Quality assessment of anatomical MRI images from generative adversarial networks: Human assessment and image quality metrics

Treder, Matthias S.; Codrai, Ryan; Tsvetanov, Kamen A.

doi:10.1016/j.jneumeth.2022.109579

Cited by 16 publications

(12 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To the best of our knowledge, there is no single study that addresses what criteria for each image quality metric (e.g., SSIM, PSNR, inception score, and frechet inception distance) in the GAN-based augmentation models are sufficient enough to fool the clinicians into whether the medical images are taken experimentally or generated synthetically. However, some recent studies have benefited the human assessment as a gold standard to compare the synthesized medical samples with original medical images [ 12 , 60 , 61 , 62 ]. Thus, a potential perspective work would be conducted a visual assessment by some blinded radiologists to identify real 18F-FDG PET images versus augmented ones and rate them to find out what range for these quantitative metrics is sufficient enough as a diagnostic criterion.…”

Section: Resultsmentioning

confidence: 99%

Synthetic 18F-FDG PET Image Generation Using a Combination of Biomathematical Modeling and Machine Learning

Abazari

Soltani

Kashkooli

et al. 2022

Cancers

View full text Add to dashboard Cite

No previous works have attempted to combine generative adversarial network (GAN) architectures and the biomathematical modeling of positron emission tomography (PET) radiotracer uptake in tumors to generate extra training samples. Here, we developed a novel computational model to produce synthetic 18F-fluorodeoxyglucose (18F-FDG) PET images of solid tumors in different stages of progression and angiogenesis. First, a comprehensive biomathematical model is employed for creating tumor-induced angiogenesis, intravascular and extravascular fluid flow, as well as modeling of the transport phenomena and reaction processes of 18F-FDG in a tumor microenvironment. Then, a deep convolutional GAN (DCGAN) model is employed for producing synthetic PET images using 170 input images of 18F-FDG uptake in each of 10 different tumor microvascular networks. The interstitial fluid parameters and spatiotemporal distribution of 18F-FDG uptake in tumor and healthy tissues have been compared against previously published numerical and experimental studies, indicating the accuracy of the model. The structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) of the generated PET sample and the experimental one are 0.72 and 28.53, respectively. Our results demonstrate that a combination of biomathematical modeling and GAN-based augmentation models provides a robust framework for the non-invasive and accurate generation of synthetic PET images of solid tumors in different stages.

show abstract

Section: Resultsmentioning

confidence: 99%

Synthetic 18F-FDG PET Image Generation Using a Combination of Biomathematical Modeling and Machine Learning

Abazari

Soltani

Kashkooli

et al. 2022

Cancers

View full text Add to dashboard Cite

show abstract

“…To further evaluate the difference among datasets from a quantitative perspective, we computed the Fréchet inception distance (FID) (Heusel et al, 2017 ) between each pair of datasets. FID is widely used in the GAN literature and is a popular metric for measuring the feature distance between two distributions, which also shows sensitivity to image quality and good correspondence with human perception (Treder et al, 2022 ). We randomly selected 200 samples of each dataset, took a representative slice (the central slice in the sagittal direction), and computed FID between the datasets.…”

Section: Resultsmentioning

confidence: 99%

“…As an alternative to GANs, other methods using variational autoencoders (VAEs) (Kingma & Welling, 2013) have also been devised, such as Tudosiu et al (2020). However, it has been reported that GANs tend to produce clearer images than VAEs in diffusion-weighted and T1-weighted images (Treder et al, 2022). More recently, latent diffusion models have been proposed for generating synthetic images (Pinaya et al, 2022).…”

Section: Related Workmentioning

confidence: 99%

Fast three‐dimensional image generation for healthy brain aging using diffeomorphic registration

