Deep Angiogram: Trivializing Retinal Vessel Segmentation

被引:0
作者
Hu, Dewei [1 ]
Yao, Xing [2 ]
Wang, Jiacheng [2 ]
Tao, Yuankai K. [3 ]
Oguz, Ipek [2 ]
机构
[1] Vanderbilt Univ, Dept Elect & Comp Engn, Nashville, TN USA
[2] Vanderbilt Univ, Dept Comp Sci, Nashville, TN 37235 USA
[3] Vanderbilt Univ, Dept Biomed Engn, Nashville, TN USA
来源
MEDICAL IMAGING 2023 | 2023年 / 12464卷
关键词
deep learning; vessel enhancement; vessel segmentation; domain generalization; BLOOD-VESSELS; IMAGES;
D O I
10.1117/12.2654214
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Among the research efforts to segment the retinal vasculature from fundus images, deep learning models consistently achieve superior performance. However, this data-driven approach is very sensitive to domain shifts. For fundus images, such data distribution changes can easily be caused by variations in illumination conditions as well as the presence of disease-related features such as hemorrhages and drusen. Since the source domain may not include all possible types of pathological cases, a model that can robustly recognize vessels on unseen domains is desirable but remains elusive, despite many proposed segmentation networks of ever-increasing complexity. In this work, we propose a contrastive variational auto-encoder that can filter out irrelevant features and synthesize a latent image, named deep angiogram, representing only the retinal vessels. Then segmentation can be readily accomplished by thresholding the deep angiogram. The generalizability of the synthetic network is improved by the contrastive loss that makes the model less sensitive to variations of image contrast and noisy features. Compared to baseline deep segmentation networks, our model achieves higher segmentation performance via simple thresholding. Our experiments show that the model can generate stable angiograms on different target domains, providing excellent visualization of vessels and a non-invasive, safe alternative to fluorescein angiography.
引用
收藏
页数:5
相关论文
共 18 条
[1]   Robust Vessel Segmentation in Fundus Images [J].
Budai, A. ;
Bock, R. ;
Maier, A. ;
Hornegger, J. ;
Michelson, G. .
INTERNATIONAL JOURNAL OF BIOMEDICAL IMAGING, 2013, 2013 (2013)
[2]   Retinal Vessel Segmentation Using Deep Learning: A Review [J].
Chen, Chunhui ;
Chuah, Joon Huang ;
Ali, Raza ;
Wang, Yizhou .
IEEE ACCESS, 2021, 9 :111985-112004
[3]   Enhancement of blood vessels in digital fundus photographs via the application of multiscale line operators [J].
Farnell, D. J. J. ;
Hatfield, F. N. ;
Knox, P. ;
Reakes, M. ;
Spencer, S. ;
Parry, D. ;
Harding, S. P. .
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS, 2008, 345 (07) :748-765
[4]   Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response [J].
Hoover, A ;
Kouznetsova, V ;
Goldbaum, M .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2000, 19 (03) :203-210
[5]  
Hu D., 2021, MED IMAGING DEEP LEA
[6]   LIFE: A Generalizable Autodidactic Pipeline for 3D OCT-A Vessel Segmentation [J].
Hu, Dewei ;
Cui, Can ;
Li, Hao ;
Larson, Kathleen E. ;
Tao, Yuankai K. ;
Oguz, Ipek .
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2021, PT I, 2021, 12901 :514-524
[7]   Deep learning algorithms for detection of diabetic retinopathy in retinal fundus photographs: A systematic review and meta-analysis [J].
Islam, Md Mohaimenul ;
Yang, Hsuan-Chia ;
Poly, Tahmina Nasrin ;
Jian, Wen-Shan ;
Li, Yu-Chuan .
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2020, 191
[8]  
Jiang Jue, 2020, Med Image Comput Comput Assist Interv, V12262, P347, DOI 10.1007/978-3-030-59713-9_34
[9]  
Li D, 2018, AAAI CONF ARTIF INTE, P3490
[10]   Applications of deep learning in fundus images: A review [J].
Li, Tao ;
Bo, Wang ;
Hu, Chunyu ;
Kang, Hong ;
Liu, Hanruo ;
Wang, Kai ;
Fu, Huazhu .
MEDICAL IMAGE ANALYSIS, 2021, 69