The Combination of Adaptive Convolutional Neural Network and Bag of Visual Words in Automatic Diagnosis of Third Molar Complications on Dental X-Ray Images
In dental diagnosis, recognizing tooth complications quickly from radiology (e.g., X-rays) takes highly experienced medical professionals. By using object detection models and algorithms, this work is much easier and needs less experienced medical practitioners to clear their doubts while diagnosing...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-04-01
|
Series: | Diagnostics |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-4418/10/4/209 |
id |
doaj-6be19342ed4b4b3fb066684de813d7d6 |
---|---|
record_format |
Article |
spelling |
doaj-6be19342ed4b4b3fb066684de813d7d62020-11-25T02:04:13ZengMDPI AGDiagnostics2075-44182020-04-011020920910.3390/diagnostics10040209The Combination of Adaptive Convolutional Neural Network and Bag of Visual Words in Automatic Diagnosis of Third Molar Complications on Dental X-Ray ImagesVo Truong Nhu Ngoc0Agwu Chinedu Agwu1Le Hoang Son2Tran Manh Tuan3Cu Nguyen Giap4Mai Thi Giang Thanh5Hoang Bao Duy6Tran Thi Ngan7School of Odonto–Stomatology, Hanoi Medical University, Hanoi 010000, VietnamInformation and Communication Technology Department, University of Science and Technology, Hanoi 010000, VietnamVNU Information Technology Institute, Vietnam National University, Hanoi 010000, VietnamFaculty of Information Technology, Thuyloi University, 175 Tay Son, Dong Da, Hanoi 010000, VietnamFaculty of Management Information System & E-commerce, Thuongmai University, Hanoi 010000, VietnamSchool of Odonto–Stomatology, Hanoi Medical University, Hanoi 010000, VietnamSchool of Odonto–Stomatology, Hanoi Medical University, Hanoi 010000, VietnamFaculty of Information Technology, Thuyloi University, 175 Tay Son, Dong Da, Hanoi 010000, VietnamIn dental diagnosis, recognizing tooth complications quickly from radiology (e.g., X-rays) takes highly experienced medical professionals. By using object detection models and algorithms, this work is much easier and needs less experienced medical practitioners to clear their doubts while diagnosing a medical case. In this paper, we propose a dental defect recognition model by the integration of Adaptive Convolution Neural Network and Bag of Visual Word (BoVW). In this model, BoVW is used to save the features extracted from images. After that, a designed Convolutional Neural Network (CNN) model is used to make quality prediction. To evaluate the proposed model, we collected a dataset of radiography images of 447 patients in Hanoi Medical Hospital, Vietnam, with third molar complications. The results of the model suggest accuracy of 84% ± 4%. This accuracy is comparable to that of experienced dentists and radiologists.https://www.mdpi.com/2075-4418/10/4/209dental defect recognitionBoVWradiologyAdaptive Convolutional Neural Networkdental complications |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Vo Truong Nhu Ngoc Agwu Chinedu Agwu Le Hoang Son Tran Manh Tuan Cu Nguyen Giap Mai Thi Giang Thanh Hoang Bao Duy Tran Thi Ngan |
spellingShingle |
Vo Truong Nhu Ngoc Agwu Chinedu Agwu Le Hoang Son Tran Manh Tuan Cu Nguyen Giap Mai Thi Giang Thanh Hoang Bao Duy Tran Thi Ngan The Combination of Adaptive Convolutional Neural Network and Bag of Visual Words in Automatic Diagnosis of Third Molar Complications on Dental X-Ray Images Diagnostics dental defect recognition BoVW radiology Adaptive Convolutional Neural Network dental complications |
author_facet |
Vo Truong Nhu Ngoc Agwu Chinedu Agwu Le Hoang Son Tran Manh Tuan Cu Nguyen Giap Mai Thi Giang Thanh Hoang Bao Duy Tran Thi Ngan |
author_sort |
Vo Truong Nhu Ngoc |
title |
The Combination of Adaptive Convolutional Neural Network and Bag of Visual Words in Automatic Diagnosis of Third Molar Complications on Dental X-Ray Images |
title_short |
The Combination of Adaptive Convolutional Neural Network and Bag of Visual Words in Automatic Diagnosis of Third Molar Complications on Dental X-Ray Images |
title_full |
The Combination of Adaptive Convolutional Neural Network and Bag of Visual Words in Automatic Diagnosis of Third Molar Complications on Dental X-Ray Images |
title_fullStr |
The Combination of Adaptive Convolutional Neural Network and Bag of Visual Words in Automatic Diagnosis of Third Molar Complications on Dental X-Ray Images |
title_full_unstemmed |
The Combination of Adaptive Convolutional Neural Network and Bag of Visual Words in Automatic Diagnosis of Third Molar Complications on Dental X-Ray Images |
title_sort |
combination of adaptive convolutional neural network and bag of visual words in automatic diagnosis of third molar complications on dental x-ray images |
publisher |
MDPI AG |
series |
Diagnostics |
issn |
2075-4418 |
publishDate |
2020-04-01 |
description |
In dental diagnosis, recognizing tooth complications quickly from radiology (e.g., X-rays) takes highly experienced medical professionals. By using object detection models and algorithms, this work is much easier and needs less experienced medical practitioners to clear their doubts while diagnosing a medical case. In this paper, we propose a dental defect recognition model by the integration of Adaptive Convolution Neural Network and Bag of Visual Word (BoVW). In this model, BoVW is used to save the features extracted from images. After that, a designed Convolutional Neural Network (CNN) model is used to make quality prediction. To evaluate the proposed model, we collected a dataset of radiography images of 447 patients in Hanoi Medical Hospital, Vietnam, with third molar complications. The results of the model suggest accuracy of 84% ± 4%. This accuracy is comparable to that of experienced dentists and radiologists. |
topic |
dental defect recognition BoVW radiology Adaptive Convolutional Neural Network dental complications |
url |
https://www.mdpi.com/2075-4418/10/4/209 |
work_keys_str_mv |
AT votruongnhungoc thecombinationofadaptiveconvolutionalneuralnetworkandbagofvisualwordsinautomaticdiagnosisofthirdmolarcomplicationsondentalxrayimages AT agwuchineduagwu thecombinationofadaptiveconvolutionalneuralnetworkandbagofvisualwordsinautomaticdiagnosisofthirdmolarcomplicationsondentalxrayimages AT lehoangson thecombinationofadaptiveconvolutionalneuralnetworkandbagofvisualwordsinautomaticdiagnosisofthirdmolarcomplicationsondentalxrayimages AT tranmanhtuan thecombinationofadaptiveconvolutionalneuralnetworkandbagofvisualwordsinautomaticdiagnosisofthirdmolarcomplicationsondentalxrayimages AT cunguyengiap thecombinationofadaptiveconvolutionalneuralnetworkandbagofvisualwordsinautomaticdiagnosisofthirdmolarcomplicationsondentalxrayimages AT maithigiangthanh thecombinationofadaptiveconvolutionalneuralnetworkandbagofvisualwordsinautomaticdiagnosisofthirdmolarcomplicationsondentalxrayimages AT hoangbaoduy thecombinationofadaptiveconvolutionalneuralnetworkandbagofvisualwordsinautomaticdiagnosisofthirdmolarcomplicationsondentalxrayimages AT tranthingan thecombinationofadaptiveconvolutionalneuralnetworkandbagofvisualwordsinautomaticdiagnosisofthirdmolarcomplicationsondentalxrayimages AT votruongnhungoc combinationofadaptiveconvolutionalneuralnetworkandbagofvisualwordsinautomaticdiagnosisofthirdmolarcomplicationsondentalxrayimages AT agwuchineduagwu combinationofadaptiveconvolutionalneuralnetworkandbagofvisualwordsinautomaticdiagnosisofthirdmolarcomplicationsondentalxrayimages AT lehoangson combinationofadaptiveconvolutionalneuralnetworkandbagofvisualwordsinautomaticdiagnosisofthirdmolarcomplicationsondentalxrayimages AT tranmanhtuan combinationofadaptiveconvolutionalneuralnetworkandbagofvisualwordsinautomaticdiagnosisofthirdmolarcomplicationsondentalxrayimages AT cunguyengiap combinationofadaptiveconvolutionalneuralnetworkandbagofvisualwordsinautomaticdiagnosisofthirdmolarcomplicationsondentalxrayimages AT maithigiangthanh combinationofadaptiveconvolutionalneuralnetworkandbagofvisualwordsinautomaticdiagnosisofthirdmolarcomplicationsondentalxrayimages AT hoangbaoduy combinationofadaptiveconvolutionalneuralnetworkandbagofvisualwordsinautomaticdiagnosisofthirdmolarcomplicationsondentalxrayimages AT tranthingan combinationofadaptiveconvolutionalneuralnetworkandbagofvisualwordsinautomaticdiagnosisofthirdmolarcomplicationsondentalxrayimages |
_version_ |
1724943752809676800 |