# Quantitative Susceptibility Mapping using Deep Neural Network: QSMnet

arXiv: https://arxiv.org/abs/1803.05627 · HTML: https://mlsanity.com/paper/1803.05627/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Mar 2018.

## Built on by (most cited first, 24 of 24)

- [Adaptive Diffusion Priors for Accelerated MRI Reconstruction](https://mlsanity.com/paper/2207.05876/) (2022)
- [Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformers](https://mlsanity.com/paper/2105.08059/) (2021)
- [Physics-Driven Deep Learning for Computational Magnetic Resonance Imaging](https://mlsanity.com/paper/2203.12215/) (2022)
- [Learning Fourier-Constrained Diffusion Bridges for MRI Reconstruction](https://mlsanity.com/paper/2308.01096/) (2023)
- [DIFFnet: Diffusion parameter mapping network generalized for input diffusion gradient schemes and bvalues](https://mlsanity.com/paper/2102.02463/) (2021)
- [MoDL-QSM: Model-based Deep Learning for Quantitative Susceptibility Mapping](https://mlsanity.com/paper/2101.08413/) (2021)
- [Choice of training label matters: how to best use deep learning for quantitative MRI parameter estimation](https://mlsanity.com/paper/2205.05587/) (2022)
- [SelfCoLearn: Self-supervised collaborative learning for accelerating dynamic MR imaging](https://mlsanity.com/paper/2208.03904/) (2022)
- [CoRRECT: A Deep Unfolding Framework for Motion-Corrected Quantitative R2* Mapping](https://mlsanity.com/paper/2210.06330/) (2022)
- [BlindHarmony: "Blind" Harmonization for MR Images via Flow model](https://mlsanity.com/paper/2305.10732/) (2023)
- [Quantitative Susceptibility Mapping through Model-based Deep Image Prior (MoDIP)](https://mlsanity.com/paper/2308.09467/) (2023)
- [MOST: MR reconstruction Optimization for multiple downStream Tasks via continual learning](https://mlsanity.com/paper/2409.10394/) (2024)
- [Improved Padding in CNNs for Quantitative Susceptibility Mapping](https://mlsanity.com/paper/2106.15331/) (2021)
- [Data and Physics Driven Learning Models for Fast MRI -- Fundamentals and Methodologies from CNN, GAN to Attention and Transformers](https://mlsanity.com/paper/2204.01706/) (2022)
- [Affine Transformation Edited and Refined Deep Neural Network for Quantitative Susceptibility Mapping](https://mlsanity.com/paper/2211.13942/) (2022)
- [DeepSTI: Towards Tensor Reconstruction using Fewer Orientations in Susceptibility Tensor Imaging](https://mlsanity.com/paper/2209.04504/) (2022)
- [Motion Artifact Reduction in Quantitative Susceptibility Mapping using Deep Neural Network](https://mlsanity.com/paper/2105.01746/) (2021)
- [NeXtQSM -- A complete deep learning pipeline for data-consistent quantitative susceptibility mapping trained with hybrid data](https://mlsanity.com/paper/2107.07752/) (2021)
- [Self-supervised training of deep denoisers in multi-coil MRI considering noise correlations](https://mlsanity.com/paper/2208.07552/) (2022)
- [Quantitative Susceptibility Mapping in Cognitive Decline: A Review of Technical Aspects and Applications](https://mlsanity.com/paper/2211.04764/) (2022)
- [High-pass filtered fidelity-imposed network edit (HP-FINE) for robust quantitative susceptibility mapping from high-pass filtered phase](https://mlsanity.com/paper/2305.03844/) (2023)
- [IR2QSM: Quantitative Susceptibility Mapping via Deep Neural Networks with Iterative Reverse Concatenations and Recurrent Modules](https://mlsanity.com/paper/2406.12300/) (2024)
- [Efficient and robust 3D blind harmonization for large domain gaps](https://mlsanity.com/paper/2505.00133/) (2025)
- [Predicting before Reconstruction: A generative prior framework for MRI acceleration](https://mlsanity.com/paper/2510.19472/) (2025)

## Abstract (arXiv)

Deep neural networks have demonstrated promising potential for the field of medical image reconstruction. In this work, an MRI reconstruction algorithm, which is referred to as quantitative susceptibility mapping (QSM), has been developed using a deep neural network in order to perform dipole deconvolution, which restores magnetic susceptibility source from an MRI field map. Previous approaches of QSM require multiple orientation data (e.g. Calculation of Susceptibility through Multiple Orientation Sampling or COSMOS) or regularization terms (e.g. Truncated K-space Division or TKD; Morphology Enabled Dipole Inversion or MEDI) to solve the ill-conditioned deconvolution problem. Unfortunately, they either require long multiple orientation scans or suffer from artifacts. To overcome these shortcomings, a deep neural network, QSMnet, is constructed to generate a high quality susceptibility map from single orientation data. The network has a modified U-net structure and is trained using gold-standard COSMOS QSM maps. 25 datasets from 5 subjects (5 orientation each) were applied for patch-wise training after doubling the data using augmentation. Two additional datasets of 5 orientation data were used for validation and test (one dataset each). The QSMnet maps of the test dataset were compared with those from TKD and MEDI for image quality and consistency in multiple head orientations. Quantitative and qualitative image quality comparisons demonstrate that the QSMnet results have superior image quality to those of TKD or MEDI and have comparable image quality to those of COSMOS. Additionally, QSMnet maps reveal substantially better consistency across the multiple orientations than those from TKD or MEDI. As a preliminary application, the network was tested for two patients. The QSMnet maps showed similar lesion contrasts with those from MEDI, demonstrating potential for future applications.