Survey: application and analysis of generative adversarial networks in medical images

被引：2

作者：

Heng, Yang ^{[1
]}

Ma, Yinghua ^{[1
]}

Khan, Fiaz Gul ^{[1
]}

Khan, Ahmad ^{[1
]}

Ali, Farman ^{[2
]}

Alzubi, Ahmad Ali ^{[3
]}

Hui, Zeng ^{[1
]}

机构：

[1] COMSATS Univ Islamabad, Comp Sci, Univ Rd,Abbottabad Campus, Abbottabad 22044, Khyber Pakhtun, Pakistan

[2] Sungkyunkwan Univ, Coll Comp & Informat, Sch Convergence, Dept Appl AI, Seoul 03063, South Korea

[3] King Saud Univ, Community Coll, Dept Comp Sci, Riyadh, Saudi Arabia

来源：

ARTIFICIAL INTELLIGENCE REVIEW | 2024年 / 58卷 / 02期

关键词：

Generative adversarial networks; Deep learning; Medical images; GAN survey; Medical image analysis; NEURAL-NETWORKS; BREAST-CANCER; GAN; SEGMENTATION; EFFICIENT; REDUCTION;

D O I：

10.1007/s10462-024-10992-z

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Generative Adversarial Networks (GANs) have shown promising prospects and achieved significant results in medical image analysis tasks. This article provides a comprehensive review of recent research on GANs and their variants in medical applications, including tasks such as image synthesis, segmentation, classification, detection, denoising, reconstruction, fusion, registration, and prediction. We summarize and analyze the reviewed literature, with a focus on model framework design,dataset sources, and performance evaluation. Our research findings are presented in the form of tables. In the end,article discusses open challenges and directions for future research.

引用

页数：81

共 213 条

[1] Data augmentation for skin lesion using self-attention based progressive generative adversarial network [J].