{"url":"/task/mri-reconstruction","name":"MRI Reconstruction","slug":"mri-reconstruction","description_markdown":"In its most basic form, MRI reconstruction consists in retrieving a complex-valued image from its under-sampled Fourier coefficients. \r\nBesides, it can be addressed as a encoder-decoder task, in which the normative model in the latent space will only capture the relevant information without noise or corruptions. Then, we decode the latent space in order to have a reconstructed MRI.","categories":[{"name":"Medical","url":"/area/medical"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":441,"papers_with_code":198,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":2,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/mri-reconstruction-on-fastmri-knee-8x","slug":"mri-reconstruction-on-fastmri-knee-8x","dataset":"fastMRI Knee 8x","dataset_url":"/dataset/fastmri","rows_in_archive":4,"metrics":["SSIM","PSNR"],"first_row_in_archive_order":{"model":"HUMUS-Net (train+val data)","paper_title":"HUMUS-Net: Hybrid unrolled multi-scale network architecture for accelerated MRI reconstruction","paper_url":"/paper/humus-net-hybrid-unrolled-multi-scale-network","paper_date":"2022-03-15","arxiv_id":"2203.08213","code_links":[{"title":"z-fabian/HUMUS-Net","url":"https://github.com/z-fabian/HUMUS-Net"},{"title":"MathFLDS/HUMUS-Net","url":"https://github.com/MathFLDS/HUMUS-Net"}],"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/mri-reconstruction-on-fastmri-knee-val-8x","slug":"mri-reconstruction-on-fastmri-knee-val-8x","dataset":"fastMRI Knee Val 8x","dataset_url":"/dataset/fastmri","rows_in_archive":4,"metrics":["SSIM","PSNR","NMSE","Params (M)"],"first_row_in_archive_order":{"model":"PromptMR","paper_title":"Fill the K-Space and Refine the Image: Prompting for Dynamic and Multi-Contrast MRI Reconstruction","paper_url":"/paper/fill-the-k-space-and-refine-the-image","paper_date":"2023-09-25","arxiv_id":"2309.13839","code_links":[{"title":"hellopipu/promptmr","url":"https://github.com/hellopipu/promptmr"}],"syntology":null}},{"leaderboard":"/sota/mri-reconstruction-on-fastmri-brain-4x","slug":"mri-reconstruction-on-fastmri-brain-4x","dataset":"fastMRI Brain 4x","dataset_url":"/dataset/fastmri","rows_in_archive":2,"metrics":["SSIM","PSNR"],"first_row_in_archive_order":{"model":"End-to-end variational network","paper_title":"End-to-End Variational Networks for Accelerated MRI Reconstruction","paper_url":"/paper/end-to-end-variational-networks-for","paper_date":"2020-04-14","arxiv_id":"2004.06688","code_links":[{"title":"facebookresearch/fastMRI","url":"https://github.com/facebookresearch/fastMRI"},{"title":"z-fabian/MRAugment","url":"https://github.com/z-fabian/MRAugment"},{"title":"MathFLDS/MRAugment","url":"https://github.com/MathFLDS/MRAugment"}],"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/mri-reconstruction-on-fastmri-brain-8x","slug":"mri-reconstruction-on-fastmri-brain-8x","dataset":"fastMRI Brain 8x","dataset_url":"/dataset/fastmri","rows_in_archive":2,"metrics":["SSIM","PSNR"],"first_row_in_archive_order":{"model":"End-to-end variational network","paper_title":"End-to-End Variational Networks for Accelerated MRI Reconstruction","paper_url":"/paper/end-to-end-variational-networks-for","paper_date":"2020-04-14","arxiv_id":"2004.06688","code_links":[{"title":"facebookresearch/fastMRI","url":"https://github.com/facebookresearch/fastMRI"},{"title":"z-fabian/MRAugment","url":"https://github.com/z-fabian/MRAugment"},{"title":"MathFLDS/MRAugment","url":"https://github.com/MathFLDS/MRAugment"}],"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/mri-reconstruction-on-fastmri-knee-4x","slug":"mri-reconstruction-on-fastmri-knee-4x","dataset":"fastMRI Knee 4x","dataset_url":"/dataset/fastmri","rows_in_archive":2,"metrics":["SSIM","PSNR"],"first_row_in_archive_order":{"model":"End-to-end variational network","paper_title":"End-to-End Variational Networks for Accelerated MRI Reconstruction","paper_url":"/paper/end-to-end-variational-networks-for","paper_date":"2020-04-14","arxiv_id":"2004.06688","code_links":[{"title":"facebookresearch/fastMRI","url":"https://github.com/facebookresearch/fastMRI"},{"title":"z-fabian/MRAugment","url":"https://github.com/z-fabian/MRAugment"},{"title":"MathFLDS/MRAugment","url":"https://github.com/MathFLDS/MRAugment"}],"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/mri-reconstruction-on-ixi-dataset","slug":"mri-reconstruction-on-ixi-dataset","dataset":"IXI","dataset_url":"/dataset/ixi-dataset","rows_in_archive":1,"metrics":["DSSIM","MSE"],"first_row_in_archive_order":{"model":"Residual