An automatic liver fibrosis qualitative analysis method based on hyperspectral images

JianSheng Wang; Mei Zhou II; Qingli Li III; Li Sun IV; Song Qiu V

doi:10.1117/12.2502980

9 August 2018 An automatic liver fibrosis qualitative analysis method based on hyperspectral images

JianSheng Wang, Mei Zhou II, Qingli Li III, Li Sun IV, Song Qiu V

Proceedings Volume 10806, Tenth International Conference on Digital Image Processing (ICDIP 2018); 1080634 (2018) https://doi.org/10.1117/12.2502980
Event: Tenth International Conference on Digital Image Processing (ICDIP 2018), 2018, Shanghai, China

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.

Citation Download Citation

JianSheng Wang, Mei Zhou II, Qingli Li III, Li Sun IV, and Song Qiu V "An automatic liver fibrosis qualitative analysis method based on hyperspectral images", Proc. SPIE 10806, Tenth International Conference on Digital Image Processing (ICDIP 2018), 1080634 (9 August 2018); https://doi.org/10.1117/12.2502980

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available