Dataset Information

Accelerating High b-Value Diffusion-Weighted MRI Using a Convolutional Recurrent Neural Network (CRNN-DWI).

ABSTRACT:

Purpose

To develop a novel convolutional recurrent neural network (CRNN-DWI) and apply it to reconstruct a highly undersampled (up to six-fold) multi-b-value, multi-direction diffusion-weighted imaging (DWI) dataset.

Methods

A deep neural network that combines a convolutional neural network (CNN) and recurrent neural network (RNN) was first developed by using a set of diffusion images as input. The network was then used to reconstruct a DWI dataset consisting of 14 b-values, each with three diffusion directions. For comparison, the dataset was also reconstructed with zero-padding and 3D-CNN. The experiments were performed with undersampling rates (R) of 4 and 6. Standard image quality metrics (SSIM and PSNR) were employed to provide quantitative assessments of the reconstructed image quality. Additionally, an advanced non-Gaussian diffusion model was employed to fit the reconstructed images from the different approaches, thereby generating a set of diffusion parameter maps. These diffusion parameter maps from the different approaches were then compared using SSIM as a metric.

Results

Both the reconstructed diffusion images and diffusion parameter maps from CRNN-DWI were better than those from zero-padding or 3D-CNN. Specifically, the average SSIM and PSNR of CRNN-DWI were 0.750 ± 0.016 and 28.32 ± 0.69 (R = 4), and 0.675 ± 0.023 and 24.16 ± 0.77 (R = 6), respectively, both of which were substantially higher than those of zero-padding or 3D-CNN reconstructions. The diffusion parameter maps from CRNN-DWI also yielded higher SSIM values for R = 4 (>0.8) and for R = 6 (>0.7) than the other two approaches (for R = 4, <0.7, and for R = 6, <0.65).

Conclusions

CRNN-DWI is a viable approach for reconstructing highly undersampled DWI data, providing opportunities to reduce the data acquisition burden.

SUBMITTER: Zhong Z

PROVIDER: S-EPMC10376839 | biostudies-literature | 2023 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Accelerating High b-Value Diffusion-Weighted MRI Using a Convolutional Recurrent Neural Network (CRNN-DWI).

Zhong Zheng Z Ryu Kanghyun K Mao Jonathan J Sun Kaibao K Dan Guangyu G Vasanawala Shreyas S SS Zhou Xiaohong Joe XJ

Bioengineering (Basel, Switzerland) 20230721 7

<h4>Purpose</h4>To develop a novel convolutional recurrent neural network (CRNN-DWI) and apply it to reconstruct a highly undersampled (up to six-fold) multi-b-value, multi-direction diffusion-weighted imaging (DWI) dataset.<h4>Methods</h4>A deep neural network that combines a convolutional neural network (CNN) and recurrent neural network (RNN) was first developed by using a set of diffusion images as input. The network was then used to reconstruct a DWI dataset consisting of 14 b-values, each ...[more]

PMID: 37508891

Similar Datasets

Project description:PurposeTo investigate the feasibility of accelerating prostate diffusion-weighted imaging (DWI) by reducing the number of acquired averages and denoising the resulting image using a proposed guided denoising convolutional neural network (DnCNN).Materials and methodsRaw data from the prostate DWI scans were retrospectively gathered between July 2018 and July 2019 from six single-vendor MRI scanners. There were 103 datasets used for training (median age, 64 years; interquartile range [IQR], 11), 15 for validation (median age, 68 years; IQR, 12), and 37 for testing (median age, 64 years; IQR, 12). High b-value diffusion-weighted (hb DW) data were reconstructed into noisy images using two averages and reference images using all 16 averages. A conventional DnCNN was modified into a guided DnCNN, which uses the low b-value DW image as a guidance input. Quantitative and qualitative reader evaluations were performed on the denoised hb DW images. A cumulative link mixed regression model was used to compare the readers' scores. The agreement between the apparent diffusion coefficient (ADC) maps (denoised vs reference) was analyzed using Bland-Altman analysis.ResultsCompared with the original DnCNN, the guided DnCNN produced denoised hb DW images with higher peak signal-to-noise ratio (32.79 ± 3.64 [standard deviation] vs 33.74 ± 3.64), higher structural similarity index (0.92 ± 0.05 vs 0.93 ± 0.04), and lower normalized mean square error (3.9% ± 10 vs 1.6% ± 1.5) (P < .001 for all). Compared with the reference images, the denoised images received higher image quality scores from the readers (P < .0001). The ADC values based on the denoised hb DW images were in good agreement with the reference ADC values (mean ADC difference ranged from -0.04 to 0.02 × 10-3 mm2/sec).ConclusionAccelerating prostate DWI by reducing the number of acquired averages and denoising the resulting image using the proposed guided DnCNN is technically feasible. Supplemental material is available for this article. © RSNA, 2020.

