Share Email Print

Proceedings Paper

An automatic liver fibrosis qualitative analysis method based on hyperspectral images
Author(s): JianSheng Wang; Mei Zhou II; Qingli Li III; Li Sun IV; Song Qiu V
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Serious liver fibrosis will develop into liver tumor. Therefore, prevention and early treatment of hepatocellular carcinoma are the focuses of the medical community. To automatically identify and analyze the degree of liver fibrosis, a more intuitive and convenient approach is proposed to segmentation of liver pathological slice images. This paper aims to use hyperspectral image processing technology to analyze the pathological sections of liver tissue cells. The method uses the spectral math for image preprocessing, and utilizes the superior classification ability of neural net (NN) and support vector machines (SVM) to identify the pathological images of liver tissue. On this basis, Majority/Minority Analysis (MMA) is as the post classified tool to weaken small plaques interference. At last the original image and the classification results are synthesized by RGB bands, and good analysis results can be obtained. The experimental results show that the presented method has great practical value in clinical diagnosis.

Paper Details

Date Published: 9 August 2018
PDF: 8 pages
Proc. SPIE 10806, Tenth International Conference on Digital Image Processing (ICDIP 2018), 1080634 (9 August 2018); doi: 10.1117/12.2502980
Show Author Affiliations
JianSheng Wang, East China Normal Univ. (China)
Mei Zhou II, East China Normal Univ. (China)
Qingli Li III, East China Normal Univ. (China)
Li Sun IV, East China Normal Univ. (China)
Song Qiu V, East China Normal University (China)

Published in SPIE Proceedings Vol. 10806:
Tenth International Conference on Digital Image Processing (ICDIP 2018)
Xudong Jiang; Jenq-Neng Hwang, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?