Self-Supervised Bulk Motion Artifact Removal in Optical Coherence Tomography Angiography

被引:1
作者
Ren, Jiaxiang [1 ]
Park, Kicheon [2 ]
Pan, Yingtian [2 ]
Ling, Haibin [1 ]
机构
[1] SUNY Stony Brook, Dept Comp Sci, Stony Brook, NY 11794 USA
[2] SUNY Stony Brook, Dept Biomed Engn, Stony Brook, NY 11794 USA
来源
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) | 2022年
基金
美国国家科学基金会;
关键词
QUANTIFICATION; TRACKING;
D O I
10.1109/CVPR52688.2022.01996
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Optical coherence tomography angiography (OCTA) is an important imaging modality in many bioengineering tasks. The image quality of OCTA, however, is often degraded by Bulk Motion Artifacts (BMA), which are due to micromotion of subjects and typically appear as bright stripes surrounded by blurred areas. State-of-the-art methods usually treat BMA removal as a learning-based image inpainting problem, but require numerous training samples with nontrivial annotation. In addition, these methods discard the rich structural and appearance information carried in the BMA stripe region. To address these issues, in this paper we propose a self-supervised content-aware BMA removal model. First, the gradient-based structural information and appearance feature are extracted from the BMA area and injected into the model to capture more connectivity. Second, with easily collected defective masks, the model is trained in a self-supervised manner, in which only the clear areas are used for training while the BMA areas for inference. With the structural information and appearance feature from noisy image as references, our model can remove larger BMA and produce better visualizing result. In addition, only 2D images with defective masks are involved, hence improving the efficiency of our method. Experiments on OCTA of mouse cortex demonstrate that our model can remove most BMA with extremely large sizes and inconsistent intensities while previous methods fail.
引用
收藏
页码:20585 / 20593
页数:9
相关论文
共 30 条
[1]  
[Anonymous], 2018, ICML, DOI DOI 10.1038/S41586-018-0485-4
[2]  
[Anonymous], 2008, Advances in Neural Information Processing Ssystems
[3]  
Broaddus Coleman, 2020, ISBI
[4]   Evaluation of artifact reduction in optical coherence tomography angiography with real-time tracking and motion correction technology [J].
Camino, Acner ;
Zhang, Miao ;
Gao, Simon S. ;
Hwang, Thomas S. ;
Sharma, Utkarsh ;
Wilson, David J. ;
Huang, David ;
Jia, Yali .
BIOMEDICAL OPTICS EXPRESS, 2016, 7 (10) :3905-3915
[5]   Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration [J].
Chen, Yunjin ;
Pock, Thomas .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (06) :1256-1272
[6]   Image denoising by sparse 3-D transform-domain collaborative filtering [J].
Dabov, Kostadin ;
Foi, Alessandro ;
Katkovnik, Vladimir ;
Egiazarian, Karen .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2007, 16 (08) :2080-2095
[7]   A Deep Learning Approach to Denoise Optical Coherence Tomography Images of the Optic Nerve Head [J].
Devalla, Sripad Krishna ;
Subramanian, Giridhar ;
Tan Hung Pham ;
Wang, Xiaofei ;
Perera, Shamira ;
Tun, Tin A. ;
Aung, Tin ;
Schmetterer, Leopold ;
Thiery, Alexandre H. ;
Girard, Michael J. A. .
SCIENTIFIC REPORTS, 2019, 9 (1)
[8]  
Fadnavis Shreyas, 2020, NEURIPS
[9]  
Frangi AF, 1998, LECT NOTES COMPUT SC, V1496, P130, DOI 10.1007/BFb0056195
[10]   OPTICAL COHERENCE TOMOGRAPHY [J].
HUANG, D ;
SWANSON, EA ;
LIN, CP ;
SCHUMAN, JS ;
STINSON, WG ;
CHANG, W ;
HEE, MR ;
FLOTTE, T ;
GREGORY, K ;
PULIAFITO, CA ;
FUJIMOTO, JG .
SCIENCE, 1991, 254 (5035) :1178-1181