Advancements in diagnosing oral potentially malignant disorders: leveraging Vision transformers for multi-class detection.
Humans
Mouth Neoplasms
/ diagnosis
Precancerous Conditions
/ diagnosis
Lichen Planus, Oral
/ diagnosis
Leukoplakia, Oral
/ diagnosis
Sensitivity and Specificity
Photography
Diagnosis, Differential
Carcinoma, Squamous Cell
/ diagnosis
Male
Female
Photography, Dental
Image Interpretation, Computer-Assisted
/ methods
Artificial Intelligence
Deep learning
Leukoplakia
Malignant transformation
Oral lichen planus
Oral squamous cell carcinoma
Journal
Clinical oral investigations
ISSN: 1436-3771
Titre abrégé: Clin Oral Investig
Pays: Germany
ID NLM: 9707115
Informations de publication
Date de publication:
08 Jun 2024
08 Jun 2024
Historique:
received:
13
04
2024
accepted:
01
06
2024
medline:
8
6
2024
pubmed:
8
6
2024
entrez:
7
6
2024
Statut:
epublish
Résumé
Diagnosing oral potentially malignant disorders (OPMD) is critical to prevent oral cancer. This study aims to automatically detect and classify the most common pre-malignant oral lesions, such as leukoplakia and oral lichen planus (OLP), and distinguish them from oral squamous cell carcinomas (OSCC) and healthy oral mucosa on clinical photographs using vision transformers. 4,161 photographs of healthy mucosa, leukoplakia, OLP, and OSCC were included. Findings were annotated pixel-wise and reviewed by three clinicians. The photographs were divided into 3,337 for training and validation and 824 for testing. The training and validation images were further divided into five folds with stratification. A Mask R-CNN with a Swin Transformer was trained five times with cross-validation, and the held-out test split was used to evaluate the model performance. The precision, F1-score, sensitivity, specificity, and accuracy were calculated. The area under the receiver operating characteristics curve (AUC) and the confusion matrix of the most effective model were presented. The detection of OSCC with the employed model yielded an F1 of 0.852 and AUC of 0.974. The detection of OLP had an F1 of 0.825 and AUC of 0.948. For leukoplakia the F1 was 0.796 and the AUC was 0.938. OSCC were effectively detected with the employed model, whereas the detection of OLP and leukoplakia was moderately effective. Oral cancer is often detected in advanced stages. The demonstrated technology may support the detection and observation of OPMD to lower the disease burden and identify malignant oral cavity lesions earlier.
Identifiants
pubmed: 38849649
doi: 10.1007/s00784-024-05762-8
pii: 10.1007/s00784-024-05762-8
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
364Informations de copyright
© 2024. The Author(s).
Références
Lingen MW, Abt E, Agrawal N et al (2017) Evidence-based clinical practice guideline for the evaluation of potentially malignant disorders in the oral cavity a report of the American Dental Association. J Am Dent Assoc 148:712–727e10. https://doi.org/10.1016/j.adaj.2017.07.032
doi: 10.1016/j.adaj.2017.07.032
pubmed: 28958308
Warnakulasuriya S, Johnson NW, Waal IVD (2007) Nomenclature and classification of potentially malignant disorders of the oral mucosa. J Oral Pathol Med 36:575–580. https://doi.org/10.1111/j.1600-0714.2007.00582.x
doi: 10.1111/j.1600-0714.2007.00582.x
pubmed: 17944749
Mello FW, Miguel AFP, Dutra KL et al (2018) Prevalence of oral potentially malignant disorders: a systematic review and meta-analysis. J Oral Pathol Med 47:633–640. https://doi.org/10.1111/jop.12726
doi: 10.1111/jop.12726
pubmed: 29738071
Meij EHVD, Waal IVD (2003) Lack of clinicopathologic correlation in the diagnosis of oral lichen planus based on the presently available diagnostic criteria and suggestions for modifications. J Oral Pathol Med 32:507–512. https://doi.org/10.1034/j.1600-0714.2003.00125.x
doi: 10.1034/j.1600-0714.2003.00125.x
pubmed: 12969224
Achararit P, Manaspon C, Jongwannasiri C et al (2023) Artificial Intelligence-based diagnosis of oral Lichen Planus using deep convolutional neural networks. Eur J Dent. https://doi.org/10.1055/s-0042-1760300
