首页|Universiti Malaya Reports Findings in Root Resorption (Application of deep learn ing and feature selection technique on external root resorption identification o n CBCT images)
Universiti Malaya Reports Findings in Root Resorption (Application of deep learn ing and feature selection technique on external root resorption identification o n CBCT images)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Dental Diseases and Co nditions - Root Resorption is the subject of a report. According to news reporti ng from Kuala Lumpur, Malaysia, by NewsRx journalists, research stated, "Artific ial intelligence has been proven to improve the identification of various maxill ofacial lesions. The aim of the current study is two-fold: to assess the perform ance of four deep learning models (DLM) in external root resorption (ERR) identi fication and to assess the effect of combining feature selection technique (FST) with DLM on their ability in ERR identification." Financial support for this research came from Fundamental Research Grant Scheme. The news correspondents obtained a quote from the research from Universiti Malay a, "External root resorption was simulated on 88 extracted premolar teeth using tungsten bur in different depths (0.5 mm, 1 mm, and 2 mm). All teeth were scanne d using a Cone beam CT (Carestream Dental, Atlanta, GA). Afterward, a training ( 70%), validation (10%), and test (20%) da taset were established. The performance of four DLMs including Random Forest (RF ) + Visual Geometry Group 16 (VGG), RF + EfficienNetB4 (EFNET), Support Vector M achine (SVM) + VGG, and SVM + EFNET) and four hybrid models (DLM + FST: (i) FS + RF + VGG, (ii) FS + RF + EFNET, (iii) FS + SVM + VGG and (iv) FS + SVM + EFNET) was compared. Five performance parameters were assessed: classification accurac y, F1-score, precision, specificity, and error rate. FST algorithms (Boruta and Recursive Feature Selection) were combined with the DLMs to assess their perform ance. RF + VGG exhibited the highest performance in identifying ERR, followed by the other tested models. Similarly, FST combined with RF + VGG outperformed oth er models with classification accuracy, F1-score, precision, and specificity of 81.9%, weighted accuracy of 83%, and area under the cu rve (AUC) of 96%. Kruskal Wallis test revealed a significant differ ence (p = 0.008) in the prediction accuracy among the eight DLMs. In general, al l DLMs have similar performance on ERR identification."
Kuala LumpurMalaysiaAsiaDental Dis eases and ConditionsDentistryHealth and MedicineMachine LearningRoot Res orptionSupport Vector MachinesTooth Diseases and ConditionsTooth Resorptio n
NETL
NSTL
