Gingivitis identification via multichannel gray‐level co‐occurrence matrix and particle swarm optimization neural network. Issue 2 (6th December 2019)

• Record Type: Journal Article
• Authors: Li, Wen; Jiang, Xianwei; Sun, Weibin; Wang, Shui‐Hua; Liu, Chao; Zhang, Xuan; Zhang, Yu‐Dong; Zhou, Wei; Miao, Leiying
• Is Part Of: International journal of imaging systems and technology. Volume 30:Issue 2(2020)
• Page Start: 401
• Page End: 411
• Publication Date: 2019-12-06
• Subjects: artificial neural network -- gingivitis identification -- multichannel gray‐level co‐occurrence matrix -- particle swarm optimization -- pattern recognition; Imaging systems -- Periodicals; Image processing -- Periodicals; 621.367
• DOI: 10.1002/ima.22385
• Languages: English
• ISSNs: 0899-9457

Abstract

Abstract: The oral maintenance of patients with periodontal disease mainly depends on clinical examination. However, insufficient number of medical workers cannot carry out detailed oral health education for a large number of patients within limited time and provide these patients with proper and effective oral health nursing methods. In this research, our study put forward a new Artificial Intelligence (AI) based method to diagnose chronic gingivitis, which is based on multichannel gray‐levelco‐occurrence matrix (MGLCM) and particle swarm optimization neural network(PSONN). Meanwhile, different training algorithms were used as comparison groups. The data set contains 800 images: 400 chronic gingivitis images and 400 healthy gingiva images. The results certify that the specificity, sensitivity, precision, accuracy and F1 Score of MGLCM (PSONN as a classifier) method is 78.17%, 78.23%, 78.24%, 78.20%and 78.17%, respectively. The association of MGLCM and PSONN is more accurate and efficient than approaches: NBC, WN+SVM, ELM and CLAHE+ELM.