Diagnosing of some hepatic lesions from light microscope images based on morphological and texture features

Zamen Fadhel Jabr, Mohammed abd Alabbas Hasan

Abstract


One of the common problems observed in medicines is hepatotoxicity as liver play mainly role in metabolizes the herbal medicines. Although, the acceptance of herbal medicines is growing nowadays still there is an absence of knowledge about their toxicological properties and the right use being a hepatotoxic.This paper presents method to detect and diagnoses liver lesions in four types: necrotic cells, fatty degenerative cells, hepatocellular hypertrophic cells and congested cells using image processing techniques. The method is proposed to perform two tasks the first is conclude whether the liver image is normal or abnormal the second if abnormal state is detected then diagnosis lesions type must performs. The method progresses in many steps are preprocessing, features extraction, classification and lesion diagnosing. Grey level co-occurrence Matrix (GLCM) technique is utilize to concentrate features to distinguish between normal and abnormal case using neural network classifier if abnormal state is detected the method feedback with colour image to analyse cells shape and image intensity colour to determine which type of diseases founded in image based on statistical and morphological features of cells. The method tested on 107 images it is got on the accuracy 100% in classification and 95% in diagnosing.

Keywords


GLCM; Hepatic lesions diagnosing; Light microscope image; Morphological cells features; Neural network

Full Text:

PDF


DOI: http://doi.org/10.11591/ijeecs.v18.i2.pp995-1003

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Indonesian Journal of Electrical Engineering and Computer Science (IJEECS)
p-ISSN: 2502-4752, e-ISSN: 2502-4760
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).

shopify stats IJEECS visitor statistics