Synthesize High-Quality Multi-Contrast Magnetic Resonance Imaging From Multi-Echo Acquisition Using Multi-Task Deep Generative Model

Wang, Guanhua; Gong, Enhao; Banerjee, Suchandrima; Martin, Dann; Tong, Elizabeth; Choi, Jinsoo; Chen, Huijun; Wintermark, Max; Pauly, John M.; Zaharchuk, Greg

doi:10.1109/tmi.2020.2987026

Cited by 34 publications

(43 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, machine learning has shown great potential in multiple medical image processing tasks, such as registration, 19–21 segmentation, 22,23 super resolution, 24 and image synthesis 25 in inter‐ and intra‐modality image transformations. With machine learning methods, studies have demonstrated the feasibility of synthesizing high‐quality multi‐contrast MR images from multi‐echo acquisition, that is, predicting pre‐contrast T1 and fluid‐attenuated inversion recovery (FLAIR) images from postcontrast T1‐weighted images and T2‐weighted images, as well as contrast enhanced CT images from unenhanced CT images 26–29 …”

Section: Introductionmentioning

confidence: 99%

Magnetic resonance imaging contrast enhancement synthesis using cascade networks with local supervision

et al. 2022

View full text Add to dashboard Cite

Purpose: Gadolinium-based contrast agents (GBCAs) are widely administrated in MR imaging for diagnostic studies and treatment planning. Although GBCAs are generally thought to be safe, various health and environmental concerns have been raised recently about their use in MR imaging. The purpose of this work is to derive synthetic contrast enhance MR images from unenhanced counterpart images, thereby eliminating the need for GBCAs, using a cascade deep learning workflow that incorporates contour information into the network. Methods and materials: The proposed workflow consists of two sequential networks: (1) a retina U-Net, which is first trained to derive semantic features from the non-contrast MR images in representing the tumor regions; and (2) a synthesis module, which is trained after the retina U-Net to take the concatenation of the semantic feature maps and non-contrast MR image as input and to generate the synthetic contrast enhanced MR images. After network training, only the non-contrast enhanced MR images are required for the input in the proposed workflow. The MR images of 369 patients from the multimodal brain tumor segmentation challenge 2020 (BraTS2020) dataset were used in this study to evaluate the proposed workflow for synthesizing contrast enhanced MR images (200 patients for five-fold cross-validation and 169 patients for holdout test). Quantitative evaluations were conducted by calculating the normalized mean absolute error (NMAE), structural similarity index measurement (SSIM), and Pearson correlation coefficient (PCC). The original contrast enhanced MR images were considered as the ground truth in this analysis. Results: The proposed cascade deep learning workflow synthesized contrast enhanced MR images that are not visually differentiable from the ground truth with and without supervision of the tumor contours during the network training. Difference images and profiles of the synthetic contrast enhanced MR images revealed that intensity differences could be observed in the tumor region if the contour information was not incorporated in network training. Among the holdout test patients, mean values and standard deviations of the NMAE, SSIM, and PCC were 0.063±0.022, 0.991±0.007 and 0.995±0.006, respectively, for the whole brain; and were 0.050±0.025, 0.993±0.008 and 0.999±0.003, respectively, for the tumor contour regions. Quantitative evaluations with five-fold crossvalidation and hold-out test showed that the calculated metrics can be significantly enhanced (p-values ≤ 0.002) with the tumor contour supervision in network training. Conclusion:The proposed workflow was able to generate synthetic contrast enhanced MR images that closely resemble the ground truth images from non-contrast enhanced MR images when the network training included tumor 3278

show abstract

Section: Introductionmentioning

confidence: 99%

Magnetic resonance imaging contrast enhancement synthesis using cascade networks with local supervision

et al. 2022

View full text Add to dashboard Cite

show abstract

“…This section studies the performance efficiency of the proposed SFANR technique and existing noise removal techniques [1], [17]. This work uses brain MS lesion MRI data used in [30] which is very similar to brain MRI used [1], [17]. In this work noise such as Speckle, Gaussian, and Rician is added to the brain MS lesion MRI.…”

Section: Simulation Analysis and Resultsmentioning

confidence: 99%

“…5. A higher value indicates better performance; thus, the SFANR achieves much better outcomes than existing methods, namely, a U-NET [1], Multi-Task Deep Learning (MTDL) [1], Deep Parallel Ensemble Denoising (DPED) [17]. Thus, are very efficient in removing Gaussian, Speckle, and Rician noise from MS lesion MRI.…”

Section: Simulation Analysis and Resultsmentioning

confidence: 99%

“…In [17], the author designed a deep learning model through multi-task learning for extracting association among spatial and relaxation features. The model utilizes association mapping among different T2-weighted MRI with varying contrast for enhancing the reconstruction quality such as low SNR (Signalto-Noise-Ratio), chemical shift artifacts, and edgeenhancement are seen [3] as shown in Fig.…”

