Synthetic FLAIR as a Substitute for FLAIR Sequence in Acute Ischemic                     Stroke

Benzakoun, Joseph; Deslys, Marc-Antoine; Legrand, Laurence; Hmeydia, Ghazi; Turc, Guillaume; Hassen, Wagih Ben; Charron, Sylvain; Debacker, Clément; Naggara, Olivier; Thirion, Bertrand; Oppenheim, Catherine

doi:10.1148/radiol.211394

Cited by 17 publications

(9 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 17 18 19 With the development of deep-learning GAN, researchers have recently studied cross-modality syntheses through this technique. 20 21 …”

Section: Discussionmentioning

confidence: 99%

“…A previous study tried to synthesize fluid-attenuated inversion recovery (FLAIR) sequences in brain MRI of patients with acute ischemic stroke. 20 They tried to generate FLAIR images from diffusion-weighted images and evaluated the feasibility of replacing the true image with a synthetic one. The agreement between the true and generated FLAIR was comparable (ĸ=0.88) to the present study results (ĸ=0.81-0.88).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Synthesis of T2-weighted images from proton density images using a generative adversarial network in a temporomandibular joint magnetic resonance imaging protocol

Lee

Choi

et al. 2022

Imaging Sci Dent

View full text Add to dashboard Cite

Purpose This study proposed a generative adversarial network (GAN) model for T2-weighted image (WI) synthesis from proton density (PD)-WI in a temporomandibular joint (TMJ) magnetic resonance imaging (MRI) protocol. Materials and Methods From January to November 2019, MRI scans for TMJ were reviewed and 308 imaging sets were collected. For training, 277 pairs of PD- and T2-WI sagittal TMJ images were used. Transfer learning of the pix2pix GAN model was utilized to generate T2-WI from PD-WI. Model performance was evaluated with the structural similarity index map (SSIM) and peak signal-to-noise ratio (PSNR) indices for 31 predicted T2-WI (pT2). The disc position was clinically diagnosed as anterior disc displacement with or without reduction, and joint effusion as present or absent. The true T2-WI-based diagnosis was regarded as the gold standard, to which pT2-based diagnoses were compared using Cohen’s ĸ coefficient. Results The mean SSIM and PSNR values were 0.4781(±0.0522) and 21.30(±1.51) dB, respectively. The pT2 protocol showed almost perfect agreement (ĸ=0.81) with the gold standard for disc position. The number of discordant cases was higher for normal disc position (17%) than for anterior displacement with reduction (2%) or without reduction (10%). The effusion diagnosis also showed almost perfect agreement (ĸ=0.88), with higher concordance for the presence (85%) than for the absence (77%) of effusion. Conclusion The application of pT2 images for a TMJ MRI protocol useful for diagnosis, although the image quality of pT2 was not fully satisfactory. Further research is expected to enhance pT2 quality.

show abstract

“… 17 18 19 With the development of deep-learning GAN, researchers have recently studied cross-modality syntheses through this technique. 20 21 …”

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Synthesis of T2-weighted images from proton density images using a generative adversarial network in a temporomandibular joint magnetic resonance imaging protocol

Lee

Choi

et al. 2022

Imaging Sci Dent

View full text Add to dashboard Cite

show abstract

“…5 In recent years, deep learning, particularly the generative adversarial network, has been successfully used in various medical image synthesis problems. 7,8 Nie et al proposed a deep convolutional adversarial network incorporating gradient difference loss to learn the nonlinear 3T-to-7T mapping. 9 Qu et al introduced a deep learning network (i.e., WATNet) that leverages the wavelet domain as a prior to synthesizing 7T images with better tissue contrast and greater detail.…”

mentioning

confidence: 99%

“…However, the effectiveness of these methods is typically limited by the quality of hand‐crafted features 5 . In recent years, deep learning, particularly the generative adversarial network, has been successfully used in various medical image synthesis problems 7,8 . Nie et al proposed a deep convolutional adversarial network incorporating gradient difference loss to learn the nonlinear 3T‐to‐7T mapping 9 .…”

mentioning

confidence: 99%

Synthesized 7T MPRAGE From 3T MPRAGE Using Generative Adversarial Network and Validation in Clinical Brain Imaging: A Feasibility Study