U-NET","paper_title":"Deep Convolutional Autoencoders for reconstructing magnetic resonance images of the healthy brain","paper_url":"/paper/deep-convolutional-autoencoders-for","paper_date":"2021-01-19","arxiv_id":null,"code_links":[{"title":"AdrianArnaiz/Brain-MRI-Autoencoder","url":"https://github.com/AdrianArnaiz/Brain-MRI-Autoencoder"}],"syntology":null}}],"datasets":[{"url":"/dataset/fastmri","name":"fastMRI","full_name":"","num_papers_in_archive":332},{"url":"/dataset/ixi-dataset","name":"IXI","full_name":"IXI Brain Development Dataset","num_papers_in_archive":23},{"url":"/dataset/skm-tea","name":"SKM-TEA","full_name":"Stanford Knee MRI with Multi-Task Evaluation","num_papers_in_archive":16},{"url":"/dataset/m4raw","name":"M4Raw","full_name":"A multi-contrast, multi-repetition, multi-channel MRI k-space dataset for low-field MRI research","num_papers_in_archive":11}],"subtasks":[{"url":"/task/magnetic-resonance-fingerprinting","name":"Magnetic Resonance Fingerprinting"},{"url":"/task/quantitative-mri","name":"Quantitative MRI"}],"parent_tasks":[{"url":"/task/image-reconstruction","name":"Image Reconstruction"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":198,"tagged_in_all":441,"items":[{"url":"/paper/assessment-of-data-consistency-through","title":"Assessment of Data Consistency through Cascades of Independently Recurrent Inference Machines for fast and robust accelerated MRI reconstruction","date":"2021-11-30","arxiv_id":"2111.15498","repositories_listed":7,"syntology":null},{"url":"/paper/homotopic-gradients-of-generative-density","title":"Homotopic Gradients of Generative Density Priors for MR Image Reconstruction","date":"2020-08-14","arxiv_id":"2008.06284","repositories_listed":5,"syntology":null},{"url":"/paper/can-un-trained-neural-networks-compete-with","title":"Accelerated MRI with Un-trained Neural Networks","date":"2020-07-06","arxiv_id":"2007.02471","repositories_listed":4,"syntology":null},{"url":"/paper/dp-mdm-detail-preserving-mr-reconstruction","title":"DP-MDM: Detail-Preserving MR Reconstruction via Multiple Diffusion Models","date":"2024-05-09","arxiv_id":"2405.05763","repositories_listed":3,"syntology":null},{"url":"/paper/recurrent-variational-network-a-deep-learning","title":"Recurrent Variational Network: A Deep Learning Inverse Problem Solver applied to the task of Accelerated MRI Reconstruction","date":"2021-11-18","arxiv_id":"2111.09639","repositories_listed":3,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":2}},{"url":"/paper/state-of-the-art-machine-learning-mri","title":"Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction","date":"2020-12-09","arxiv_id":"2012.06318","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/xpdnet-for-mri-reconstruction-an-application","title":"XPDNet for MRI Reconstruction: an application to the 2020 fastMRI challenge","date":"2020-10-15","arxiv_id":"2010.07290","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/end-to-end-variational-networks-for","title":"End-to-End Variational Networks for Accelerated MRI Reconstruction","date":"2020-04-14","arxiv_id":"2004.06688","repositories_listed":3,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/dm-mamba-dual-domain-multi-scale-mamba-for","title":"DH-Mamba: Exploring Dual-domain Hierarchical State Space Models for MRI Reconstruction","date":"2025-01-14","arxiv_id":"2501.08163","repositories_listed":2,"syntology":null},{"url":"/paper/smrd-sure-based-robust-mri-reconstruction","title":"SMRD: SURE-based Robust MRI Reconstruction with Diffusion Models","date":"2023-10-03","arxiv_id":"2310.01799","repositories_listed":2,"syntology":null},{"url":"/paper/learning-weakly-convex-regularizers-for","title":"Learning Weakly Convex Regularizers for Convergent Image-Reconstruction Algorithms","date":"2023-08-21","arxiv_id":"2308.10542","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_unverified":2,"n_pointer_only":11}},{"url":"/paper/generative-image-priors-for-mri","title":"Generative Priors for MRI Reconstruction Trained from Magnitude-Only Images Using