Osteoarthritis Disease Detection System using Self Organizing Maps Method based on Ossa Manus X-Ray

TL;DR

This paper presents a system using Self Organizing Maps to detect osteoarthritis in Ossa Manus X-ray images, achieving over 92% accuracy in classification.

Contribution

It introduces a novel application of Self Organizing Maps for osteoarthritis detection in X-ray images with a detailed image processing pipeline.

Findings

Training accuracy of 96.42%

Testing accuracy of 92.8%

Effective detection of osteoarthritis in X-ray images

Abstract

Osteoarthritis is a disease found in the world, including in Indonesia. The purpose of this study was to detect the disease Osteoarthritis using Self Organizing mapping (SOM), and to know the procedure of artificial intelligence on the methods of Self Organizing Mapping (SOM). In this system, there are several stages to preserve to detect disease Osteoarthritis using Self Organizing maps is the result of photographic images rontgen Ossa Manus normal and sick with the resolution (150 x 200 pixels) do the repair phase contrast, the Gray scale, thresholding process, Histogram of process , and do the last process, where the process of doing training (Training) and testing on images that have kept the shape data (.text). the conclusion is the result of testing by using a data image, where 42 of data have 12 Normal image data and image data 30 sick. On the results of the process of training data there are 8 X-ray image revealed normal right and 19 data x-ray image of pain expressed is correct. Then the accuracy on the process of training was 96.42%, and in the process of testing normal true image 4 obtained revealed Normal, 9 data pain stated true pain and 1 data imagery hurts stated incorrectly, then the accuracy gained from the results of testing are 92,8%.