Fast and Robust Diffusion Kurtosis Parametric Mapping Using a Three-Dimensional Convolutional Neural Network

Li, Zhiwei; Gong, Ting; Lin, Zhichao; He, Hongjian; Tong, Qiqi; Li, Chen; Sun, Yi; Feng, Yilin; Zhong, Jianhui

doi:10.1109/access.2019.2919241

Cited by 21 publications

(32 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, we used a deep learning‐ (DL‐) based parameter estimation method to address residual motion effects. This was motivated by the fact that DL‐based methods have recently been shown to have excellent results in estimating diffusion‐derived measures from highly undersampled data 27‐31 . Here, we demonstrate this new approach by combining a DL‐based method using a hierarchical convolutional neural network (H‐CNN) 29 with a motion assessment and data rejection procedure (Figure 1C).…”

Section: Introductionmentioning

confidence: 75%

“…Unlike conventional techniques, the proposed method requires an additional input—a few training subjects. This is because at the heart of the technique is a patch‐based H‐CNN model, 29 trained with supervised learning, to map any given subset of the full data to the metrics derived from the full data. To train the model, the technique requires minimally motion‐contaminated data from one to two subjects who are able to lie still over the entire diffusion acquisition; these subjects are referred to as the training subjects henceforth.…”

Section: Methodsmentioning

confidence: 99%

“…This was motivated by the fact that DL-based methods have recently been shown to have excellent results in estimating diffusion-derived measures from highly undersampled data. [27][28][29][30][31] Here, we demonstrate this new approach by combining a DL-based method using a hierarchical convolutional neural network (H-CNN) 29 with a motion assessment and data rejection procedure ( Figure 1C). The proposed technique is evaluated for recovering DKI-and DTI-derived measures from motion-contaminated data.…”

Section: Introductionmentioning

confidence: 94%

“…A subject-specific H-CNN model is trained with a separate set of training subjects. The network architecture of H-CNN is fully described in Li et al, 29 but for completeness it is included here as Supporting Information Figure S1. Two aspects of the model are relevant here.…”

Section: H-cnn Model and Trainingmentioning

confidence: 99%

See 3 more Smart Citations

Deep learning‐based method for reducing residual motion effects in diffusion parameter estimation

Gong

Tong

et al. 2020

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

Conventional motion-correction techniques for diffusion MRI can introduce motion-level-dependent bias in derived metrics. To address this challenge, a deep learning-based technique was developed to minimize such residual motion effects. Methods: The data-rejection approach was adopted in which motion-corrupted data are discarded before model-fitting. A deep learning-based parameter estimation algorithm, using a hierarchical convolutional neural network (H-CNN), was combined with motion assessment and corrupted volume rejection. The method was designed to overcome the limitations of existing methods of this kind that produce parameter estimations whose quality depends strongly on a proportion of the data discarded. Evaluation experiments were conducted for the estimation of diffusion kurtosis and diffusion-tensor-derived measures at both the individual and group levels. The performance was compared with the robust approach of iteratively reweighted linear least squares (IRLLS) after motion correction with and without outlier replacement. Results: Compared with IRLLS, the H-CNN-based technique is minimally sensitive to motion effects. It was tested at severe motion levels when 70% to 90% of the data are rejected and when random motion is present. The technique had a stable performance independent of the numbers and schemes of data rejection. A further test on a data set from children with attention-deficit hyperactivity disorder shows the technique can potentially ameliorate spurious group-level difference caused by head motion. Conclusion: This method shows great potential for reducing residual motion effects in motion-corrupted diffusion-weighted-imaging data, bringing benefits that include reduced bias in derived metrics in individual scans and reduced motion-leveldependent bias in population studies employing diffusion MRI.

show abstract

Section: Introductionmentioning

confidence: 75%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 94%

Section: H-cnn Model and Trainingmentioning

confidence: 99%

See 2 more Smart Citations

Deep learning‐based method for reducing residual motion effects in diffusion parameter estimation

