Self Organization Map based Texture Feature Extraction for Efficient Medical Image Categorization

TL;DR

This paper introduces a novel texture feature extraction method using self-organizing maps (SOM) combined with region partitioning and Fisherfaces for improved medical image categorization accuracy.

Contribution

It proposes an enhanced feature extraction approach based on SOM and region partitioning, specifically tailored for medical image analysis.

Findings

High accuracy in medical image categorization demonstrated

Effective texture feature extraction method validated on MIAS dataset

Improved visualization and exploration of image data properties

Abstract

Texture is one of the most important properties of visual surface that helps in discriminating one object from another or an object from background. The self-organizing map (SOM) is an excellent tool in exploratory phase of data mining. It projects its input space on prototypes of a low-dimensional regular grid that can be effectively utilized to visualize and explore properties of the data. This paper proposes an enhancement extraction method for accurate extracting features for efficient image representation it based on SOM neural network. In this approach, we apply three different partitioning approaches as a region of interested (ROI) selection methods for extracting different accurate textural features from medical image as a primary step of our extraction method. Fisherfaces feature selection is used, for selecting discriminated features form extracted textural features. Experimental result showed the high accuracy of medical image categorization with our proposed extraction method. Experiments held on Mammographic Image Analysis Society (MIAS) dataset.