Generative Adversarial Networks to Synthesize Missing T1 and FLAIR                     MRI Sequences for Use in a Multisequence Brain Tumor Segmentation                     Model

Conte, Gian Marco; Weston, Alexander D.; Vogelsang, David C; Philbrick, Kenneth A.; Cai, Jason; Barbera, Maurizio; Sanvito, Francesco; Lachance, Daniel H.; Jenkins, Robert B.; Tobin, W Oliver; Eckel‐Passow, Jeanette E.; Erickson, Bradley J.

doi:10.1148/radiol.2021219009

Cited by 8 publications

(9 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, our network differs from others due to its special tumor-targeting loss, which sets the focus on the later field of application in glioma segmentation. With our approach and this specific loss, we were able to replicate and in some cases exceed the results Conte et al 7 achieved, for example, with an MSE of 0.003 for synthetic T1w images compared with their result of 0.005. We achieve a lower variance in our results with an interquartile range from 0.002 to 0.004 compared with their result of 0.001 to 0.015.…”

Section: Discussionsupporting

confidence: 61%

“…Other authors, for example, Conte et al, 7 suggest similar approaches. Compared with their study, our algorithm not only is able to synthesize all missing sequences in comparison to only FLAIR and T1w, but does so with only one GAN and therefore only one generator, thanks to the many-to-many mapping approach.…”

Section: Discussionmentioning

confidence: 87%

“…An alternative approach is to fill the missing input with a mask of the patient's brain. More recently, deep learning networks based on generative adversarial networks (GANs) have been explored for this task 7 . The motivating principle behind GANs is a “competition” between 2 networks, a generator that creates new images and a discriminator that judges if images are real or generated.…”

mentioning

confidence: 99%

“…More recently, deep learning networks based on generative adversarial networks (GANs) have been explored for this task. 7 The motivating principle behind GANs is a "competition" between 2 networks, a generator that creates new images and a discriminator that judges if images are real or generated. In this setting, each network tries to "overpower" the other and both improve, generating more realistic images over time.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Improving Automated Glioma Segmentation in Routine Clinical Use Through Artificial Intelligence-Based Replacement of Missing Sequences With Synthetic Magnetic Resonance Imaging Scans

et al. 2021

View full text Add to dashboard Cite

Objectives: Although automated glioma segmentation holds promise for objective assessment of tumor biology and response, its routine clinical use is impaired by missing sequences, for example, due to motion artifacts. The aim of our study was to develop and validate a generative adversarial network for synthesizing missing sequences to allow for a robust automated segmentation. Materials and Methods: Our model was trained on data from The Cancer Imaging Archive (n = 238 WHO II-IV gliomas) to synthesize either missing FLAIR, T2-weighted, T1-weighted (T1w), or contrast-enhanced T1w images from available sequences, using a novel tumor-targeting loss to improve synthesis of tumor areas. We validated performance in a test set from both the REMBRANDT repository and our local institution (n = 68 WHO II-IV gliomas), using qualitative image appearance metrics, but also segmentation performance with state-of-the-art segmentation models. Segmentation of synthetic images was compared with 2 commonly used strategies for handling missing input data, entering a blank mask or copying an existing sequence. Results: Across tumor areas and missing sequences, synthetic images generally outperformed both conventional approaches, in particular when FLAIR was missing.Here, for edema and whole tumor segmentation, we improved the Dice score, a common metric for evaluation of segmentation performance, by 12% and 11%, respectively, over the best conventional method. No method was able to reliably replace missing contrast-enhanced T1w images. Discussion: Replacing missing nonenhanced magnetic resonance sequences via synthetic images significantly improves segmentation quality over most conventional approaches. This model is freely available and facilitates more widespread use of automated segmentation in routine clinical use, where missing sequences are common.

show abstract

Section: Discussionsupporting

confidence: 61%

Section: Discussionmentioning

confidence: 87%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Improving Automated Glioma Segmentation in Routine Clinical Use Through Artificial Intelligence-Based Replacement of Missing Sequences With Synthetic Magnetic Resonance Imaging Scans

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Multiparametric MRI has been used for analyses using deep learning. Multiparametric MRI is potentially useful for lesion segmentation to fully capture the extent of the disease and has been used to segment cancers and multiple sclerosis plaques 133,139,141,143–149 . Wahid et al 143 used a CNN model based on the 3D residual U-net architecture to segment oropharyngeal cancers based on 5 multiparametric MRI inputs (T2-weighted and T1-weighted image, ADC map, as well as volume transfer constant [K trans ] and extravascular extracellular volume fraction [Ve] derived from DCE MRI).…”

Section: Analyzing Multiparametric Mr Imagesmentioning

confidence: 99%

Multiparametric MRI

et al. 2023

View full text Add to dashboard Cite

With the recent advancements in rapid imaging methods, higher numbers of contrasts and quantitative parameters can be acquired in less and less time. Some acquisition models simultaneously obtain multiparametric images and quantitative maps to reduce scan times and avoid potential issues associated with the registration of different images. Multiparametric magnetic resonance imaging (MRI) has the potential to provide complementary information on a target lesion and thus overcome the limitations of individual techniques. In this review, we introduce methods to acquire multiparametric MRI data in a clinically feasible scan time with a particular focus on simultaneous acquisition techniques, and we discuss how multiparametric MRI data can be analyzed as a whole rather than each parameter separately. Such data analysis approaches include clinical scoring systems, machine learning, radiomics, and deep learning. Other techniques combine multiple images to create new quantitative maps associated with meaningful aspects of human biology. They include the magnetic resonance g-ratio, the inner to the outer diameter of a nerve fiber, and the aerobic glycolytic index, which captures the metabolic status of tumor tissues.

show abstract

Domain-Adaptive 3D Medical Image Synthesis: An Efficient Unsupervised Approach

Qingqiao

Zhang

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Generative Adversarial Networks to Synthesize Missing T1 and FLAIR MRI Sequences for Use in a Multisequence Brain Tumor Segmentation Model

Cited by 8 publications

References 0 publications

Improving Automated Glioma Segmentation in Routine Clinical Use Through Artificial Intelligence-Based Replacement of Missing Sequences With Synthetic Magnetic Resonance Imaging Scans

Improving Automated Glioma Segmentation in Routine Clinical Use Through Artificial Intelligence-Based Replacement of Missing Sequences With Synthetic Magnetic Resonance Imaging Scans

Multiparametric MRI

Domain-Adaptive 3D Medical Image Synthesis: An Efficient Unsupervised Approach

Contact Info

Product

Resources

About