Journal
ENTROPY
Volume 25, Issue 6, Pages -Publisher
MDPI
DOI: 10.3390/e25060951
Keywords
full-field optical angiography; nonsubsampled contourlet transform; image fusion; contrast spatial frequency; sparse representation
Categories
Ask authors/readers for more resources
Full-field optical angiography (FFOA) has the potential for clinical applications in disease prevention and diagnosis. However, existing FFOA imaging techniques can only acquire blood flow information within a limited depth of focus, resulting in partially unclear images. To address this issue, a novel FFOA image fusion method based on the nonsubsampled contourlet transform and contrast spatial frequency is proposed, which significantly expands the range of focus and outperforms state-of-the-art methods.
Full-field optical angiography (FFOA) has considerable potential for clinical applications in the prevention and diagnosis of various diseases. However, owing to the limited depth of focus attainable using optical lenses, only information about blood flow in the plane within the depth of field can be acquired using existing FFOA imaging techniques, resulting in partially unclear images. To produce fully focused FFOA images, an FFOA image fusion method based on the nonsubsampled contourlet transform and contrast spatial frequency is proposed. Firstly, an imaging system is constructed, and the FFOA images are acquired by intensity-fluctuation modulation effect. Secondly, we decompose the source images into low-pass and bandpass images by performing nonsubsampled contourlet transform. A sparse representation-based rule is introduced to fuse the lowpass images to effectively retain the useful energy information. Meanwhile, a contrast spatial frequency rule is proposed to fuse bandpass images, which considers the neighborhood correlation and gradient relationships of pixels. Finally, the fully focused image is produced by reconstruction. The proposed method significantly expands the range of focus of optical angiography and can be effectively extended to public multi-focused datasets. Experimental results confirm that the proposed method outperformed some state-of-the-art methods in both qualitative and quantitative evaluations.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available