Automatic caries detection in bitewing radiographs: Part I—deep learning
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00064165%3A_____%2F23%3A10469919" target="_blank" >RIV/00064165:_____/23:10469919 - isvavai.cz</a>
Nalezeny alternativní kódy
RIV/68407700:21230/23:00371239 RIV/00216208:11110/23:10469919
Výsledek na webu
<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=uHRM_bnn~T" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=uHRM_bnn~T</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/s00784-023-05335-1" target="_blank" >10.1007/s00784-023-05335-1</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Automatic caries detection in bitewing radiographs: Part I—deep learning
Popis výsledku v původním jazyce
Objective: The aim of this work was to assemble a large annotated dataset of bitewing radiographs and to use convolutional neural networks to automate the detection of dental caries in bitewing radiographs with human-level performance.Materials and Methods: A dataset of 3989 bitewing radiographs was created and 7257 carious lesions were annotated using minimal bounding boxes. The dataset was then divided into 3 parts for the training (70%), validation (15%), and testing (15%) of multiple object detection convolutional neural networks (CNN). The tested CNN architectures included YOLOv5, Faster R-CNN, RetinaNet, and EfficientDet. To further improve the detection performance, model ensembling was used, and nested predictions were removed during post-processing. The models were compared in terms of the F1 score and average precision (AP) with various thresholds of the intersection over union (IoU).Results: The twelve tested architectures had F1 scores of 0.72-0.76. Their performance was improved by ensembling which increased the F1 score to 0.79-0.80. The best-performing ensemble detected caries with the precision of 0.83, recall of 0.77, F1 = 0.80, and AP of 0.86 at IoU=0.5. Small carious lesions were predicted with slightly lower accuracy (AP 0.82) than medium or large lesions (AP 0.88). Conclusions: The trained ensemble of object detection CNNs detected caries with satisfactory accuracy and performed at least as well as experienced dentists (see companion paper, Part II). The performance on small lesions was likely limited by inconsistencies in the training dataset.Clinical Significance: Caries can be automatically detected using convolutional neural networks. However, detecting incipient carious lesions remains challenging.
Název v anglickém jazyce
Automatic caries detection in bitewing radiographs: Part I—deep learning
Popis výsledku anglicky
Objective: The aim of this work was to assemble a large annotated dataset of bitewing radiographs and to use convolutional neural networks to automate the detection of dental caries in bitewing radiographs with human-level performance.Materials and Methods: A dataset of 3989 bitewing radiographs was created and 7257 carious lesions were annotated using minimal bounding boxes. The dataset was then divided into 3 parts for the training (70%), validation (15%), and testing (15%) of multiple object detection convolutional neural networks (CNN). The tested CNN architectures included YOLOv5, Faster R-CNN, RetinaNet, and EfficientDet. To further improve the detection performance, model ensembling was used, and nested predictions were removed during post-processing. The models were compared in terms of the F1 score and average precision (AP) with various thresholds of the intersection over union (IoU).Results: The twelve tested architectures had F1 scores of 0.72-0.76. Their performance was improved by ensembling which increased the F1 score to 0.79-0.80. The best-performing ensemble detected caries with the precision of 0.83, recall of 0.77, F1 = 0.80, and AP of 0.86 at IoU=0.5. Small carious lesions were predicted with slightly lower accuracy (AP 0.82) than medium or large lesions (AP 0.88). Conclusions: The trained ensemble of object detection CNNs detected caries with satisfactory accuracy and performed at least as well as experienced dentists (see companion paper, Part II). The performance on small lesions was likely limited by inconsistencies in the training dataset.Clinical Significance: Caries can be automatically detected using convolutional neural networks. However, detecting incipient carious lesions remains challenging.
Klasifikace
Druh
J<sub>imp</sub> - Článek v periodiku v databázi Web of Science
CEP obor
—
OECD FORD obor
30208 - Dentistry, oral surgery and medicine
Návaznosti výsledku
Projekt
<a href="/cs/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Výzkumné centrum informatiky</a><br>
Návaznosti
V - Vyzkumna aktivita podporovana z jinych verejnych zdroju
Ostatní
Rok uplatnění
2023
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název periodika
Clinical Oral Investigations
ISSN
1432-6981
e-ISSN
1436-3771
Svazek periodika
27
Číslo periodika v rámci svazku
12
Stát vydavatele periodika
DE - Spolková republika Německo
Počet stran výsledku
9
Strana od-do
7463-7471
Kód UT WoS článku
001102291500001
EID výsledku v databázi Scopus
2-s2.0-85176781185