doi: 10.1055/s-0042-1760300
pubmed: 36669652
pmcid: 10756816
Carrozzo M (2008) How common is oral lichen planus? Évid-Based Dent 9:112–113. https://doi.org/10.1038/sj.ebd.6400614
doi: 10.1038/sj.ebd.6400614
pubmed: 19151683
Schruf E, Biermann MH, Jacob J et al (2022) Lichen Planus in Germany – epidemiology, treatment, and comorbidity. A retrospective claims data analysis. Jddg J Der Deutschen Dermatologischen Gesellschaft. https://doi.org/10.1111/ddg.14808
doi: 10.1111/ddg.14808
Iocca O, Sollecito TP, Alawi F et al (2020) Potentially malignant disorders of the oral cavity and oral dysplasia: a systematic review and meta-analysis of malignant transformation rate by subtype. Head Neck 42:539–555. https://doi.org/10.1002/hed.26006
doi: 10.1002/hed.26006
pubmed: 31803979
Holmstrup P, Vedtofte P, Reibel J, Stoltze K (2006) Long-term treatment outcome of oral premalignant lesions. Oral Oncol 42:461–474. https://doi.org/10.1016/j.oraloncology.2005.08.011
doi: 10.1016/j.oraloncology.2005.08.011
pubmed: 16316774
Chuang S-L, Wang C-P, Chen M-K et al (2018) Malignant transformation to oral cancer by subtype of oral potentially malignant disorder: a prospective cohort study of Taiwanese nationwide oral cancer screening program. Oral Oncol 87:58–63. https://doi.org/10.1016/j.oraloncology.2018.10.021
doi: 10.1016/j.oraloncology.2018.10.021
pubmed: 30527244
Feng J, Xu Z, Shi L et al (2013) Expression of cancer stem cell markers ALDH1 and Bmi1 in oral erythroplakia and the risk of oral cancer. J Oral Pathol Med 42:148–153. https://doi.org/10.1111/j.1600-0714.2012.01191.x
doi: 10.1111/j.1600-0714.2012.01191.x
pubmed: 22725270
Giuliani M, Troiano G, Cordaro M et al (2019) Rate of malignant transformation of oral lichen planus: a systematic review. Oral Dis 25:693–709. https://doi.org/10.1111/odi.12885
doi: 10.1111/odi.12885
pubmed: 29738106
Cabay RJ, Morton TH, Epstein JB (2007) Proliferative verrucous leukoplakia and its progression to oral carcinoma: a review of the literature. J Oral Pathol Med 36:255–261. https://doi.org/10.1111/j.1600-0714.2007.00506.x
doi: 10.1111/j.1600-0714.2007.00506.x
pubmed: 17448134
Parakh MK, Ulaganambi S, Ashifa N et al (2019) Oral potentially malignant disorders: clinical diagnosis and current screening aids: a narrative review. Eur J cancer Prev: off J Eur Cancer Prev Organ (ECP) 29:65–72. https://doi.org/10.1097/cej.0000000000000510
doi: 10.1097/cej.0000000000000510
Ramesh S, Nazeer SS, Thomas S et al (2021) Optical diagnosis of oral lichen planus: a clinical study on the use of autofluorescence spectroscopy combined with multivariate analysis. Spectrochim Acta Part A: Mol Biomol Spectrosc 248:119240. https://doi.org/10.1016/j.saa.2020.119240
doi: 10.1016/j.saa.2020.119240
Neumann FW, Neumann H, Spieth S, Remmerbach TW (2022) Retrospective evaluation of the oral brush biopsy in daily dental routine — an effective way of early cancer detection. Clin Oral Invest 1–7. https://doi.org/10.1007/s00784-022-04620-9
Rao RS, Chatura KR, SV S et al (2020) Procedures and pitfalls in incisional biopsies of oral squamous cell carcinoma with respect to histopathological diagnosis. Dis-a-Mon 66:101035. https://doi.org/10.1016/j.disamonth.2020.101035
doi: 10.1016/j.disamonth.2020.101035
Mehrotra R, Singh M, Thomas S et al (2010) A cross-sectional study evaluating chemiluminescence and autofluorescence in the detection of clinically innocuous precancerous and cancerous oral lesions. J Am Dent Assoc 141:151–156. https://doi.org/10.14219/jada.archive.2010.0132
doi: 10.14219/jada.archive.2010.0132
pubmed: 20123872
Keser G, Bayrakdar İŞ, Pekiner FN et al (2023) A deep learning algorithm for classification of oral lichen planus lesions from photographic images: a retrospective study. J Stomatology Oral Maxillofac Surg 124:101264. https://doi.org/10.1016/j.jormas.2022.08.007
doi: 10.1016/j.jormas.2022.08.007
Warin K, Limprasert W, Suebnukarn S et al (2022) AI-based analysis of oral lesions using novel deep convolutional neural networks for early detection of oral cancer. PLoS ONE 17:e0273508. https://doi.org/10.1371/journal.pone.0273508