Phase Augmentation","date":"2023-08-04","arxiv_id":"2308.02340","repositories_listed":2,"syntology":null},{"url":"/paper/generative-ai-for-medical-imaging-extending","title":"Generative AI for Medical Imaging: extending the MONAI Framework","date":"2023-07-27","arxiv_id":"2307.15208","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/mri-recovery-with-self-calibrated-denoisers","title":"MRI Recovery with Self-Calibrated Denoisers without Fully-Sampled Data","date":"2023-04-25","arxiv_id":"2304.12890","repositories_listed":2,"syntology":null},{"url":"/paper/smug-towards-robust-mri-reconstruction-by","title":"SMUG: Towards robust MRI reconstruction by smoothed unrolling","date":"2023-03-14","arxiv_id":"2303.12735","repositories_listed":2,"syntology":null},{"url":"/paper/fast-diffusion-sampler-for-inverse-problems","title":"Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems","date":"2023-03-10","arxiv_id":"2303.05754","repositories_listed":2,"syntology":{"n":27,"n_ran":16,"n_unverified":11,"n_pointer_only":27}},{"url":"/paper/a-neural-network-based-convex-regularizer-for","title":"A Neural-Network-Based Convex Regularizer for Inverse Problems","date":"2022-11-22","arxiv_id":"2211.12461","repositories_listed":2,"syntology":null},{"url":"/paper/t-2-lr-net-an-unrolling-reconstruction","title":"T2LR-Net: An unrolling network learning transformed tensor low-rank prior for dynamic MR image reconstruction","date":"2022-09-08","arxiv_id":"2209.03832","repositories_listed":2,"syntology":null},{"url":"/paper/monarch-expressive-structured-matrices-for","title":"Monarch: Expressive Structured Matrices for Efficient and Accurate Training","date":"2022-04-01","arxiv_id":"2204.00595","repositories_listed":2,"syntology":{"n":15,"n_ran":2,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/humus-net-hybrid-unrolled-multi-scale-network","title":"HUMUS-Net: Hybrid unrolled multi-scale network architecture for accelerated MRI reconstruction","date":"2022-03-15","arxiv_id":"2203.08213","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/swin-transformer-for-fast-mri","title":"Swin Transformer for Fast MRI","date":"2022-01-10","arxiv_id":"2201.03230","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/subtle-inverse-crimes-naively-training","title":"Subtle Data Crimes: Naively training machine learning algorithms could lead to overly-optimistic results","date":"2021-09-16","arxiv_id":"2109.08237","repositories_listed":2,"syntology":null},{"url":"/paper/data-augmentation-for-deep-learning-based-2","title":"Data augmentation for deep learning based accelerated MRI reconstruction with limited data","date":"2021-06-28","arxiv_id":"2106.14947","repositories_listed":2,"syntology":null},{"url":"/paper/is-good-old-grappa-dead","title":"Is good old GRAPPA dead?","date":"2021-06-01","arxiv_id":"2106.00753","repositories_listed":2,"syntology":null},{"url":"/paper/regularization-agnostic-compressed-sensing","title":"Regularization-Agnostic Compressed Sensing MRI Reconstruction with Hypernetworks","date":"2021-01-06","arxiv_id":"2101.02194","repositories_listed":2,"syntology":null},{"url":"/paper/interpreting-u-nets-via-task-driven","title":"Learning Multiscale Convolutional Dictionaries for Image Reconstruction","date":"2020-11-25","arxiv_id":"2011.12815","repositories_listed":2,"syntology":null},{"url":"/paper/self-supervised-learning-of-physics-based","title":"Self-Supervised Learning of Physics-Guided Reconstruction Neural Networks without Fully-Sampled Reference Data","date":"2019-12-16","arxiv_id":"1912.07669","repositories_listed":2,"syntology":null},{"url":"/paper/deep-generative-adversarial-networks-for","title":"Deep Generative Adversarial Networks for Compressed Sensing Automates MRI","date":"2017-05-31","arxiv_id":"1706.00051","repositories_listed":2,"syntology":null},{"url":"/paper/mdpg-multi-domain-diffusion-prior-guidance","title":"MDPG: Multi-domain Diffusion Prior Guidance for MRI Reconstruction","date":"2025-06-30","arxiv_id":"2506.23701","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-feature-learning-for-cardiac","title":"Self-supervised feature learning for cardiac Cine MR image reconstruction","date":"2025-05-29","arxiv_id":"2505.23408","repositories_listed":1,"syntology":null}],"syntology_records":10,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}