Section: Literature Surveymentioning

confidence: 99%

“…In [15] reduced the scanning time by combining contrast and under-sampling reconstruction. Additionally, [16] introduce feature structure to resolve unknown contrast problem during image reconstruction [17]. In [18] presented a new noise removal technique through multi-task deep GAN; However, poor correlation among different layers impacts the quality of the feature constructed.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Sparse Feature Aware Noise Removal Technique for Brain Multiple Sclerosis Lesions using Magnetic Resonance Imaging

Swetha¹,

Aditya²

2022

IJACSA

View full text Add to dashboard Cite

Medical Resonance Imaging (MRI) is nonradioactive-based medical imaging that provides a superresolution of tissues. However, because of its complex nature using existing Deep Learning-based noise removal (i.e., Denoising) techniques, the reconstruction quality is poor and time-consuming. An extensive study shows very limited work has been done on Brain Multiple Sclerosis (MS) Lesions MRI. Designing an efficient noise removal technique will aid in improving MRI quality; thereby will aid in achieving better segmentation classification performance. In reducing computing time and enhancing image quality (i.e. reduce noise) this paper presents the Sparse Feature Aware Noise Removal (SFANR) technique for Brain MRI using Convolution Neural Network (CNN) architecture. A sparse-aware feature is incorporated into the patch-wise morphology learning model for removing noise in large-scale MRI MS lesion datasets. Experimental results demonstrated that our model SFANR outperforms all other state-of-art noise removal techniques in terms of Peak-Signal-Noise-Ratio (PSNR), Structural Similarity Index Metric (SSIM) with less running time.

show abstract

Deep‐Learning‐Based Contrast Synthesis From MRF Parameter Maps in the Knee Joint

Nykänen

Nevalainen

Casula

et al. 2022

Magnetic Resonance Imaging

View full text Add to dashboard Cite

BackgroundMagnetic resonance fingerprinting (MRF) is a method to speed up acquisition of quantitative MRI data. However, MRF does not usually produce contrast‐weighted images that are required by radiologists, limiting reachable total scan time improvement. Contrast synthesis from MRF could significantly decrease the imaging time.PurposeTo improve clinical utility of MRF by synthesizing contrast‐weighted MR images from the quantitative data provided by MRF, using U‐nets that were trained for the synthesis task utilizing L1‐ and perceptual loss functions, and their combinations.Study TypeRetrospective.PopulationKnee joint MRI data from 184 subjects from Northern Finland 1986 Birth Cohort (ages 33–35, gender distribution not available).Field Strength and SequenceA 3 T, multislice‐MRF, proton density (PD)‐weighted 3D‐SPACE (sampling perfection with application optimized contrasts using different flip angle evolution), fat‐saturated T2‐weighted 3D‐space, water‐excited double echo steady state (DESS).AssessmentData were divided into training, validation, test, and radiologist's assessment sets in the following way: 136 subjects to training, 3 for validation, 3 for testing, and 42 for radiologist's assessment. The synthetic and target images were evaluated using 5‐point Likert scale by two musculoskeletal radiologists blinded and with quantitative error metrics.Statistical TestsFriedman's test accompanied with post hoc Wilcoxon signed‐rank test and intraclass correlation coefficient. The statistical cutoff P <0.05 adjusted by Bonferroni correction as necessary was utilized.ResultsThe networks trained in the study could synthesize conventional images with high image quality (Likert scores 3–4 on a 5‐point scale). Qualitatively, the best synthetic images were produced with combination of L1‐ and perceptual loss functions and perceptual loss alone, while L1‐loss alone led to significantly poorer image quality (Likert scores below 3). The interreader and intrareader agreement were high (0.80 and 0.92, respectively) and significant. However, quantitative image quality metrics indicated best performance for the pure L1‐loss.Data ConclusionSynthesizing high‐quality contrast‐weighted images from MRF data using deep learning is feasible. However, more studies are needed to validate the diagnostic accuracy of these synthetic images.Evidence Level4.Technical EfficacyStage 1.

show abstract

Synthesize High-Quality Multi-Contrast Magnetic Resonance Imaging From Multi-Echo Acquisition Using Multi-Task Deep Generative Model

Cited by 34 publications

References 44 publications

Magnetic resonance imaging contrast enhancement synthesis using cascade networks with local supervision

Magnetic resonance imaging contrast enhancement synthesis using cascade networks with local supervision

Sparse Feature Aware Noise Removal Technique for Brain Multiple Sclerosis Lesions using Magnetic Resonance Imaging

Deep‐Learning‐Based Contrast Synthesis From MRF Parameter Maps in the Knee Joint

Contact Info

Product

Resources

About