Benchmarking Deep Nets MRI Reconstruction Models on the FastMRI Publicly Available Dataset

Abstract : The MRI reconstruction field lacked a proper data set that allowed for reproducible results on real raw data (i.e. complex-valued), especially when it comes to deep learning (DL) methods as this kind of approaches require much more data than classical Compressed Sensing (CS) reconstruction. This lack is now filled by the fastMRI data set, and it is needed to evaluate recent DL models on this benchmark. Besides, these networks are written in different frameworks and repositories (if publicly available), it is therefore needed to have a common tool, publicly available, allowing a reproducible benchmark of the different methods and ease of building new models. We provide such a tool that allows the benchmark of different reconstruction deep learning models.
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download

https://hal.inria.fr/hal-02436223
Contributor : Zaccharie Ramzi <>
Submitted on : Sunday, January 12, 2020 - 6:58:22 PM
Last modification on : Wednesday, January 22, 2020 - 1:31:00 PM

File

benchmark_abstract (2).pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02436223, version 1

Citation

Zaccharie Ramzi, Philippe Ciuciu, Jean-Luc Starck. Benchmarking Deep Nets MRI Reconstruction Models on the FastMRI Publicly Available Dataset. ISBI 2020 - International Symposium on Biomedical Imaging, Apr 2020, Iowa City, United States. ⟨hal-02436223⟩

Share

Metrics

Record views

46

Files downloads

168