Tzortzakakis

Barroso

et al. 2022

Human Brain Mapping

View full text Add to dashboard Cite

Predicting brain aging can help in the early detection and prognosis of neurodegenerative diseases. Longitudinal cohorts of healthy subjects scanned through magnetic resonance imaging (MRI) have been essential to understand the structural brain changes due to aging. However, these cohorts suffer from missing data due to logistic issues in the recruitment of subjects. This paper proposes a methodology for filling up missing data in longitudinal cohorts with anatomically plausible images that capture the subject‐specific aging process. The proposed methodology is developed within the framework of diffeomorphic registration. First, two novel modules are introduced within Synthmorph, a fast, state‐of‐the‐art deep learning‐based diffeomorphic registration method, to simulate the aging process between the first and last available MRI scan for each subject in three‐dimensional (3D). The use of image registration also makes the generated images plausible by construction. Second, we used six image similarity measurements to rearrange the generated images to the specific age range. Finally, we estimated the age of every generated image by using the assumption of linear brain decay in healthy subjects. The methodology was evaluated on 2662 T1‐weighted MRI scans from 796 healthy participants from 3 different longitudinal cohorts: Alzheimer's Disease Neuroimaging Initiative, Open Access Series of Imaging Studies‐3, and Group of Neuropsychological Studies of the Canary Islands (GENIC). In total, we generated 7548 images to simulate the access of a scan per subject every 6 months in these cohorts. We evaluated the quality of the synthetic images using six quantitative measurements and a qualitative assessment by an experienced neuroradiologist with state‐of‐the‐art results. The assumption of linear brain decay was accurate in these cohorts ( R 2 ∈ [.924, .940]). The experimental results show that the proposed methodology can produce anatomically plausible aging predictions that can be used to enhance longitudinal datasets. Compared to deep learning‐based generative methods, diffeomorphic registration is more likely to preserve the anatomy of the different structures of the brain, which makes it more appropriate for its use in clinical applications. The proposed methodology is able to efficiently simulate anatomically plausible 3D MRI scans of brain aging of healthy subjects from two images scanned at two different time points.

show abstract

“…Naturally, it is impractical to find such an image, because generative models generate images that have a multivariate statistical relationship with a set of real images, but not twins of real images. Therefore, non-reference methods, such as the naturalness image quality evaluator (NIQE), began to be used with a combination of other methods [ 36 ]. The statistical distribution of the image is evaluated not by that of another base image but by calculating the deviations from the statistical regularities of the image itself.…”

Section: Related Workmentioning

confidence: 99%

“…Because of this, it cannot evaluate the similarity between the real set and the synthetic set, it can only evaluate the quality of the image. However, in the work [ 36 ], it was noted that the use of the NIQE method in the earlier epochs of GAN, gives good results. As in the initial epochs of the training, the images will be of poor quality and slightly noisy.…”

Section: Related Workmentioning

confidence: 99%

Evaluating Synthetic Medical Images Using Artificial Intelligence with the GAN Algorithm

Abdusalomov

Nasimov

Nasimova

et al. 2023

Sensors

View full text Add to dashboard Cite

In recent years, considerable work has been conducted on the development of synthetic medical images, but there are no satisfactory methods for evaluating their medical suitability. Existing methods mainly evaluate the quality of noise in the images, and the similarity of the images to the real images used to generate them. For this purpose, they use feature maps of images extracted in different ways or distribution of images set. Then, the proximity of synthetic images to the real set is evaluated using different distance metrics. However, it is not possible to determine whether only one synthetic image was generated repeatedly, or whether the synthetic set exactly repeats the training set. In addition, most evolution metrics take a lot of time to calculate. Taking these issues into account, we have proposed a method that can quantitatively and qualitatively evaluate synthetic images. This method is a combination of two methods, namely, FMD and CNN-based evaluation methods. The estimation methods were compared with the FID method, and it was found that the FMD method has a great advantage in terms of speed, while the CNN method has the ability to estimate more accurately. To evaluate the reliability of the methods, a dataset of different real images was checked.

show abstract

Quality assessment of anatomical MRI images from generative adversarial networks: Human assessment and image quality metrics

Cited by 16 publications

References 60 publications

Synthetic 18F-FDG PET Image Generation Using a Combination of Biomathematical Modeling and Machine Learning

Synthetic 18F-FDG PET Image Generation Using a Combination of Biomathematical Modeling and Machine Learning

Fast three‐dimensional image generation for healthy brain aging using diffeomorphic registration

Evaluating Synthetic Medical Images Using Artificial Intelligence with the GAN Algorithm

Contact Info

Product

Resources

About