Evaluating Synthetic Medical Images Using Artificial Intelligence with the GAN Algorithm

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.

[1]  K. Chung,et al.  Robust Data Augmentation Generative Adversarial Network for Object Detection , 2022, Sensors.

[2]  H. P. Oliveira,et al.  Lung CT image synthesis using GANs , 2022, Expert Syst. Appl..

[3]  Sridha Sridharan,et al.  Pose-driven Attention-guided Image Generation for Person Re-Identification , 2021, Pattern Recognit..

[4]  M. Tsiknakis,et al.  Enhancing cancer differentiation with synthetic MRI examinations via generative models: a systematic review , 2022, Insights into imaging.

[5]  I. Tarimer,et al.  Effect of Feature Selection on the Accuracy of Music Popularity Classification Using Machine Learning Algorithms , 2022, Electronics.

[6]  Nawaf R Alharbe,et al.  Generating Synthetic Images for Healthcare with Novel Deep Pix2Pix GAN , 2022, Electronics.

[7]  T. Whangbo,et al.  Improved Feature Parameter Extraction from Speech Signals Using Machine Learning Algorithm , 2022, Sensors.

[8]  K. Brock,et al.  Evaluating the Performance of StyleGAN2-ADA on Medical Images , 2022, SASHIMI@MICCAI.

[9]  T. Whangbo,et al.  Attention 3D U-Net with Multiple Skip Connections for Segmentation of Brain Tumor Images , 2022, Sensors.

[10]  Á. Figueira,et al.  Survey on Synthetic Data Generation, Evaluation Methods and GANs , 2022, Mathematics.

[11]  Aaron S. Coyner,et al.  Synthetic Medical Images for Robust, Privacy-Preserving Training of Artificial Intelligence , 2022, Ophthalmology science.

[12]  Ren Wang,et al.  AUE-Net: Automated Generation of Ultrasound Elastography Using Generative Adversarial Network , 2022, Diagnostics.

[13]  M. Treder,et al.  Quality assessment of anatomical MRI images from generative adversarial networks: Human assessment and image quality metrics , 2022, Journal of Neuroscience Methods.

[14]  Mukhriddin Mukhiddinov,et al.  An improvement for the automatic classification method for ultrasound images used on CNN , 2021, Int. J. Wavelets Multiresolution Inf. Process..

[15]  Sajad Amouei Sheshkal,et al.  SinGAN-Seg: Synthetic training data generation for medical image segmentation , 2021, PloS one.

[16]  Simulation and Synthesis in Medical Imaging: 7th International Workshop, SASHIMI 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022, Proceedings , 2022, SASHIMI@MICCAI.

[17]  D. Shen,et al.  Review and Prospect: Artificial Intelligence in Advanced Medical Imaging , 2021, Frontiers in Radiology.

[18]  B. Muminov,et al.  Comparative Analysis of the Results of Algorithms for Dilated Cardiomyopathy and Hypertrophic Cardiomyopathy Using Deep Learning , 2021, 2021 International Conference on Information Science and Communications Technologies (ICISCT).

[19]  Taeg Keun Whangbo,et al.  3D Volume Reconstruction from MRI Slices based on VTK , 2021, 2021 International Conference on Information and Communication Technology Convergence (ICTC).

[20]  Okyay Kaynak,et al.  When medical images meet generative adversarial network: recent development and research opportunities , 2021, Discover Artificial Intelligence.

[21]  Ming Y. Lu,et al.  Synthetic data in machine learning for medicine and healthcare , 2021, Nature Biomedical Engineering.

[22]  S. Seyyedsalehi,et al.  Multi WGAN-GP loss for pathological stain transformation using GAN , 2021, 2021 29th Iranian Conference on Electrical Engineering (ICEE).

[23]  Eyke Hüllermeier,et al.  Ranking Structured Objects with Graph Neural Networks , 2021, DS.

[24]  Ye Duan,et al.  Novel Transfer Learning Approach for Medical Imaging with Limited Labeled Data , 2021, Cancers.

[25]  W. Paul Segars,et al.  Generation of annotated multimodal ground truth datasets for abdominal medical image registration , 2020, International Journal of Computer Assisted Radiology and Surgery.

[26]  S. Balachandar,et al.  Machine learning for physics-informed generation of dispersed multiphase flow using generative adversarial networks , 2020, Theoretical and Computational Fluid Dynamics.

[27]  T. Tommasi,et al.  Bridging the gap between Natural and Medical Images through Deep Colorization , 2020, 2020 25th International Conference on Pattern Recognition (ICPR).

[28]  Frederik Hvilshøj,et al.  Backpropagating through Fréchet Inception Distance , 2021 .

[29]  Ricardo João Cruz Correia,et al.  GANs for Tabular Healthcare Data Generation: A Review on Utility and Privacy , 2021, IFIP Working Conference on Database Semantics.

[30]  Health Informatics: A Computational Perspective in Healthcare , 2021, Health Informatics.

[31]  K. Suganthi,et al.  Review of Medical Image Synthesis using GAN Techniques , 2021, ITM Web of Conferences.

[32]  Khalid Raza,et al.  Medical Image Generation Using Generative Adversarial Networks: A Review , 2021, Health Informatics.

[33]  M. Abdel-Aty,et al.  Crash data augmentation using variational autoencoder. , 2020, Accident; analysis and prevention.

[34]  Yang Lei,et al.  A review on medical imaging synthesis using deep learning and its clinical applications , 2020, Journal of applied clinical medical physics.

[35]  Bakhodir Muminov,et al.  Localization and Classification of Myocardial Infarction Based on Artificial Neural Network , 2020, 2020 Information Communication Technologies Conference (ICTC).

[36]  Alex Noel Joseph Raj,et al.  RDA-UNET-WGAN: An Accurate Breast Ultrasound Lesion Segmentation Using Wasserstein Generative Adversarial Networks , 2020, Arabian Journal for Science and Engineering.

[37]  Yang Lei,et al.  Deep attentional GAN-based high-resolution ultrasound imaging , 2020, Medical Imaging.

[38]  Bin Yang,et al.  MedGAN: Medical Image Translation using GANs , 2018, Comput. Medical Imaging Graph..

[39]  Yu Yao,et al.  Interactive Translation in Echocardiography Training System With Enhanced Cycle-GAN , 2020, IEEE Access.

[40]  P. Abolmaesumi,et al.  GAN-enhanced Conditional Echocardiogram Generation , 2019, ArXiv.

[41]  Marius Erdt,et al.  Synthesis of Medical Images Using GANs , 2019, UNSURE/CLIP@MICCAI.

[42]  Shiyuan Wang,et al.  A Real-Time Medical Ultrasound Simulator Based on a Generative Adversarial Network Model , 2019, 2019 IEEE International Conference on Image Processing (ICIP).

[43]  Taeg Keun Whangbo,et al.  Fully Automatic Stroke Symptom Detection Method Based on Facial Features and Moving Hand Differences , 2019, 2019 International Symposium on Multimedia and Communication Technology (ISMAC).

[44]  Rafal Scherer,et al.  HEMIGEN: Human Embryo Image Generator Based on Generative Adversarial Networks , 2019, Sensors.

[45]  Michael S. Bernstein,et al.  HYPE: Human eYe Perceptual Evaluation of Generative Models , 2019, DGS@ICLR.

[46]  Sjoerd van Steenkiste,et al.  FVD: A new Metric for Video Generation , 2019, DGS@ICLR.

[47]  Ali Borji,et al.  Pros and Cons of GAN Evaluation Measures , 2018, Comput. Vis. Image Underst..

[48]  Aykut Erdem,et al.  Image Synthesis in Multi-Contrast MRI With Conditional Generative Adversarial Networks , 2018, IEEE Transactions on Medical Imaging.

[49]  James Y. Zou,et al.  EchoNet-Dynamic: a Large New Cardiac Motion Video Data Resource for Medical Machine Learning , 2019 .

[50]  Hitoshi Kiya,et al.  Checkerboard artifacts free convolutional neural networks , 2019, APSIPA Transactions on Signal and Information Processing.

[51]  Hayit Greenspan,et al.  GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification , 2018, Neurocomputing.

[52]  Alexei A. Efros,et al.  The Unreasonable Effectiveness of Deep Features as a Perceptual Metric , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[53]  Mario Lucic,et al.  Are GANs Created Equal? A Large-Scale Study , 2017, NeurIPS.

[54]  Sepp Hochreiter,et al.  GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium , 2017, NIPS.

[55]  V. Bello,et al.  Speckle-Tracking Imaging, Principles and Clinical Applications: A Review for Clinical Cardiologists , 2016 .

[56]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[57]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.