Liver diseases diagnosis using fuzzy logic

Abstract EN

In this paper, a new system for liver diseases diagnosis has suggested based on using fuzzy logic by analyzing histological liver images.

The suggested system has performed in four steps: the first step is a pre-processing step where the image has enhanced to improve its quality; the goal of image improving is to obtain an image with a high contrast and visual details.

The second step is for image analysis by using wavelet transform to decompose and analysis the images into sub-bands.

The third step is to extract best features, which will be use the results from the wavelet transform to obtain most important features.

The fourth stage is by using the fuzzy logic system to diagnose the livers diseases types (Auto immune, Non-autoimmune, Alcoholic and Hepatitis A, B, C, D and E).

The performance of the suggested system has tested and evaluated using 86 histological images and the experimental results confirmed that the proposed system gave 98% accuracy.