Deep learning in medical image super resolution: a review

被引：21

作者：

Yang, Hujun ^{[1
]}

Wang, Zhongyang ^{[2
,3
]}

Liu, Xinyao ^{[1
]}

Li, Chuangang ^{[1
]}

Xin, Junchang ^{[2
,3
]}

Wang, Zhiqiong ^{[1
]}

机构：

[1] Northeastern Univ, Coll Med & Biol Informat Engn, Shenyang 110169, Peoples R China

[2] Northeastern Univ, Sch Comp Sci & Engn, Shenyang 110169, Peoples R China

[3] Northeastern Univ, Key Lab Big Data Management & Analyt, Shenyang 110169, Peoples R China

来源：

APPLIED INTELLIGENCE | 2023年 / 53卷 / 18期

基金：

中国国家自然科学基金;

关键词：

Super-resolution; Medical image; Deep learning; Assessment metrics; Review; MULTI-CONTRAST SUPERRESOLUTION; QUALITY ASSESSMENT; MRI; NETWORK; SINGLE; ATTENTION; CT;

D O I：

10.1007/s10489-023-04566-9

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Super-resolution (SR) reconstruction is a hot topic in medical image processing. SR implies reconstructing corresponding high-resolution (HR) images from observed low-resolution (LR) images or image sequences. In recent years, significant breakthroughs in SR based on deep learning have been made, and many advanced results have been achieved. However, there is a lack of review literature that summarizes the field's current state and provides an outlook on future developments. Therefore, we provide a comprehensive summary of the literature on medical image SR (MedSR) based on deep learning since 2018 in five aspects: (1) The SR problem of medical images is described, and the methods of image degradation are summarized. (2) We divide the existing studies into three categories: two-dimensional image SR (2DISR), three-dimensional image SR (3DISR), and video SR (VSR). Each category is subdivided. We analyze the network structure and method characteristics of typical methods. (3) Existing SR reconstruction quality evaluation metrics are presented in detail. (4) The application of MedSR methods based on deep learning is discussed. (5) We discuss the challenges of this phase and point out valuable research directions.

引用

页码：20891 / 20916

页数：26

共 148 条

[11] Efficient and Accurate MRI Super-Resolution Using a Generative Adversarial Network and 3D Multi-level Densely Connected Network
Chen, Yuhua
Shi, Feng
Christodoulou, Anthony G.
Xie, Yibin
Zhou, Zhengwei
Li, Debiao
[J]. MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2018, PT I, 2018, 11070 : 91 - 99
[12] The ratio of length at first maturity to maximum length across marine and freshwater fishes
Chen, Zhaomin
Bigman, Jennifer
Xian, Weiwei
Liang, Cui
Chu, Elaine
Pauly, Daniel
[J]. JOURNAL OF FISH BIOLOGY, 2022, 101 (02) : 400 - 407
[13] Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation
Chu, Mengyu
Xie, You
Mayer, Jonas
Leal-Taix, Laura
Thuerey, Nils
[J]. ACM TRANSACTIONS ON GRAPHICS, 2020, 39 (04):
[14] Chu XX, 2021, ADV NEUR IN
[15] Chudasama Vishal, 2021, IEEE Transactions on Biometrics, Behavior, and Identity Science, V3, P166, DOI 10.1109/TBIOM.2021.3059196
[16] Dai Dengxin, 2016, IEEE WINTER C APPL C
[17] Diffusion-weighted and spectroscopic MRI super-resolution using sparse representations
Deka, Bhabesh
Datta, Sumit
Mullah, Helal Uddin
Hazarika, Suman
[J]. BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2020, 60
[18] Deep Residual Dense U-Net for Resolution Enhancement in Accelerated MRI Acquisition
Ding, Pak Lun Kevin
Li, Zhiqiang
Zho, Yuxiang
Li, Baoxin
[J]. MEDICAL IMAGING 2019: IMAGE PROCESSING, 2019, 10949
[19] Learning a Deep Convolutional Network for Image Super-Resolution
Dong, Chao
Loy, Chen Change
He, Kaiming
Tang, Xiaoou
[J]. COMPUTER VISION - ECCV 2014, PT IV, 2014, 8692 : 184 - 199
[20] Super-resolution reconstruction of single anisotropic 3D MR images using residual convolutional neural network
Du, Jinglong
He, Zhongshi
Wang, Lulu
Gholipour, Ali
Zhou, Zexun
Chen, Dingding
Jia, Yuanyuan
[J]. NEUROCOMPUTING, 2020, 392 : 209 - 220

← 1 2 3 4 5 6 7 8 9 10 →