Automatic caries detection in bitewing radiographs-Part II: experimental comparison
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00064165%3A_____%2F24%3A10469921" target="_blank" >RIV/00064165:_____/24:10469921 - isvavai.cz</a>
Alternative codes found
RIV/68407700:21230/24:00373356 RIV/00216208:11110/24:10469921
Result on the web
<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=bOrgQJEgP-" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=bOrgQJEgP-</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/s00784-024-05528-2" target="_blank" >10.1007/s00784-024-05528-2</a>
Alternative languages
Result language
angličtina
Original language name
Automatic caries detection in bitewing radiographs-Part II: experimental comparison
Original language description
Objective: The objective of this study was to compare the detection of caries in bitewing radiographs by multiple dentists with an automatic method and to evaluate the detection performance in the absence of reliable ground truth.Materials and Methods: Four experts and three novices marked caries using bounding boxes in 100 bitewing radiographs. The same dataset was processed by an automatic object detection deep learning method. All annotators were compared in terms of the number of errors and intersection over union (IoU) using pairwise comparisons, with respect to the consensus standard, and with respect to the annotator of the training dataset of the automatic method.Results: The number of lesions marked by experts in 100 images varied between 241 and 425. Pair- wise comparisons showed that the automatic method outperformed all dentists except the original annotator in the mean number of errors, while being among the best in terms of IoU. With respect to a consensus standard, the performance of the automatic method was best in terms of the num- ber of errors and slightly below average in terms of IoU. Compared with the original annotator, the automatic method had the highest IoU and only one expert made fewer errors.Conclusions: Caries detection is challenging even for humans. The automatic method consistently outperformed less experienced dentists and performed as well as highly experienced dentists. Clinical Significance: The consensus in caries detection between experts is low. An automatic method can improve both the accuracy and repeatability of caries detection, providing a useful second opinion even for very experienced dentists.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
30208 - Dentistry, oral surgery and medicine
Result continuities
Project
<a href="/en/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Research Center for Informatics</a><br>
Continuities
V - Vyzkumna aktivita podporovana z jinych verejnych zdroju
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Clinical Oral Investigations
ISSN
1432-6981
e-ISSN
1436-3771
Volume of the periodical
28
Issue of the periodical within the volume
2
Country of publishing house
DE - GERMANY
Number of pages
10
Pages from-to
133
UT code for WoS article
001156150200002
EID of the result in the Scopus database
2-s2.0-85184407305