Project description:BackgroundThe change in apparent diffusion coefficient (ADC) measured from diffusion-weighted imaging (DWI) has been shown to be predictive of pathologic complete response (pCR) for patients with locally invasive breast cancer undergoing neoadjuvant chemotherapy.PurposeTo investigate the additive value of tumor ADC in a multicenter clinical trial setting.Study typeRetrospective analysis of multicenter prospective data.PopulationIn all, 415 patients who enrolled in the I-SPY 2 TRIAL from 2010 to 2014 were included.Field strength/sequence1.5T or 3T MRI system using a fat-suppressed single-shot echo planar imaging sequence with b-values of 0 and 800 s/mm2 for DWI, followed by a T1-weighted sequence for dynamic contrast-enhanced MRI (DCE-MRI) performed at pre-NAC (T0), after 3 weeks of NAC (T1), mid-NAC (T2), and post-NAC (T3).AssessmentFunctional tumor volume and tumor ADC were measured at each MRI exam; pCR measured at surgery was assessed as the binary outcome. Breast cancer subtype was defined by hormone receptor (HR) and human epidermal growth factor receptor 2 (HER2) status.Statistical testsA logistic regression model was used to evaluate associations between MRI predictors with pCR. The cross-validated area under the curve (AUC) was calculated to assess the predictive performance of the model with and without ADC.ResultsIn all, 354 patients (128 HR+/HER2-, 60 HR+/HER2+, 34 HR-/HER2+, 132 HR-/HER2-) were included in the analysis. In the full cohort, adding ADC predictors increased the AUC from 0.76 to 0.78 at mid-NAC and from 0.76 to 0.81 at post-NAC. In HR/HER2 subtypes, the AUC increased from 0.52 to 0.65 at pre-NAC for HR+/HER2-, from 0.67 to 0.73 at mid-NAC and from 0.72 to 0.76 at post-NAC for HR+/HER2+, from 0.71 to 0.81 at post-NAC for triple negatives.Data conclusionThe addition of ADC to standard functional tumor volume MRI showed improvement in the prediction of treatment response in HR+ and triple-negative breast cancer.Level of evidence2 Technical Efficacy Stage: 4 J. Magn. Reson. Imaging 2019;50:1742-1753.

Project description:BackgroundIt is of clinical importance to assess the histopathological features of rectal cancer. The adipose tissue microenvironment is closely associated with tumor formation and progression. The chemical shift-encoded magnetic resonance imaging (CSE-MRI) sequence can noninvasively quantify adipose tissue. In this study, we aimed to investigate the feasibility of using CSE-MRI and diffusion-weighted imaging (DWI) to predict the histopathological features of rectal adenocarcinoma.MethodsIn this retrospective study, 84 patients with rectal adenocarcinoma and 30 healthy controls were consecutively enrolled at the Tongji Hospital of Tongji Medical College of Huazhong University of Science and Technology. CSE-MRI and DWI sequences were performed. The intratumoral proton density fat fraction (PDFF) and R2* of rectal tumors and normal rectal walls were measured. The histopathological features, including pathological T/N stage, tumor grade, mesorectum fascia (MRF) involvement, and extramural venous invasion (EMVI) status were analyzed. The Mann-Whitney test, Spearman correlation, and receiver operating characteristic (ROC) curves were used for statistical analyses.ResultsPatients with rectal adenocarcinoma demonstrated significantly lower PDFF and R2* values than did the control participants (5.35%±1.70% vs. 11.55%±3.41%, P<0.001; 35.60 s-1±7.30 s-1 vs. 40.15 s-1±5.72 s-1, P=0.003). PDFF and R2* were significantly different in the discrimination of T/N stage, tumor grade, and MRF/EMVI status (P=0.000-0.005). A significant difference was only noted in the differentiation of the T stage for the apparent diffusion coefficient (ADC) (1.09±0.26×10-3 mm2/s vs. 1.00±0.11×10-3 mm2/s; P=0.001). PDFF and R2* exhibited positive correlations with all the histopathological features (r=0.306-0.734; P=0.000-0.005), while ADC was negatively correlated with the T stage (r=-0.380; P<0.001). PDFF demonstrated diagnostic ability, with a sensitivity of 95.00% and a specificity of 87.50%, while R2* had a sensitivity of 95.00% and a specificity of 79.20% in differentiating T stage; both demonstrated a better diagnostic performance than did ADC.ConclusionsQuantitative CSE-MRI imaging might serve as a noninvasive biomarker for assessing the histopathological features of rectal adenocarcinoma.

Dataset Information

Accelerating High b-Value Diffusion-Weighted MRI Using a Convolutional Recurrent Neural Network (CRNN-DWI).

Purpose

Methods

Results

Conclusions

Publications

Accelerating High b-Value Diffusion-Weighted MRI Using a Convolutional Recurrent Neural Network (CRNN-DWI).

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets