Evaluating Synthetic Medical Images Using Artificial Intelligence with the GAN Algorithm
Author:
Abdusalomov Akmalbek Bobomirzaevich1ORCID, Nasimov Rashid2, Nasimova Nigorakhon2, Muminov Bahodir2, Whangbo Taeg Keun1
Affiliation:
1. Department of Computer Engineering, Gachon University, Sujeong-Gu, Seongnam-Si 461-701, Gyeonggi-Do, Republic of Korea 2. Department of Artificial Intelligence, Tashkent State University of Economics, Tashkent 100066, Uzbekistan
Abstract
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.
Funder
GRRC Program of Gyeonggi Province
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference57 articles.
1. Nasimova, N., Muminov, B., Nasimov, R., Abdurashidova, K., and Abdullaev, M. (2021, January 3–5). November. Comparative Analysis of the Results of Algorithms for Dilated Cardiomyopathy and Hypertrophic Cardiomyopathy Using Deep Learning. Proceedings of the 2021 International Conference on Information Science and Communications Technologies (ICISCT), Tashkent, Uzbekistan. 2. Muminov, B., Nasimov, R., Mirzahalilov, S., Sayfullaeva, N., and Gadoyboyeva, N. (2020, January 29–31). Localization and Classification of Myocardial Infarction Based on Artificial Neural Network. Proceedings of the 2020 Information Communication Technologies Conference (ICTC), Nanjing, China. 3. He, X., Lei, Y., Liu, Y., Tian, Z., Wang, T., Curran, W.J., Liu, T., and Yang, X. (2020, January 16). Deep attentional GAN-based high-resolution ultrasound imaging. Proceedings of the SPIE 11319, Medical Imaging 2020: Ultrasonic Imaging and Tomography, 113190B, Bellingham, WA, USA. 4. Peng, B., Huang, X., Wang, S., and Jiang, J. (2019, January 22–25). A Real-Time Medical Ultrasound Simulator Based on a Generative Adversarial Network Model. Proceedings of the 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan. 5. Interactive Translation in Echocardiography Training System with Enhanced Cycle-GAN;Teng;IEEE Access,2020
Cited by
17 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|