A Multi-view Open-access Dataset of Paired Knee MRI for Motion Artifact Removal
Abstract
Magnetic resonance imaging (MRI) has become a standard examination method for the knee, facilitating the identification of a range of knee-related issues, including injuries, arthritis, and other conditions. The lengthy image acquisition time inherent to MRI results in the generation of motion artifacts, which in turn impairs the efficiency of MRI applications. To address this challenge, we present a multi-view, multi-sequence knee joint paired MRI dataset (image with motion artifact vs. Ground Truth obtained after rescanning), named Knee MRI for Artifact Removal (KMAR)-50K, which includes 1,190 patients, 1,444 pairs of MRI sequences, and 62,506 scan images. The dataset comprises images of anonymous paired NIfTI files that have undergone bias field correction, maximum minimum normalization, and paired image spatial registration in sequence. The objective of our data-sharing program is to facilitate the benchmark testing of methods of knee MRI motion artifact removal. Benchmarking three models revealed U-Net’s superior transverse plane performance (PSNR = 28.468, SSIM = 0.927) with fastest inference (0.5 s/volume), highlighting its clinical value in accuracy-efficiency balance.
Read the paper
Related studies
- Learning from First-Generation Qualitative Approaches in the IS Discipline: An Evolutionary View and Some Implications for Authors and Evaluators (PART 1/2)
- Commentary on the clinical and preclinical dosage limits of interstitially administered magnetic fluids for therapeutic hyperthermia based on current practice and efficacy models
- Prosthesis: New Technological Opportunities and Innovative Biomedical Devices
- The history and future of neural modeling for cochlear implants
- Ryanodine receptors: waking up from refractoriness
- Novel Transgenic Rabbit Model Sheds Light on the Puzzling Role of Matrix Metalloproteinase-12 in Atherosclerosis
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.