Cover Image

Application of deep learning and feature selection technique on external root resorption identification on CBCT images

BackgroundArtificial intelligence has been proven to improve the identification of various maxillofacial lesions. The aim of the current study is two-fold: to assess the performance of four deep learning models (DLM) in external root resorption (ERR) identification and to assess the effect of combin...

Full description

Saved in:
Bibliographic Details
Main Authors: Reduwan, Nor Hidayah, Aziz, Azwatee Abdul Abdul, Razi, Roziana Mohd, Abdullah, Erma Rahayu Mohd Faizal, Nezhad, Seyed Matin Mazloom, Gohain, Meghna, Ibrahim, Norliza
Format: Article
Published: BioMed Central 2024
Subjects:
QA75 Electronic computers. Computer science
RK Dentistry
Online Access:http://eprints.um.edu.my/45600/
https://doi.org/10.1186/s12903-024-03910-w
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.um.eprints.45600
record_format eprints
spelling my.um.eprints.456002024-11-06T01:38:05Z http://eprints.um.edu.my/45600/ Application of deep learning and feature selection technique on external root resorption identification on CBCT images Reduwan, Nor Hidayah Aziz, Azwatee Abdul Abdul Razi, Roziana Mohd Abdullah, Erma Rahayu Mohd Faizal Nezhad, Seyed Matin Mazloom Gohain, Meghna Ibrahim, Norliza QA75 Electronic computers. Computer science RK Dentistry BackgroundArtificial intelligence has been proven to improve the identification of various maxillofacial lesions. The aim of the current study is two-fold: to assess the performance of four deep learning models (DLM) in external root resorption (ERR) identification and to assess the effect of combining feature selection technique (FST) with DLM on their ability in ERR identification.MethodsExternal 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 scanned using a Cone beam CT (Carestream Dental, Atlanta, GA). Afterward, a training (70%), validation (10%), and test (20%) dataset were established. The performance of four DLMs including Random Forest (RF) + Visual Geometry Group 16 (VGG), RF + EfficienNetB4 (EFNET), Support Vector Machine (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 accuracy, F1-score, precision, specificity, and error rate. FST algorithms (Boruta and Recursive Feature Selection) were combined with the DLMs to assess their performance.ResultsRF + VGG exhibited the highest performance in identifying ERR, followed by the other tested models. Similarly, FST combined with RF + VGG outperformed other models with classification accuracy, F1-score, precision, and specificity of 81.9%, weighted accuracy of 83%, and area under the curve (AUC) of 96%. Kruskal Wallis test revealed a significant difference (p = 0.008) in the prediction accuracy among the eight DLMs.ConclusionIn general, all DLMs have similar performance on ERR identification. However, the performance can be improved by combining FST with DLMs. BioMed Central 2024-02 Article PeerReviewed Reduwan, Nor Hidayah and Aziz, Azwatee Abdul Abdul and Razi, Roziana Mohd and Abdullah, Erma Rahayu Mohd Faizal and Nezhad, Seyed Matin Mazloom and Gohain, Meghna and Ibrahim, Norliza (2024) Application of deep learning and feature selection technique on external root resorption identification on CBCT images. BMC Oral Health, 24 (1). p. 252. ISSN 1472-6831, DOI https://doi.org/10.1186/s12903-024-03910-w <https://doi.org/10.1186/s12903-024-03910-w>. https://doi.org/10.1186/s12903-024-03910-w 10.1186/s12903-024-03910-w
institution Universiti Malaya
building UM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaya
content_source UM Research Repository
url_provider http://eprints.um.edu.my/
topic QA75 Electronic computers. Computer science
RK Dentistry
spellingShingle QA75 Electronic computers. Computer science
RK Dentistry
Reduwan, Nor Hidayah
Aziz, Azwatee Abdul Abdul
Razi, Roziana Mohd
Abdullah, Erma Rahayu Mohd Faizal
Nezhad, Seyed Matin Mazloom
Gohain, Meghna
Ibrahim, Norliza
Application of deep learning and feature selection technique on external root resorption identification on CBCT images
description BackgroundArtificial intelligence has been proven to improve the identification of various maxillofacial lesions. The aim of the current study is two-fold: to assess the performance of four deep learning models (DLM) in external root resorption (ERR) identification and to assess the effect of combining feature selection technique (FST) with DLM on their ability in ERR identification.MethodsExternal 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 scanned using a Cone beam CT (Carestream Dental, Atlanta, GA). Afterward, a training (70%), validation (10%), and test (20%) dataset were established. The performance of four DLMs including Random Forest (RF) + Visual Geometry Group 16 (VGG), RF + EfficienNetB4 (EFNET), Support Vector Machine (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 accuracy, F1-score, precision, specificity, and error rate. FST algorithms (Boruta and Recursive Feature Selection) were combined with the DLMs to assess their performance.ResultsRF + VGG exhibited the highest performance in identifying ERR, followed by the other tested models. Similarly, FST combined with RF + VGG outperformed other models with classification accuracy, F1-score, precision, and specificity of 81.9%, weighted accuracy of 83%, and area under the curve (AUC) of 96%. Kruskal Wallis test revealed a significant difference (p = 0.008) in the prediction accuracy among the eight DLMs.ConclusionIn general, all DLMs have similar performance on ERR identification. However, the performance can be improved by combining FST with DLMs.
format Article
author Reduwan, Nor Hidayah
Aziz, Azwatee Abdul Abdul
Razi, Roziana Mohd
Abdullah, Erma Rahayu Mohd Faizal
Nezhad, Seyed Matin Mazloom
Gohain, Meghna
Ibrahim, Norliza
author_facet Reduwan, Nor Hidayah
Aziz, Azwatee Abdul Abdul
Razi, Roziana Mohd
Abdullah, Erma Rahayu Mohd Faizal
Nezhad, Seyed Matin Mazloom
Gohain, Meghna
Ibrahim, Norliza
author_sort Reduwan, Nor Hidayah
title Application of deep learning and feature selection technique on external root resorption identification on CBCT images
title_short Application of deep learning and feature selection technique on external root resorption identification on CBCT images
title_full Application of deep learning and feature selection technique on external root resorption identification on CBCT images
title_fullStr Application of deep learning and feature selection technique on external root resorption identification on CBCT images
title_full_unstemmed Application of deep learning and feature selection technique on external root resorption identification on CBCT images
title_sort application of deep learning and feature selection technique on external root resorption identification on cbct images
publisher BioMed Central
publishDate 2024
url http://eprints.um.edu.my/45600/
https://doi.org/10.1186/s12903-024-03910-w
_version_ 1814933279183208448
score 13.211869

Similar Items