Classification of Intraoral Photographs with Deep Learning Algorithms Trained According to Cephalometric Measurements

<b>Background/Objectives</b>: Clinical intraoral photographs are important for orthodontic diagnosis, treatment planning, and documentation. This study aimed to evaluate deep learning algorithms trained utilizing actual cephalometric measurements for the classification of intraoral clini...

Full description

Saved in:
Bibliographic Details
Main Authors: Sultan Büşra Ay Kartbak, Mehmet Birol Özel, Duygu Nur Cesur Kocakaya, Muhammet Çakmak, Enver Alper Sinanoğlu
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/15/9/1059
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849322449984815104
author Sultan Büşra Ay Kartbak
Mehmet Birol Özel
Duygu Nur Cesur Kocakaya
Muhammet Çakmak
Enver Alper Sinanoğlu
author_facet Sultan Büşra Ay Kartbak
Mehmet Birol Özel
Duygu Nur Cesur Kocakaya
Muhammet Çakmak
Enver Alper Sinanoğlu
author_sort Sultan Büşra Ay Kartbak
collection DOAJ
description <b>Background/Objectives</b>: Clinical intraoral photographs are important for orthodontic diagnosis, treatment planning, and documentation. This study aimed to evaluate deep learning algorithms trained utilizing actual cephalometric measurements for the classification of intraoral clinical photographs. <b>Methods</b>: This study was executed on lateral cephalograms and intraoral right-side images of 990 patients. IMPA, interincisal angle, U1–palatal plane angle, and Wits appraisal values were measured utilizing WebCeph. Intraoral photographs were divided into three groups based on cephalometric measurements. A total of 14 deep learning models (DenseNet 121, DenseNet 169, DenseNet 201, EfficientNet B0, EfficientNet V2, Inception V3, MobileNet V2, NasNetMobile, ResNet101, ResNet152, ResNet50, VGG16, VGG19, and Xception) were employed to classify the intraoral photographs. Performance metrics (F1 scores, accuracy, precision, and recall) were calculated and confusion matrices were formed. <b>Results</b>: The highest accuracy rates were 98.33% for IMPA groups, 99.00% for interincisal angle groups, 96.67% for U1–palatal plane angle groups, and 98.33% for Wits measurement groups. Lowest accuracy rates were 59% for IMPA groups, 53% for interincisal angle groups, 33.33% for U1–palatal plane angle groups, and 83.67% for Wits measurement groups. <b>Conclusions</b>: Although accuracy rates varied among classifications and DL algorithms, successful classification could be achieved in the majority of cases. Our results may be promising for case classification and analysis without the need for lateral cephalometric radiographs.
format Article
id doaj-art-594b7afac04a4d6d9fda9dd802e37f18
institution Kabale University
issn 2075-4418
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-594b7afac04a4d6d9fda9dd802e37f182025-08-20T03:49:22ZengMDPI AGDiagnostics2075-44182025-04-01159105910.3390/diagnostics15091059Classification of Intraoral Photographs with Deep Learning Algorithms Trained According to Cephalometric MeasurementsSultan Büşra Ay Kartbak0Mehmet Birol Özel1Duygu Nur Cesur Kocakaya2Muhammet Çakmak3Enver Alper Sinanoğlu4Department of Orthodontics, Faculty of Dentistry, Kocaeli University, Kocaeli 41190, TürkiyeDepartment of Orthodontics, Faculty of Dentistry, Kocaeli University, Kocaeli 41190, TürkiyePrivate Practice, Gölcük 41650, TürkiyeDepartment of Computer Engineering, Faculty of Engineering and Architecture, Sinop University, Sinop 57000, TürkiyeDepartment of Oral and Maxillofacial Radiology, Faculty of Dentistry, Kocaeli University, Kocaeli 41190, Türkiye<b>Background/Objectives</b>: Clinical intraoral photographs are important for orthodontic diagnosis, treatment planning, and documentation. This study aimed to evaluate deep learning algorithms trained utilizing actual cephalometric measurements for the classification of intraoral clinical photographs. <b>Methods</b>: This study was executed on lateral cephalograms and intraoral right-side images of 990 patients. IMPA, interincisal angle, U1–palatal plane angle, and Wits appraisal values were measured utilizing WebCeph. Intraoral photographs were divided into three groups based on cephalometric measurements. A total of 14 deep learning models (DenseNet 121, DenseNet 169, DenseNet 201, EfficientNet B0, EfficientNet V2, Inception V3, MobileNet V2, NasNetMobile, ResNet101, ResNet152, ResNet50, VGG16, VGG19, and Xception) were employed to classify the intraoral photographs. Performance metrics (F1 scores, accuracy, precision, and recall) were calculated and confusion matrices were formed. <b>Results</b>: The highest accuracy rates were 98.33% for IMPA groups, 99.00% for interincisal angle groups, 96.67% for U1–palatal plane angle groups, and 98.33% for Wits measurement groups. Lowest accuracy rates were 59% for IMPA groups, 53% for interincisal angle groups, 33.33% for U1–palatal plane angle groups, and 83.67% for Wits measurement groups. <b>Conclusions</b>: Although accuracy rates varied among classifications and DL algorithms, successful classification could be achieved in the majority of cases. Our results may be promising for case classification and analysis without the need for lateral cephalometric radiographs.https://www.mdpi.com/2075-4418/15/9/1059deep learningartificial intelligenceintraoral photographcephalometry
spellingShingle Sultan Büşra Ay Kartbak
Mehmet Birol Özel
Duygu Nur Cesur Kocakaya
Muhammet Çakmak
Enver Alper Sinanoğlu
Classification of Intraoral Photographs with Deep Learning Algorithms Trained According to Cephalometric Measurements
Diagnostics
deep learning
artificial intelligence
intraoral photograph
cephalometry
title Classification of Intraoral Photographs with Deep Learning Algorithms Trained According to Cephalometric Measurements
title_full Classification of Intraoral Photographs with Deep Learning Algorithms Trained According to Cephalometric Measurements
title_fullStr Classification of Intraoral Photographs with Deep Learning Algorithms Trained According to Cephalometric Measurements
title_full_unstemmed Classification of Intraoral Photographs with Deep Learning Algorithms Trained According to Cephalometric Measurements
title_short Classification of Intraoral Photographs with Deep Learning Algorithms Trained According to Cephalometric Measurements
title_sort classification of intraoral photographs with deep learning algorithms trained according to cephalometric measurements
topic deep learning
artificial intelligence
intraoral photograph
cephalometry
url https://www.mdpi.com/2075-4418/15/9/1059
work_keys_str_mv AT sultanbusraaykartbak classificationofintraoralphotographswithdeeplearningalgorithmstrainedaccordingtocephalometricmeasurements
AT mehmetbirolozel classificationofintraoralphotographswithdeeplearningalgorithmstrainedaccordingtocephalometricmeasurements
AT duygunurcesurkocakaya classificationofintraoralphotographswithdeeplearningalgorithmstrainedaccordingtocephalometricmeasurements
AT muhammetcakmak classificationofintraoralphotographswithdeeplearningalgorithmstrainedaccordingtocephalometricmeasurements
AT enveralpersinanoglu classificationofintraoralphotographswithdeeplearningalgorithmstrainedaccordingtocephalometricmeasurements