Generative Adversarial Networks in Medical Image Processing

Gong, Meiqin; Chen, Siyu; Chen, Qingyuan; Zeng, Yuanqi; Zhang, Yongqing

doi:10.2174/1381612826666201125110710

Cited by 39 publications

(23 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In terms of GAN type selection, CycleGAN produces more acceptable synthetic images compared to other widely used GAN models based on similarity metric evaluations [35]. In addition, CycleGAN is superior to other GAN models because it does not require paired datasets, does not have the risk of disappearing of gradient, and is more successful in the case of a small amount of data [35,36]. For this reason, this study proposes a CycleGAN data augmentation+CNN classification model with residual blocks for classifying brain tumors.…”

Section: Review Of the Existing Methods In Brain Tumor Classificationmentioning

confidence: 99%

Improving Brain Tumor Classification with Deep Learning Using燬ynthetic燚ata

Yapıcı¹,

Karakış²,

Gurkahraman³

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Deep learning (DL) techniques, which do not need complex preprocessing and feature analysis, are used in many areas of medicine and achieve promising results. On the other hand, in medical studies, a limited dataset decreases the abstraction ability of the DL model. In this context, we aimed to produce synthetic brain images including three tumor types (glioma, meningioma, and pituitary), unlike traditional data augmentation methods, and classify them with DL. This study proposes a tumor classification model consisting of a Dense Convolutional Network (DenseNet121)based DL model to prevent forgetting problems in deep networks and delay information flow between layers. By comparing models trained on two different datasets, we demonstrated the effect of synthetic images generated by Cycle Generative Adversarial Network (CycleGAN) on the generalization of DL. One model is trained only on the original dataset, while the other is trained on the combined dataset of synthetic and original images. Synthetic data generated by CycleGAN improved the best accuracy values for glioma, meningioma, and pituitary tumor classes from 0.9633, 0.9569, and 0.9904 to 0.9968, 0.9920, and 0.9952, respectively. The developed model using synthetic data obtained a higher accuracy value than the related studies in the literature. Additionally, except for pixel-level and affine transform data augmentation, synthetic data has been generated in the figshare brain dataset for the first time.

show abstract

Section: Review Of the Existing Methods In Brain Tumor Classificationmentioning

confidence: 99%

Improving Brain Tumor Classification with Deep Learning Using燬ynthetic燚ata

Yapıcı¹,

Karakış²,

Gurkahraman³

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…A GAN, in particular, does not need labeled data to attain an exquisite outcome, which could be generated through the Generator (G) and Discriminator (D) networks competition. As a result, GANs are fast proving to be a cutting-edge basis, achieving better results in various medical applications including image registration [9].…”

Section: B Generative Adversarial Network (Gan)mentioning

confidence: 99%

D²BGAN: Dual Discriminator Bayesian Generative Adversarial Network for Deformable MR-Ultrasound Registration Applied to Brain Shift compensation

Rahmani

Moghadssi

Farnia

et al. 2022

Preprint

View full text Add to dashboard Cite

Purpose: In neurosurgery, image guidance is provided based on the patient to pre-operative data registration with a neuronavigation system. However, the brain shift phenomena invalidate the accuracy of the navigation system during neurosurgery. One of the most common approaches for brain shift compensation is using intra-operative ultrasound (iUS) imaging followed by registration of iUS with pre-operative magnetic resonance (MR) images. While, due to the unpredictable nature of brain deformation and the low quality of ultrasound images, finding a satisfactory multimodal image registration approach remains a challenging task. Methods: We proposed a new automatic unsupervised end-to-end MR-iUS registration approach based on the Dual Discriminator Bayesian Generative Adversarial Network (D2BGAN). The proposed network consists of two discriminators and is optimized by introducing a Bayesian loss function to improve the generator functionality and adding a mutual information loss function to the discriminator for similarity measurement. An evaluation was performed using the RESECT training dataset based on the organizer manual landmarks. Results: The mean Target Registration Error (mTRE) after MR-iUS registration using D2BGAN reached 0.75 mm. The D2BGAN illustrated a clear advantage by 85% improvement in the mTRE of MR-iUS registration over the initial error. Also, the results confirmed that the proposed Bayesian loss function rather than the typical loss function outperforms the accuracy of MR-iUS registration by 23%. Conclusion: The D2BGAN improved the registration accuracy while allowing us to maintain the intensity and anatomical information of the input images in the registration process. It promotes the advancement of deep learning-based multi-modality registration techniques.

show abstract

“…Motivated by the impressive results achieved by GANs on natural images, the goal of this work is to evaluate how well these machines perform on medical data, an area well-known for its smaller datasets and strict anatomical requirements. Recent reviews have been published, analyzing the use of GANs in medical image analysis [ 4 , 5 , 6 ]. The distinctiveness of our work is the empirical evaluation of the benefits of GAN-generated data in this context, in addition to the large hyperparameters analysis of the different approaches.…”

Section: Introductionmentioning

confidence: 99%

GANs for Medical Image Synthesis: An Empirical Study

Skandarani¹,

2023

View full text Add to dashboard Cite

Generative adversarial networks (GANs) have become increasingly powerful, generating mind-blowing photorealistic images that mimic the content of datasets they have been trained to replicate. One recurrent theme in medical imaging, is whether GANs can also be as effective at generating workable medical data, as they are for generating realistic RGB images. In this paper, we perform a multi-GAN and multi-application study, to gauge the benefits of GANs in medical imaging. We tested various GAN architectures, from basic DCGAN to more sophisticated style-based GANs, on three medical imaging modalities and organs, namely: cardiac cine-MRI, liver CT, and RGB retina images. GANs were trained on well-known and widely utilized datasets, from which their FID scores were computed, to measure the visual acuity of their generated images. We further tested their usefulness by measuring the segmentation accuracy of a U-Net trained on these generated images and the original data. The results reveal that GANs are far from being equal, as some are ill-suited for medical imaging applications, while others performed much better. The top-performing GANs are capable of generating realistic-looking medical images by FID standards, that can fool trained experts in a visual Turing test and comply to some metrics. However, segmentation results suggest that no GAN is capable of reproducing the full richness of medical datasets.

show abstract

Generative Adversarial Networks in Medical Image Processing

Cited by 39 publications

References 59 publications

Improving Brain Tumor Classification with Deep Learning Using燬ynthetic燚ata

Improving Brain Tumor Classification with Deep Learning Using燬ynthetic燚ata

D²BGAN: Dual Discriminator Bayesian Generative Adversarial Network for Deformable MR-Ultrasound Registration Applied to Brain Shift compensation

GANs for Medical Image Synthesis: An Empirical Study

Contact Info

Product

Resources

About

Generative Adversarial Networks in Medical Image Processing

Cited by 39 publications

References 59 publications

Improving Brain Tumor Classification with Deep Learning Using燬ynthetic燚ata

Improving Brain Tumor Classification with Deep Learning Using燬ynthetic燚ata

D2BGAN: Dual Discriminator Bayesian Generative Adversarial Network for Deformable MR-Ultrasound Registration Applied to Brain Shift compensation

GANs for Medical Image Synthesis: An Empirical Study

Contact Info

Product

Resources

About

D²BGAN: Dual Discriminator Bayesian Generative Adversarial Network for Deformable MR-Ultrasound Registration Applied to Brain Shift compensation