PMID- 37571620
OWN - NLM
STAT- MEDLINE
DCOM- 20230814
LR  - 20230815
IS  - 1424-8220 (Electronic)
IS  - 1424-8220 (Linking)
VI  - 23
IP  - 15
DP  - 2023 Jul 31
TI  - Teeth Lesion Detection Using Deep Learning and the Internet of Things 
      Post-COVID-19.
LID - 10.3390/s23156837 [doi]
LID - 6837
AB  - With a view of the post-COVID-19 world and probable future pandemics, this paper 
      presents an Internet of Things (IoT)-based automated healthcare diagnosis model 
      that employs a mixed approach using data augmentation, transfer learning, and 
      deep learning techniques and does not require physical interaction between the 
      patient and physician. Through a user-friendly graphic user interface and 
      availability of suitable computing power on smart devices, the embedded 
      artificial intelligence allows the proposed model to be effectively used by a 
      layperson without the need for a dental expert by indicating any issues with the 
      teeth and subsequent treatment options. The proposed method involves multiple 
      processes, including data acquisition using IoT devices, data preprocessing, deep 
      learning-based feature extraction, and classification through an unsupervised 
      neural network. The dataset contains multiple periapical X-rays of five different 
      types of lesions obtained through an IoT device mounted within the mouth guard. A 
      pretrained AlexNet, a fast GPU implementation of a convolutional neural network 
      (CNN), is fine-tuned using data augmentation and transfer learning and employed 
      to extract the suitable feature set. The data augmentation avoids overtraining, 
      whereas accuracy is improved by transfer learning. Later, support vector machine 
      (SVM) and the K-nearest neighbors (KNN) classifiers are trained for lesion 
      classification. It was found that the proposed automated model based on the 
      AlexNet extraction mechanism followed by the SVM classifier achieved an accuracy 
      of 98%, showing the effectiveness of the presented approach.
FAU - Shafi, Imran
AU  - Shafi I
AD  - College of Electrical and Mechanical Engineering, National University of Sciences 
      and Technology (NUST), Islamabad 44000, Pakistan.
FAU - Sajad, Muhammad
AU  - Sajad M
AD  - Abasyn University Islamabad Campus, Islamabad 44000, Pakistan.
FAU - Fatima, Anum
AU  - Fatima A
AD  - College of Electrical and Mechanical Engineering, National University of Sciences 
      and Technology (NUST), Islamabad 44000, Pakistan.
FAU - Aray, Daniel Gavilanes
AU  - Aray DG
AD  - Higher Polytechnic School, Universidad Europea del Atlantico, Isabel Torres 21, 
      39011 Santander, Spain.
AD  - Universidad Internacional Iberoamericana, Campeche 24560, Mexico.
AD  - Fundacion Universitaria Internacional de Colombia Bogota, Bogota 11131, Colombia.
FAU - Lipari, Vivian
AU  - Lipari V
AD  - Higher Polytechnic School, Universidad Europea del Atlantico, Isabel Torres 21, 
      39011 Santander, Spain.
AD  - Universidad Internacional Iberoamericana Arecibo, Puerto Rico, PR 00613, USA.
AD  - Universidade Internacional do Cuanza, Cuito EN250, Bie, Angola.
FAU - Diez, Isabel de la Torre
AU  - Diez IT
AUID- ORCID: 0000-0003-3134-7720
AD  - Department of Signal Theory, Communications and Telematics Engineering, 
      Unviersity of Valladolid, Paseo de Belen, 15, 47011 Valladolid, Spain.
FAU - Ashraf, Imran
AU  - Ashraf I
AUID- ORCID: 0000-0002-8271-6496
AD  - Department of Information and Communication Engineering, Yeungnam University, 
      Gyeongsan 38541, Republic of Korea.
LA  - eng
GR  - N/A/the European University of Atlantic/
PT  - Journal Article
DEP - 20230731
PL  - Switzerland
TA  - Sensors (Basel)
JT  - Sensors (Basel, Switzerland)
JID - 101204366
SB  - IM
MH  - Humans
MH  - Artificial Intelligence
MH  - *COVID-19
MH  - *Deep Learning
MH  - *Internet of Things
MH  - Cluster Analysis
PMC - PMC10422255
OTO - NOTNLM
OT  - AlexNet
OT  - IoT enabled framework
OT  - automated detection model
OT  - teeth lesion detection
OT  - transfer learning
COIS- The authors declare no conflict of interest.
EDAT- 2023/08/12 10:45
MHDA- 2023/08/14 06:42
PMCR- 2023/07/31
CRDT- 2023/08/12 01:23
PHST- 2023/07/05 00:00 [received]
PHST- 2023/07/26 00:00 [revised]
PHST- 2023/07/29 00:00 [accepted]
PHST- 2023/08/14 06:42 [medline]
PHST- 2023/08/12 10:45 [pubmed]
PHST- 2023/08/12 01:23 [entrez]
PHST- 2023/07/31 00:00 [pmc-release]
AID - s23156837 [pii]
AID - sensors-23-06837 [pii]
AID - 10.3390/s23156837 [doi]
PST - epublish
SO  - Sensors (Basel). 2023 Jul 31;23(15):6837. doi: 10.3390/s23156837.