Dataset Information

Improving high frequency image features of deep learning reconstructions via k-space refinement with null-space kernel.

ABSTRACT:

Purpose

Deep learning (DL) based reconstruction using unrolled neural networks has shown great potential in accelerating MRI. However, one of the major drawbacks is the loss of high-frequency details and textures in the output. The purpose of the study is to propose a novel refinement method that uses null-space kernel to refine k-space and improve blurred image details and textures.

Methods

The proposed method constrains the output of the DL to comply to the linear neighborhood relationship calibrated in the auto-calibration lines. To demonstrate efficacy, we tested our refinement method on the DL reconstruction under a variety of conditions (i.e., dataset, unrolled neural networks, and under-sampling scheme). Specifically, the method was tested on three large-scale public datasets (knee and brain) from fastMRI's multi-coil track.

Results

The proposed scheme visually reduces the structural error in the k-space domain, enhance the homogeneity of the k-space intensity. Consequently, reconstructed image shows sharper images with enhanced details and textures. The proposed method is also successful in improving high-frequency image details (SSIM, GMSD) without sacrificing overall image error (PSNR).

Conclusion

Our findings imply that refining DL output using the proposed method may generally improve DL reconstruction as tested with various large-scale dataset and networks.

SUBMITTER: Ryu K

PROVIDER: S-EPMC9246879 | biostudies-literature | 2022 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Improving high frequency image features of deep learning reconstructions via k-space refinement with null-space kernel.

Ryu Kanghyun K Alkan Cagan C Vasanawala Shreyas S SS

Magnetic resonance in medicine 20220415 3

<h4>Purpose</h4>Deep learning (DL) based reconstruction using unrolled neural networks has shown great potential in accelerating MRI. However, one of the major drawbacks is the loss of high-frequency details and textures in the output. The purpose of the study is to propose a novel refinement method that uses null-space kernel to refine k-space and improve blurred image details and textures.<h4>Methods</h4>The proposed method constrains the output of the DL to comply to the linear neighborhood r ...[more]

PMID: 35426470

Similar Datasets

Project description:BackgroundIn the medical imaging domain, deep learning-based methods have yet to see widespread clinical adoption, in part due to limited generalization performance across different imaging devices and acquisition protocols. The deviation between estimated brain age and biological age is an established biomarker of brain health and such models may benefit from increased cross-site generalizability.PurposeTo develop and evaluate a deep learning-based image harmonization method to improve cross-site generalizability of deep learning age prediction.Study typeRetrospective.PopulationEight thousand eight hundred and seventy-six subjects from six sites. Harmonization models were trained using all subjects. Age prediction models were trained using 2739 subjects from a single site and tested using the remaining 6137 subjects from various other sites.Field strength/sequenceBrain imaging with magnetization prepared rapid acquisition with gradient echo or spoiled gradient echo sequences at 1.5 T and 3 T.AssessmentStarGAN v2, was used to perform a canonical mapping from diverse datasets to a reference domain to reduce site-based variation while preserving semantic information. Generalization performance of deep learning age prediction was evaluated using harmonized, histogram matched, and unharmonized data.Statistical testsMean absolute error (MAE) and Pearson correlation between estimated age and biological age quantified the performance of the age prediction model.ResultsOur results indicated a substantial improvement in age prediction in out-of-sample data, with the overall MAE improving from 15.81 (±0.21) years to 11.86 (±0.11) with histogram matching to 7.21 (±0.22) years with generative adversarial network (GAN)-based harmonization. In the multisite case, across the 5 out-of-sample sites, MAE improved from 9.78 (±6.69) years to 7.74 (±3.03) years with histogram normalization to 5.32 (±4.07) years with GAN-based harmonization.Data conclusionWhile further research is needed, GAN-based medical image harmonization appears to be a promising tool for improving cross-site deep learning generalization.Level of evidence4 TECHNICAL EFFICACY: Stage 1.

Dataset Information

Improving high frequency image features of deep learning reconstructions via k-space refinement with null-space kernel.

Purpose

Methods

Results

Conclusion

Publications

Improving high frequency image features of deep learning reconstructions via k-space refinement with null-space kernel.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets