Muti-shell Diffusion MRI Harmonisation and Enhancement Challenge (MUSHAC): Progress and Results

Ning, Lipeng; Bonet‐Carne, Elisenda; Grussu, Francesco; Sepehrband, Farshid; Kaden, Enrico; Veraart, Jelle; Blumberg, Stefano B.; Khoo, Can Son; Palombo, Marco; Coll‐Font, Jaume; Scherrer, Benoît; Warfield, Simon K.; Karayumak, Süheyla Çetin; Rathi, Yogesh; Koppers, Simon; Weninger, Leon; Ebert, Julia; Merhof, Dorit; Moyer, Daniel; Pietsch, Maximilian; Christiaens, Daan; Teixeira, Rui Pedro A. G.; Tournier, Jacques‐Donald; Zhylka, Andrey; Pluim, Josien P. W.; Parker, Greg D.; Rudrapatna, Umesh; Evans, John; Charron, Cyril; Jones, Derek K.; Tax, Chantal

doi:10.1007/978-3-030-05831-9_18

Cited by 15 publications

(15 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We demonstrate our proposed method on the MICCAI Computational Diffusion MRI challenge dataset [41,51,59], showing substantial improvement compared to a recently published baseline method. We also introduce technical improvements to the training of neural architectures on diffusion-weighted data, and discuss the limitations and error modes of our proposed method.…”

Section: Introductionmentioning

confidence: 87%

“…In a supervised (paired) task, direct image-to-image transfer has been explored both in the harmonization context [29,34,41] as well as the similar super-resolution context [9,49]. This family of methods generally relies on high expressive-capacity function fitting (e.g., neural networks) to map directly between patches of pairs of images.…”

Section: Relevant Prior Workmentioning

confidence: 99%

See 1 more Smart Citation

Scanner invariant representations for diffusion MRI harmonization

Moyer

Steeg

Tax

et al. 2020

Magnetic Resonance in Med

Self Cite

101

106

View full text Add to dashboard Cite

Purpose: In the present work we describe the correction of diffusion-weighted MRI for site and scanner biases using a novel method based on invariant representation.Theory and Methods: Pooled imaging data from multiple sources are subject to variation between the sources. Correcting for these biases has become very important as imaging studies increase in size and multi-site cases become more common. We propose learning an intermediate representation invariant to site/protocol variables, a technique adapted from information theory-based algorithmic fairness; by leveraging the data processing inequality, such a representation can then be used to create an image reconstruction that is uninformative of its original source, yet still faithful to underlying structures. To implement this, we use a deep learning method based on variational auto-encoders (VAE) to construct scanner invariant encodings of the imaging data.Results: To evaluate our method, we use training data from the 2018 MICCAI Computational Diffusion MRI (CDMRI) Challenge Harmonization dataset. Our proposed method shows improvements on independent test data relative to a recently published baseline method on each subtask, mapping data from three different scanning contexts to and from one separate target scanning context. Conclusion:As imaging studies continue to grow, the use of pooled multi-site imaging will similarly increase. Invariant representation presents a strong candidate for the harmonization of these data.

show abstract

Section: Introductionmentioning

confidence: 87%

Section: Relevant Prior Workmentioning

confidence: 99%

Scanner invariant representations for diffusion MRI harmonization

Moyer

Steeg

Tax

et al. 2020

Magnetic Resonance in Med

Self Cite

101

106

View full text Add to dashboard Cite

show abstract

“…It is not necessarily true that this property would also be valid for other neurological disorders such as tumors, especially if their features are not well represented in the training data as we have mentioned previously in Section 5.3. Another aspect that we did not explicitly cover is multishell data, that is, data sets acquired with multiple b-values, which was in fact part of the following CDMRI challenge (Ning et al, 2019). Nevertheless, our method can still be used on such data sets, but would not be aware of the relationship between DWIs beyond the angular domain.…”

Section: Limitations Of Our Algorithm and Possible Improvementsmentioning

confidence: 99%

Harmonization of diffusionMRIdata sets with adaptive dictionary learning

St-Jean

Viergever

Leemans

2020

Human Brain Mapping

View full text Add to dashboard Cite

Diffusion magnetic resonance imaging can indirectly infer the microstructure of tissues and provide metrics subject to normal variability in a population. Potentially abnormal values may yield essential information to support analysis of controls and patients cohorts, but subtle confounds could be mistaken for purely biologically driven variations amongst subjects. In this work, we propose a new harmonization algorithm based on adaptive dictionary learning to mitigate the unwanted variability caused by different scanner hardware while preserving the natural biological variability of the data. Our harmonization algorithm does not require paired training data sets, nor spatial registration or matching spatial resolution. Overcomplete dictionaries are learned iteratively from all data sets at the same time with an adaptive regularization criterion, removing variability attributable to the scanners in the process. The obtained mapping is applied directly in the native space of each subject toward a scanner-space. The method is evaluated with a public database which consists of two different protocols acquired on three different scanners. Results show that the effect size of the four studied diffusion metrics is preserved while removing variability attributable to the scanner. Experiments with alterations using a free water compartment, which is not simulated in the training data, shows that the modifications applied to the diffusion weighted images are preserved in the diffusion metrics after harmonization, while still reducing global variability at the same time. The algorithm could help multicenter studies pooling their data by removing scanner specific confounds, and increase statistical power in the process.

show abstract

“…The Diffusion MRI Data Harmonization 5 2017 and the Multishell Diffusion MRI Harmonization Challenge 2018 (MUSHAC 6 ) were proposed with the aim to evaluate the performance of algorithms that enable the harmonization of DWI data. From the last challenge, Ning et al (2019) presented a summary of results comparing the effects of DWIH methods on diffusion parametric maps. Different DWIH methods were used to harmonize the multi-shell DWI data.…”

Section: Discussionmentioning

confidence: 99%

Harmonization of Brain Diffusion MRI: Concepts and Methods

et al. 2020

View full text Add to dashboard Cite

MRI diffusion data suffers from significant inter-and intra-site variability, which hinders multi-site and/or longitudinal diffusion studies. This variability may arise from a range of factors, such as hardware, reconstruction algorithms and acquisition settings. To allow a reliable comparison and joint analysis of diffusion data across sites and over time, there is a clear need for robust data harmonization methods. This review article provides a comprehensive overview of diffusion data harmonization concepts and methods, and their limitations. Overall, the methods for the harmonization of multi-site diffusion images can be categorized in two main groups: diffusion parametric map harmonization (DPMH) and diffusion weighted image harmonization (DWIH). Whereas DPMH harmonizes the diffusion parametric maps (e.g., FA, MD, and MK), DWIH harmonizes the diffusionweighted images. Defining a gold standard harmonization technique for dMRI data is still an ongoing challenge. Nevertheless, in this paper we provide two classification tools, namely a feature table and a flowchart, which aim to guide the readers in selecting an appropriate harmonization method for their study.

show abstract

Muti-shell Diffusion MRI Harmonisation and Enhancement Challenge (MUSHAC): Progress and Results

Cited by 15 publications

References 23 publications

Scanner invariant representations for diffusion MRI harmonization

Scanner invariant representations for diffusion MRI harmonization

Harmonization of diffusionMRIdata sets with adaptive dictionary learning

Harmonization of Brain Diffusion MRI: Concepts and Methods

Contact Info

Product

Resources

About