Duan

Bian

Cheng

et al. 2023

Magnetic Resonance Imaging

View full text Add to dashboard Cite

BackgroundUltra‐high field 7T MRI can provide excellent tissue contrast and anatomical details, but is often cost prohibitive, and is not widely accessible in clinical practice.PurposeTo generate synthetic 7T images from widely acquired 3T images with deep learning and to evaluate the feasibility of this approach for brain imaging.Study TypeProspective.Population33 healthy volunteers and 89 patients with brain diseases, divided into training, and evaluation datasets in the ratio 4:1.Sequence and Field StrengthT1‐weighted nonenhanced or contrast‐enhanced magnetization‐prepared rapid acquisition gradient‐echo sequence at both 3T and 7T.AssessmentA generative adversarial network (SynGAN) was developed to produce synthetic 7T images from 3T images as input. SynGAN training and evaluation were performed separately for nonenhanced and contrast‐enhanced paired acquisitions. Qualitative image quality of acquired 3T and 7T images and of synthesized 7T images was evaluated by three radiologists in terms of overall image quality, artifacts, sharpness, contrast, and visualization of vessel using 5‐point Likert scales.Statistical TestsWilcoxon signed rank tests to compare synthetic 7T images with acquired 7T and 3T images and intraclass correlation coefficients to evaluate interobserver variability. P < 0.05 was considered significant.ResultsOf the 122 paired 3T and 7T MRI scans, 66 were acquired without contrast agent and 56 with contrast agent. The average time to generate synthetic images was ~11.4 msec per slice (2.95 sec per participant). The synthetic 7T images achieved significantly improved tissue contrast and sharpness in comparison to 3T images in both nonenhanced and contrast‐enhanced subgroups. Meanwhile, there was no significant difference between acquired 7T and synthetic 7T images in terms of all the evaluation criteria for both nonenhanced and contrast‐enhanced subgroups (P ≥ 0.180).Data ConclusionThe deep learning model has potential to generate synthetic 7T images with similar image quality to acquired 7T images.Level of Evidence2Technical EfficacyStage 1

show abstract

“…A GAN is a deep learning technique that enables the generation of new images from unlabeled original images [ 1 ]. GANs can learn the data distribution from training samples and generate realistic imaging data that have a similar distribution to the original data but are otherwise different [ 2 3 4 5 ]. Image generation using a GAN is an attractive solution to overcome the limitations of small datasets [ 6 7 ], and the generated images eventually become data inputs and expand the use of deep learning algorithms.…”

mentioning

confidence: 99%

Research Highlight: Use of Generative Images Created with Artificial Intelligence for Brain Tumor Imaging

et al. 2022

View full text Add to dashboard Cite

Synthetic FLAIR as a Substitute for FLAIR Sequence in Acute Ischemic Stroke

Abstract: Synthetic fluid-attenuated inversion recovery (FLAIR) generated with deep learning is asaccurate as a real FLAIR sequence for the identification of early stroke.

Cited by 17 publications

References 37 publications

Synthesis of T2-weighted images from proton density images using a generative adversarial network in a temporomandibular joint magnetic resonance imaging protocol

Synthesis of T2-weighted images from proton density images using a generative adversarial network in a temporomandibular joint magnetic resonance imaging protocol

Synthesized 7T MPRAGE From 3T MPRAGE Using Generative Adversarial Network and Validation in Clinical Brain Imaging: A Feasibility Study

Research Highlight: Use of Generative Images Created with Artificial Intelligence for Brain Tumor Imaging

Contact Info

Product

Resources

About