Detection of bone fracture based on machine learning techniques

Abstract

Computers have been shown to be valuable in every facet of human life, from banking and online shopping to communication, education, research and development, and even medical. To help doctors and hospitals better care for their patients, a lot of innovative technical resources have been developed. Because the typical scanner for X-rays produces a fuzzy picture of the bone component in issue, surgeons risk making an inaccurate diagnosis of bone fractures when they utilize it. Various stages such as pre-processing, edge detection, feature extraction and machine learning classifications, constitute the backbone of this system, with the end goal of making surgeons' lives easier. Among the various fields that benefit from machine learning algorithms nowadays are seismology, remote sensing, and medicine; this program is only one example. As a side note, several machine learning algorithms, such as Naïve Bayes, Decision Tree, Nearest Neighbors, Random Forest, and SVM, have been used specifically for handling bone fracture detection on a dataset with 270 x-ray images. Accuracy measures for the various algorithms employed in the study range from 0.64 to 0.92, with values obtained for Naïve Bayes, Decision Tree, Nearest Neighbors, Random Forest, and SVM. Statistically, the accuracy for SVM was found to be the highest in this research, which is higher than most of the reviewed research.

Ähnliche Arbeiten