19 February 2018 An enhanced narrow-band imaging method for the microvessel detection
Author Affiliations +
Proceedings Volume 10607, MIPPR 2017: Multispectral Image Acquisition, Processing, and Analysis; 106070T (2018) https://doi.org/10.1117/12.2287765
Event: Tenth International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR2017), 2017, Xiangyang, China
Abstract
A medical endoscope system combined with the narrow-band imaging (NBI), has been shown to be a superior diagnostic tool for early cancer detection. The NBI can reveal the morphologic changes of microvessels in the superficial cancer. In order to improve the conspicuousness of microvessel texture, we propose an enhanced NBI method to improve the conspicuousness of endoscopic images. To obtain the more conspicuous narrow-band images, we use the edge operator to extract the edge information of the narrow-band blue and green images, and give a weight to the extracted edges. Then, the weighted edges are fused with the narrow-band blue and green images. Finally, the displayed endoscopic images are reconstructed with the enhanced narrow-band images. In addition, we evaluate the performance of enhanced narrow-band images with different edge operators. Experimental results indicate that the Sobel and Canny operators achieve the best performance of all. Compared with traditional NBI method of Olympus company, our proposed method has more conspicuous texture of microvessel.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Feng Yu, Feng Yu, Enmin Song, Enmin Song, Hong Liu, Hong Liu, Youming Wan, Youming Wan, Jun Zhu, Jun Zhu, Chih-Cheng Hung, Chih-Cheng Hung, } "An enhanced narrow-band imaging method for the microvessel detection", Proc. SPIE 10607, MIPPR 2017: Multispectral Image Acquisition, Processing, and Analysis, 106070T (19 February 2018); doi: 10.1117/12.2287765; https://doi.org/10.1117/12.2287765
PROCEEDINGS
8 PAGES


SHARE
Back to Top