with high variability in stroke lesion size, quantity, and location. This dataset serves as the foundation for the ISLES 2022 challenge, which seeks algorithmic methods to enable the development and benchmarking of automatic, robust, and accurate segmentation methods for ischemic stroke.

SCIENTIFIC DATA (2022)

Article Multidisciplinary Sciences

TractoInferno-A large-scale, open-source, multi-site database for machine learning dMRI tractography

Philippe Poulin et al.

Summary: TractoInferno is the largest open-source multi-site tractography database in the world, aimed at providing standardized training datasets and evaluation protocols for machine learning tractography approaches. It includes 284 samples from different sites, covering a wide range of data and algorithms for research and evaluation.

SCIENTIFIC DATA (2022)

Article Multidisciplinary Sciences

The University of Pennsylvania glioblastoma (UPenn-GBM) cohort: advanced MRI, clinical, genomics, & radiomics

Spyridon Bakas et al.

Summary: Glioblastoma is the most common aggressive adult brain tumor. The publicly available datasets for glioblastoma studies have limitations in terms of subject number, acquisition protocol consistency, data quality, and clinical information. To address these limitations, the University of Pennsylvania has contributed the UPenn-GBM dataset, which is currently the largest publicly available collection of 630 patients diagnosed with de novo glioblastoma. This dataset includes advanced multi-parametric magnetic resonance imaging scans, clinical and molecular information, derivative volumes, expert annotations, and quantitative imaging features.

SCIENTIFIC DATA (2022)

Article Multidisciplinary Sciences

A large, curated, open-source stroke neuroimaging dataset to improve lesion segmentation algorithms

Sook-Lei Liew et al.

Summary: Accurate lesion segmentation is critical in stroke rehabilitation research. Current automated methods lack accuracy and reliability. To encourage better algorithm development, a larger dataset has been released. The use of this dataset and unbiased performance evaluation through hidden datasets should lead to improved algorithms and facilitate large-scale stroke research.

SCIENTIFIC DATA (2022)

Article Biology

Prostate158-An expert-annotated 3T MRI dataset and algorithm for prostate cancer detection

Lisa C. Adams et al.

Summary: This study provides an openly accessible, expert-annotated 3T dataset of prostate MRI and establishes a reproducible benchmark to foster the development of prostate segmentation algorithms.

COMPUTERS IN BIOLOGY AND MEDICINE (2022)

Article Multidisciplinary Sciences

The Cuban Human Brain Mapping Project, a young and middle age population-based EEG, MRI, and cognition dataset

Pedro A. Valdes-Sosa et al.

Summary: The CHBMP repository is an open multimodal neuroimaging and cognitive dataset from 282 healthy participants in Cuba, including EEG, MRI, psychological tests, and demographic information. This dataset is hosted by Synapse.org and available for access.

SCIENTIFIC DATA (2021)

Article Multidisciplinary Sciences

The Amsterdam Open MRI Collection, a set of multimodal MRI datasets for individual difference analyses

Lukas Snoek et al.

Summary: AOMIC is a collection of three datasets with multimodal MRI data from a large set of healthy participants, including structural, diffusion-weighted, and functional BOLD MRI data. The extensively annotated event-files for task-based fMRI during various paradigms are available. All data are publicly available on the OpenNeuro platform after undergoing extensive quality control.

SCIENTIFIC DATA (2021)

Article Anatomy & Morphology

The MRi-Share database: brain imaging in a cross-sectional cohort of 1870 university students

Ami Tsuchida et al.

Summary: The study introduces the MRi-Share multi-modal brain MRI database, detailing the neuroimaging datasets of 1870 young healthy adults and presenting preliminary findings on brain structure changes in late adolescence. Results indicate that grey matter cortical thickness and white matter volume decrease with age, while diffusivity decreases and neurite orientation dispersion and densities increase with age.

BRAIN STRUCTURE & FUNCTION (2021)

Article Radiology, Nuclear Medicine & Medical Imaging

Deep Learning Enables Automatic Detection and Segmentation of Brain Metastases on Multisequence MRI

Endre Grovik et al.

JOURNAL OF MAGNETIC RESONANCE IMAGING (2020)

Review Radiology, Nuclear Medicine & Medical Imaging

Preparing Medical Imaging Data for Machine Learning

Martin J. Willemink et al.

RADIOLOGY (2020)

Article Oncology

Artificial intelligence in cancer imaging: Clinical challenges and applications

Wenya Linda Bi et al.

CA-A CANCER JOURNAL FOR CLINICIANS (2019)

Review Radiology, Nuclear Medicine & Medical Imaging

Convolutional Neural Networks for Radiologic Images: A Radiologist's Guide

Shelly Soffer et al.

RADIOLOGY (2019)

Article Radiology, Nuclear Medicine & Medical Imaging

Ethics of Artificial Intelligence in Radiology: Summary of the Joint European and North American Multisociety Statement

J. Raymond Geis et al.

RADIOLOGY (2019)

Article Radiology, Nuclear Medicine & Medical Imaging

To share or not to share? Expected pros and cons of data sharing in radiological research

Francesco Sardanelli et al.

EUROPEAN RADIOLOGY (2018)

Review Oncology

Artificial intelligence in radiology

Ahmed Hosny et al.

NATURE REVIEWS CANCER (2018)

Article Neurosciences

The Neuro Bureau ADHD-200 Preprocessed repository

Pierre Bellec et al.

NEUROIMAGE (2017)

Article Multidisciplinary Sciences

An open resource for transdiagnostic research in pediatric mental health and learning disorders

Lindsay M. Alexander et al.

SCIENTIFIC DATA (2017)

Article Radiology, Nuclear Medicine & Medical Imaging

Image Sharing in Radiology-A Primer

Arindam R. Chatterjee et al.

ACADEMIC RADIOLOGY (2017)

Article Multidisciplinary Sciences

A phenome-wide examination of neural and cognitive function

R. A. Poldrack et al.

SCIENTIFIC DATA (2016)

Article Computer Science, Interdisciplinary Applications

Multi-Modality Vertebra Recognition in Arbitrary Views Using 3D Deformable Hierarchical Model

Yunliang Cai et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2015)

Article Multidisciplinary Sciences

The pediatric template of brain perfusion

Brian B. Avants et al.

SCIENTIFIC DATA (2015)

Article Psychology, Developmental

Corpus Callosum Area and Brain Volume in Autism Spectrum Disorder: Quantitative Analysis of Structural MRI from the ABIDE Database

R. Kucharsky Hiess et al.

JOURNAL OF AUTISM AND DEVELOPMENTAL DISORDERS (2015)

Article Cardiac & Cardiovascular Systems

Quantification of LV function and mass by cardiovascular magnetic resonance: multi-center variability and consensus contours

Avan Suinesiaputra et al.

JOURNAL OF CARDIOVASCULAR MAGNETIC RESONANCE (2015)

Article Computer Science, Software Engineering

Robust Detection and Segmentation for Diagnosis of Vertebral Diseases Using Routine MR Images

Dzenan Zukic et al.

COMPUTER GRAPHICS FORUM (2014)

Article Neurosciences

Heritability of Working Memory Brain Activation

Gabriella A. M. Blokland et al.

JOURNAL OF NEUROSCIENCE (2011)

Article Neurosciences

Open Access Series of Imaging Studies: Longitudinal MRI Data in Nondemented and Demented Older Adults

Daniel S. Marcus et al.

JOURNAL OF COGNITIVE NEUROSCIENCE (2010)