Deep learning enables reduced gadolinium dose for contrast‐enhanced brain MRI

Gong, Enhao; Pauly, John M.; Wintermark, Max; Zaharchuk, Greg

doi:10.1002/jmri.25970

Cited by 254 publications

(225 citation statements)

References 39 publications

Supporting

Mentioning

194

Contrasting

Unclassified

Order By: Relevance

“…This property has led to many applications in medical image reconstructions such as improving image quality, 12,13 solving inverse problems, [14][15][16][17] and synthetic image generation. [18][19][20][21] Considering the current outcomes of deep neural networks on these applications, the approach may be applicable for correcting the artifacts of synthetic FLAIR images.…”

mentioning

confidence: 99%

Data‐driven synthetic MRI FLAIR artifact correction via deep neural network

Ryu

Nam

Gho³

et al. 2019

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background FLAIR (fluid attenuated inversion recovery) imaging via synthetic MRI methods leads to artifacts in the brain, which can cause diagnostic limitations. The main sources of the artifacts are attributed to the partial volume effect and flow, which are difficult to correct by analytical modeling. In this study, a deep learning (DL)‐based synthetic FLAIR method was developed, which does not require analytical modeling of the signal. Purpose To correct artifacts in synthetic FLAIR using a DL method. Study Type Retrospective. Subjects A total of 80 subjects with clinical indications (60.6 ± 16.7 years, 38 males, 42 females) were divided into three groups: a training set (56 subjects, 62.1 ± 14.8 years, 25 males, 31 females), a validation set (1 subject, 62 years, male), and the testing set (23 subjects, 57.3 ± 20.4 years, 13 males, 10 females). Field Strength/Sequence 3 T MRI using a multiple‐dynamic multiple‐echo acquisition (MDME) sequence for synthetic MRI and a conventional FLAIR sequence. Assessment Normalized root mean square (NRMSE) and structural similarity (SSIM) were computed for uncorrected synthetic FLAIR and DL‐corrected FLAIR. In addition, three neuroradiologists scored the three FLAIR datasets blindly, evaluating image quality and artifacts for sulci/periventricular and intraventricular/cistern space regions. Statistical Tests Pairwise Student's t‐tests and a Wilcoxon test were performed. Results For quantitative assessment, NRMSE improved from 4.2% to 2.9% (P < 0.0001) and SSIM improved from 0.85 to 0.93 (P < 0.0001). Additionally, NRMSE values significantly improved from 1.58% to 1.26% (P < 0.001), 3.1% to 1.5% (P < 0.0001), and 2.7% to 1.4% (P < 0.0001) in white matter, gray matter, and cerebral spinal fluid (CSF) regions, respectively, when using DL‐corrected FLAIR. For qualitative assessment, DL correction achieved improved overall quality, fewer artifacts in sulci and periventricular regions, and in intraventricular and cistern space regions. Data Conclusion The DL approach provides a promising method to correct artifacts in synthetic FLAIR. Level of Evidence: 4 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2019;50:1413–1423.

show abstract

mentioning

confidence: 99%

Data‐driven synthetic MRI FLAIR artifact correction via deep neural network

Ryu

Nam

Gho³

et al. 2019

Magnetic Resonance Imaging

View full text Add to dashboard Cite

show abstract

“…Such a CNN structure has shown impressive results for image translation and segmentation in many recent studies. 20,46,47 In the current study, the U-Net structure is modified to enable dual outputs, and this new design is referred to as R-Net. Namely, the network is bifurcated following the last up-sampling layer in the decoder.…”

mentioning

confidence: 99%

SUSAN: segment unannotated image structure using adversarial network

Liu

2018

Magnetic Resonance in Med

View full text Add to dashboard Cite

Purpose To describe and evaluate a segmentation method using joint adversarial and segmentation convolutional neural network to achieve accurate segmentation using unannotated MR image datasets. Theory and Methods A segmentation pipeline was built using joint adversarial and segmentation network. A convolutional neural network technique called cycle‐consistent generative adversarial network (CycleGAN) was applied as the core of the method to perform unpaired image‐to‐image translation between different MR image datasets. A joint segmentation network was incorporated into the adversarial network to obtain additional functionality for semantic segmentation. The fully automated segmentation method termed as SUSAN was tested for segmenting bone and cartilage on 2 clinical knee MR image datasets using images and annotated segmentation masks from an online publicly available knee MR image dataset. The segmentation results were compared using quantitative segmentation metrics with the results from a supervised U‐Net segmentation method and 2 registration methods. The Wilcoxon signed‐rank test was used to evaluate the value difference of quantitative metrics between different methods. Results The proposed method SUSAN provided high segmentation accuracy with results comparable to the supervised U‐Net segmentation method (most quantitative metrics having P > 0.05) and significantly better than a multiatlas registration method (all quantitative metrics having P < 0.001) and a direct registration method (all quantitative metrics having P< 0.0001) for the clinical knee image datasets. SUSAN also demonstrated the applicability for segmenting knee MR images with different tissue contrasts. Conclusion SUSAN performed rapid and accurate tissue segmentation for multiple MR image datasets without the need for sequence specific segmentation annotation. The joint adversarial and segmentation network and training strategy have promising potential applications in medical image segmentation.

show abstract

“…One of the innovative clinical applications of AI lies in medical imaging, which includes the following aspects: image acquisition, removing the unwanted artifacts, improving the image quality, reducing the contrast agent dose, and shortening the diagnose period (Gong et al, 2018;Shan et al, 2018;Zaharchuk et al, 2018;Codari et al, 2019;Zhu et al, 2019).…”

Section: The Role Of Artificial Intelligence For Developing Novel/biomentioning

confidence: 99%

“…For biomedical imaging, the image reconstruction can be improved by exploiting machine learning or deep learning of AI, where powerful graphical processing units and neural networks formed in computer will assist the reconstruction processing (Gong et al, 2018;Shan et al, 2018;Zaharchuk et al, 2018). Alternatively, after accessing to large amount of information, the deep learning of AI will be processed and form an algorithm based on these inputs.…”

Section: The Role Of Artificial Intelligence For Developing Novel/biomentioning

confidence: 99%

“…As heavy metal gadolinium is indispensably used as MRI contrast agent and can remain in human body after scans, researchers are trying to improve the safety of patients after keeping the achieved scan information. Therefore, deep machine learning of AI can be implemented based on designed experiments, that is contrast agent experiment of less dose by comparing with that of no dose and full dose (Gong et al, 2018). For instance, Gong et al performed an attempt on contrast enhanced MRI with low dose of contrast agent through deep learning of AI (Figure 11).…”

Section: The Role Of Artificial Intelligence For Developing Novel/biomentioning

confidence: 99%

See 1 more Smart Citation