Detection of the separated root canal instrument on panoramic radiograph: a comparison of LSTM and CNN deep learning methods

dc.authorid Buyuk, Cansu/0000-0001-8126-0928
dc.authorid Er, Füsun/0000-0002-6339-8736
dc.authorid Arican, Burcin/0000-0001-5757-0571
dc.authorscopusid 56593197800
dc.authorscopusid 58110110000
dc.authorscopusid 58110017100
dc.authorwosid Buyuk, Cansu/GQH-1921-2022
dc.authorwosid Er, Füsun/JAC-0850-2023
dc.contributor.author Buyuk, Cansu
dc.contributor.author Alpay, Burcin Arican
dc.contributor.author Er, Fusun
dc.date.accessioned 2024-05-25T11:38:40Z
dc.date.available 2024-05-25T11:38:40Z
dc.date.issued 2023
dc.department Okan University en_US
dc.department-temp [Buyuk, Cansu] Istanbul Okan Univ, Fac Dent, Dept Dentomaxillofacial Radiol, Istanbul, Turkiye; [Alpay, Burcin Arican] Bahcesehir Univ, Fac Dent, Dept Endodont, Istanbul, Turkiye; [Er, Fusun] Piri Reis Univ, Fac Engn, Informat Syst Engn, Istanbul, Turkiye en_US
dc.description Buyuk, Cansu/0000-0001-8126-0928; Er, Füsun/0000-0002-6339-8736; Arican, Burcin/0000-0001-5757-0571 en_US
dc.description.abstract Objectives: A separated endodontic instrument is one of the challenging complications of root canal treatment. The purpose of this study was to compare two deep learning methods that are convolutional neural network (CNN) and long short -term memory (LSTM) to detect the separated endodontic instruments on dental radiographs.Methods: Panoramic radiographs from the hospital archive were retrospectively evaluated by two dentists. A total of 915 teeth, of which 417 are labeled as "separated instrument" and 498 are labeled as "healthy root canal treatment" were included. A total of six deep learning models, four of which are some varieties of CNN (Raw -CNN, Augmented -CNN, Gabor filtered -CNN, Gabor-filtered -augmented -CNN) and two of which are some varieties of LSTM model (Raw- LSTM, Augmented-LSTM) were trained based on several feature extraction methods with an applied or not applied an augmentation procedure. The diagnostic performances of the models were compared in terms of accuracy, sensitivity, specificity, positive-and negative-predictive value using 10 -fold cross-validation. A McNemar's tests was employed to figure out if there is a statistically significant difference between performances of the models. Receiver operating characteristic (ROC) curves were developed to assess the quality of the performance of the most promising model (Gabor filtered -CNN model) by exploring different cut -off levels in the last decision layer of the model.Results: The Gabor filtered -CNN model showed the highest accuracy (84.37 +/- 2.79), sensitivity (81.26 +/- 4.79), positive-predictive value (84.16 +/- 3.35) and negative-predictive value (84.62 +/- 4.56 with a confidence interval of 80.6 +/- 0.0076. McNemar's tests yielded that the performance of the Gabor filtered -CNN model significantly different from both LSTM models (p < 0.01).Conclusions: Both CNN and LSTM models were achieved a high predictive performance on to distinguish separated endodontic instruments in radiographs. The Gabor filtered -CNN model without data augmentation gave the best predictive performance. en_US
dc.description.sponsorship Scientific and Technological Research Council of Turkey (TUBITAK) of (1002) Short-Term R&D Funding Program [220S755] en_US
dc.description.sponsorship Funding This research project was funded by the Scientific and Technological Research Council of Turkey (TUBITAK) of (1002) Short-Term R&D Funding Program (project no: 220S755) . en_US
dc.identifier.citationcount 3
dc.identifier.doi 10.1259/dmfr.20220209
dc.identifier.issn 0250-832X
dc.identifier.issn 1476-542X
dc.identifier.issue 3 en_US
dc.identifier.pmid 36688738
dc.identifier.scopus 2-s2.0-85148479853
dc.identifier.scopusquality Q1
dc.identifier.uri https://doi.org/10.1259/dmfr.20220209
dc.identifier.uri https://hdl.handle.net/20.500.14517/1258
dc.identifier.volume 52 en_US
dc.identifier.wos WOS:000952017300001
dc.identifier.wosquality Q2
dc.institutionauthor Buyuk C.
dc.language.iso en
dc.publisher British inst Radiology en_US
dc.relation.publicationcategory Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı en_US
dc.rights info:eu-repo/semantics/openAccess en_US
dc.scopus.citedbyCount 13
dc.subject Artificial intelligence en_US
dc.subject CNN en_US
dc.subject deep learning en_US
dc.subject LSTM en_US
dc.subject panoramic radiograph en_US
dc.subject separated endodontic instruments en_US
dc.title Detection of the separated root canal instrument on panoramic radiograph: a comparison of LSTM and CNN deep learning methods en_US
dc.type Article en_US
dc.wos.citedbyCount 11

Files