Gong

Tong

et al. 2020

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

show abstract

“…Similarly, Li et al proposed a convolutional neural network to reconstruct scalar diffusion kurtosis imaging parameters from scans as short as 1-minute long. 17 In contrast to the proposed U-Net, this approach operated on…”

mentioning

confidence: 99%

Extracting diffusion tensor fractional anisotropy and mean diffusivity from 3‐direction DWI scans using deep learning

Aliotta

Nourzadeh

Patel

2020

Magnetic Resonance in Med

View full text Add to dashboard Cite

Purpose To develop and evaluate machine‐learning methods that reconstruct fractional anisotropy (FA) values and mean diffusivities (MD) from 3‐direction diffusion MRI (dMRI) acquisitions. Methods Two machine‐learning models were implemented to map undersampled dMRI signals with high‐quality FA and MD maps that were reconstructed from fully sampled DTI scans. The first model was a previously described multilayer perceptron (MLP), which maps signals and FA/MD values from a single voxel. The second was a convolutional neural network U‐Net model, which maps dMRI slices to full FA/MD maps. Each method was trained on dMRI brain scans (N = 46), and reconstruction accuracies were compared with conventional linear‐least‐squares (LLS) reconstructions. Results In an independent testing cohort (N = 20), 3‐direction U‐Net reconstructions had significantly lower absolute FA error than both 3‐direction MLP (U‐Net3‐dir: 0.06 ± 0.01 vs. MLP3‐dir: 0.08 ± 0.01, P < 1 × 10−5) and 6‐direction LLS (LLS6‐dir: 0.09 ± 0.03, P = 1 × 10−5). The MD errors were not significantly different among 3‐direction MLP (0.06 ± 0.01 × 10−3 mm2/s), 3‐direction U‐Net (0.06 ± 0.01 × 10−3 mm2/s), and 6‐direction LLS (0.07 ± 0.02 × 10−3 mm2/s, P > .1). Conclusion The proposed U‐Net model reconstructed FA from 3‐direction dMRI scans with improved accuracy compared with both a previously described MLP approach and LLS fitting from 6‐direction scans. The MD reconstruction accuracies did not differ significantly between reconstructions.

show abstract

DIMOND: DIffusion Model OptimizatioN with Deep Learning

Li,

Bilgic

et al. 2024

Advanced Science

View full text Add to dashboard Cite

Diffusion magnetic resonance imaging is an important tool for mapping tissue microstructure and structural connectivity non‐invasively in the in vivo human brain. Numerous diffusion signal models are proposed to quantify microstructural properties. Nonetheless, accurate estimation of model parameters is computationally expensive and impeded by image noise. Supervised deep learning‐based estimation approaches exhibit efficiency and superior performance but require additional training data and may be not generalizable. A new DIffusion Model OptimizatioN framework using physics‐informed and self‐supervised Deep learning entitled “DIMOND” is proposed to address this problem. DIMOND employs a neural network to map input image data to model parameters and optimizes the network by minimizing the difference between the input acquired data and synthetic data generated via the diffusion model parametrized by network outputs. DIMOND produces accurate diffusion tensor imaging results and is generalizable across subjects and datasets. Moreover, DIMOND outperforms conventional methods for fitting sophisticated microstructural models including the kurtosis and NODDI model. Importantly, DIMOND reduces NODDI model fitting time from hours to minutes, or seconds by leveraging transfer learning. In summary, the self‐supervised manner, high efficacy, and efficiency of DIMOND increase the practical feasibility and adoption of microstructure and connectivity mapping in clinical and neuroscientific applications.

show abstract

Fast and Robust Diffusion Kurtosis Parametric Mapping Using a Three-Dimensional Convolutional Neural Network

Cited by 21 publications

References 65 publications

Deep learning‐based method for reducing residual motion effects in diffusion parameter estimation

Deep learning‐based method for reducing residual motion effects in diffusion parameter estimation

Extracting diffusion tensor fractional anisotropy and mean diffusivity from 3‐direction DWI scans using deep learning

DIMOND: DIffusion Model OptimizatioN with Deep Learning

Contact Info

Product

Resources

About