Search or ask a question
Pricing
Login
Sign up
Home
Notebook
Profile
Citation booster
Literature Review
Copilot
Citation generator
Paraphraser
AI Detector
Chrome Extension
Talk with us
Use on ChatGPT
All figures (6)
Fig. 2 Illustration of two saliency maps derived from the same FA image. (a) The example FA image. (b) A saliency map based on intensity only; (c) A saliency map based on intensity enhanced by compactness measure.
Table 1 The performance of the proposed framework on detecting large focal and punctate focal leakge.
Fig. 1 Illustration of three types of leakage: (a) Large focal leakage. (b) Punctate focal leakage. (c) Vessel segment leakage.
Fig. 3 Overview of the main steps taken by our algorithm for detecting three type of leakages. From top to bottom: large focal leakage, punctate leakage, and vessel segment leakage. (a) Example FA images. (b) Saliency maps of (a). The warmer color indicates the more salient regions, and the cooler color shows the less salient regions. (c) Binary images of (b). (d) Vessel segmentation results. (e) The detected leakage regions.
Fig. 4 Detection of three types of leakage by our automated method and a human observer. (a) Input FA images with leakage. (b) Saliency maps of (a), most of the vessels and leaking regions have been highlighted with ‘warmer’ color. (c) Manual annotations. (d)Automated detection by our method. In the case of vessel segment leakage detection, the leaking vessels are assigned as red, while normal vessels as green.
Table 2 Quantitative analysis of the performance of the proposed method on vessel segments leakage detection and manual grading of the leakage vessel.
Journal Article
•
DOI
•
A compactness based saliency approach for leakages detection in fluorescein angiogram
[...]
Yitian Zhao
1
,
Pan Su
2
,
Jian Yang
1
,
Yifan Zhao
3
,
Yalin Zheng
4
,
Yongtian Wang
1
- Show less
+2 more
•
Institutions (4)
Beijing Institute of Technology
1
,
North China Electric Power University
2
,
Cranfield University
3
,
University of Liverpool
4
01 Dec 2017
-
International Journal of Machine Learning and Cybernetics