doi: 10.1371/journal.pone.0273508
pubmed: 36001628
pmcid: 9401150
Welikala RA, Remagnino P, Lim JH et al (2020) Automated detection and classification of oral lesions using deep learning for early detection of oral Cancer. Ieee Access 8:132677–132693. https://doi.org/10.1109/access.2020.3010180
doi: 10.1109/access.2020.3010180
Shamim MZM, Syed S, Shiblee M et al (2020) Automated detection of oral pre-cancerous tongue lesions using deep learning for early diagnosis of oral Cavity Cancer. Comput J 65:91–104. https://doi.org/10.1093/comjnl/bxaa136
doi: 10.1093/comjnl/bxaa136
Song B, Sunny S, Uthoff RD et al (2018) Automatic classification of dual-modalilty, smartphone-based oral dysplasia and malignancy images using deep learning. Biomed Opt Express 9:5318. https://doi.org/10.1364/boe.9.005318
doi: 10.1364/boe.9.005318
pubmed: 30460130
pmcid: 6238918
Jubair F, Al-karadsheh O, Malamos D et al (2022) A novel lightweight deep convolutional neural network for early detection of oral cancer. Oral Dis 28:1123–1130. https://doi.org/10.1111/odi.13825
doi: 10.1111/odi.13825
pubmed: 33636041
A RNB GK, S CH, et al (2021) An Ensemble Deep Neural Network Approach for oral Cancer screening. Int J Online Biomed Eng (iJOE) 17:121–134. https://doi.org/10.3991/ijoe.v17i02.19207
doi: 10.3991/ijoe.v17i02.19207
Talwar V, Singh P, Mukhia N et al (2023) AI-Assisted screening of oral potentially malignant disorders using smartphone-based photographic images. Cancers 15:4120. https://doi.org/10.3390/cancers15164120
doi: 10.3390/cancers15164120
pubmed: 37627148
pmcid: 10452422
Flügge T, Gaudin R, Sabatakakis A et al (2023) Detection of oral squamous cell carcinoma in clinical photographs using a vision transformer. Sci Rep-uk 13:2296. https://doi.org/10.1038/s41598-023-29204-9
doi: 10.1038/s41598-023-29204-9
Seoane J, Takkouche B, Varela-Centelles P et al (2012) Impact of delay in diagnosis on survival to head and neck carcinomas: a systematic review with meta‐analysis. Clin Otolaryngol 37:99–106. https://doi.org/10.1111/j.1749-4486.2012.02464.x
doi: 10.1111/j.1749-4486.2012.02464.x
pubmed: 22429704
van Harten MC, de Ridder M, Hamming-Vrieze O et al (2014) The association of treatment delay and prognosis in head and neck squamous cell carcinoma (HNSCC) patients in a Dutch comprehensive cancer center. Oral Oncol 50:282–290. https://doi.org/10.1016/j.oraloncology.2013.12.018
doi: 10.1016/j.oraloncology.2013.12.018
pubmed: 24405882
Mazur M, Ndokaj A, Venugopal DC et al (2021) In vivo imaging-based techniques for early diagnosis of oral potentially malignant disorders—systematic review and Meta-analysis. Int J Environ Res Pu 18:11775. https://doi.org/10.3390/ijerph182211775
doi: 10.3390/ijerph182211775
Petruzzi M, Lucchese A, Nardi GM et al (2014) Evaluation of autofluorescence and toluidine blue in the differentiation of oral dysplastic and neoplastic lesions from non dysplastic and neoplastic lesions: a cross-sectional study. J Biomed Opt 19:076003–076003. https://doi.org/10.1117/1.jbo.19.7.076003
doi: 10.1117/1.jbo.19.7.076003
Warin K, Limprasert W, Suebnukarn S et al (2021) Performance of deep convolutional neural network for classification and detection of oral potentially malignant disorders in photographic images. Int J Oral Max Surg. https://doi.org/10.1016/j.ijom.2021.09.001
doi: 10.1016/j.ijom.2021.09.001
Santos VCA, Cardoso L, Alves R (2023) The quest for the reliability of machine learning models in binary classification on tabular data. Sci Rep 13:18464. https://doi.org/10.1038/s41598-023-45876-9
doi: 10.1038/s41598-023-45876-9
Kim K, Lee B, Kim JW (2017) Feasibility of Deep Learning algorithms for Binary classification problems. J Intell Inf Syst 23:95–108. https://doi.org/10.13088/jiis.2017.23.1.095
doi: 10.13088/jiis.2017.23.1.095
McParland H, Warnakulasuriya S (2021) Lichenoid morphology could be an early feature of oral proliferative verrucous leukoplakia. J Oral Pathol Med 50:229–235. https://doi.org/10.1111/jop.13129
doi: 10.1111/jop.13129
pubmed: 33185900