The glowworm swarm optimization for training the radial basis function network in ultrasonic supraspinatus image classification

研究成果: Article同行評審

5 引文 斯高帕斯(Scopus)

摘要

This article proposes a study on applying the glowworm swarm optimization for training the radial basis function network for classifying the different supraspinatus disease groups that are normal, tendon inflammation, calcific tendonitis and tendon tears of the ultrasound supraspinatus images. In conventional diagnosis, the physicians observe the micro/macro structures of images to judge the severity of rotator cuff disease; however, it is not reliable because the accuracy of visual observation depends on the expertise of physicians. Four texture analysis methods-gray-level co-occurrence matrix, texture spectrum, fractal dimension and texture feature coding method-are used to extract features of tissue characteristic of supraspinatus. The F -score measurement are used to select powerful features that are generated from the four texture analysis methods for comparison in the training stage, meanwhile, the proposed trained radial basis function network is used to discriminate test images into one of the four disease groups in the classification stage. The percentage of correct classification was more than 95.0%, and experimental results showed that the proposed method performs very well for the classification of ultrasonic supraspinatus images.

原文English
頁(從 - 到)2724-2727
頁數4
期刊Advanced Science Letters
19
發行號9
DOIs
出版狀態Published - 2013 9月

All Science Journal Classification (ASJC) codes

  • 一般電腦科學
  • 健康(社會科學)
  • 一般數學
  • 教育
  • 一般環境科學
  • 一般工程
  • 一般能源

指紋

深入研究「The glowworm swarm optimization for training the radial basis function network in ultrasonic supraspinatus image classification」主題。共同形成了獨特的指紋。

引用此