The use of artificial intelligence in the diagnosis of odontogenic cysts and tumors

Lucas Lacerda de Souza; Ana Luiza Oliveira Corrêa Roza; Daniela Giraldo-Roldán; Ivan José Correia-Neto; Marcio Ajudarte Lopes; Syed Ali Khurram; Pablo Agustin Vargas

doi:10.5327/2525-5711.289

Authors

Lucas Lacerda de Souza University of Campinas, Piracicaba Dental School, Department of Oral Diagnosis – Piracicaba (SP), Brazil. https://orcid.org/0000-0002-9481-7796
Ana Luiza Oliveira Corrêa Roza University of Campinas, Piracicaba Dental School, Department of Oral Diagnosis – Piracicaba (SP), Brazil. https://orcid.org/0000-0002-4463-9602
Daniela Giraldo-Roldán University of Campinas, Piracicaba Dental School, Department of Oral Diagnosis – Piracicaba (SP), Brazil. https://orcid.org/0000-0001-7150-3025
Ivan José Correia-Neto University of Campinas, Piracicaba Dental School, Department of Oral Diagnosis – Piracicaba (SP), Brazil. https://orcid.org/0009-0007-3828-0107
Marcio Ajudarte Lopes University of Campinas, Piracicaba Dental School, Department of Oral Diagnosis – Piracicaba (SP), Brazil. https://orcid.org/0000-0001-6677-0065
Syed Ali Khurram University of Sheffield, Faculty of Health, School of Clinical Dentistry – England. https://orcid.org/0000-0002-0378-9380
Pablo Agustin Vargas University of Campinas, Piracicaba Dental School, Department of Oral Diagnosis – Piracicaba (SP), Brazil. https://orcid.org/0000-0003-1840-4911

DOI:

https://doi.org/10.5327/2525-5711.289

Keywords:

Artificial intelligence, machine learning, deep learning, Odontogenic cysts, Tumors

Abstract

The application of artificial intelligence (AI) in healthcare has garnered growing interest, particularly for its ability to improve diagnostic accuracy and streamline clinical workflows. This literature review examines the latest advancements and ongoing challenges in the use of AI for diagnosing odontogenic cysts and tumors. These lesions, originating from odontogenic epithelium or ectomesenchyme, present with a wide range of clinical and radiographic features that often overlap, complicating accurate diagnosis. AI, particularly through machine learning (ML) and deep learning (DL) models, offers promising solutions to these challenges by enhancing automation and precision in diagnostic processes. Numerous studies have highlighted the potential of AI algorithms to analyze various imaging modalities, such as radiographs, computed tomography (CT), and histopathological slides, achieving diagnostic outcomes comparable to those of expert clinicians. These AI systems have been designed to identify key radiological and histopathological characteristics, enabling earlier and more accurate detection of odontogenic lesions. Despite these promising results, significant challenges persist, such as the need for larger, more diverse datasets, the establishment of standardized protocols, and the seamless integration of AI tools into existing clinical practices.

References

Johnson NR, Gannon OM, Savage NW, Batstone MD. Frequency of odontogenic cysts and tumors: a systematic review. J Investig Clin Dent. 2014;5(1):9-14. https://doi.org/10.1111/jicd.12044

El-Gehani R, Orafi M, Elarbi M, Subhashraj K. Benign tumours of orofacial region at Benghazi, Libya: a study of 405 cases. J Craniomaxillofac Surg. 2009;37(7):370-5. https://doi.org/10.1016/j.jcms.2009.02.003

Kokubun K, Yamamoto K, Nakajima K, Akashi Y, Chujo T, Takano M, et al. Frequency of odontogenic tumors: a single center study of 1089 cases in Japan and literature review. Head Neck Pathol. 2022;16(2):494-502. https://doi.org/10.1007/s12105-021-01390-w

Osterne RLV, Brito RGM, Alves APNN, Cavalcante RB, Sousa FB. Odontogenic tumors: a 5-year retrospective study in a Brazilian population and analysis of 3406 cases reported in the literature. Oral Surg Oral Med Oral Pathol Oral Radiol Endod. 2011;111(4):474-81. https://doi.org/10.1016/j.tripleo.2010.10.018

Souza LL, Santos-Silva AR, Hagag A, Alzahem A, Vargas PA, Lopes MA. Evaluating AI models in head and neck cancer research: the use of NCI data by ChatGPT 3.5, ChatGPT 4.0, Google Bard, and Bing Chat. Oral Surg Oral Med Oral Pathol Oral Radiol. 2024;138(3):453-7. https://doi.org/10.1016/j.oooo.2024.05.012

Kang J, Le VNT, Lee DW, Kim S. Diagnosing oral and maxillofacial diseases using deep learning. Sci Rep. 2024;14(1):2497. https://doi.org/10.1038/s41598-024-52929-0

Kise Y, Ariji Y, Kuwada C, Fukuda M, Ariji E. Effect of deep transfer learning with a different kind of lesion on classification performance of pre-trained model: Verification with radiolucent lesions on panoramic radiographs. Imaging Sci Dent. 2023;53(1):27-34. https://doi.org/10.5624/isd.20220133

Watanabe H, Ariji Y, Fukuda M, Kuwada C, Kise Y, Nozawa M, et al. Deep learning object detection of maxillary cyst-like lesions on panoramic radiographs: preliminary study. Oral Radiol. 2021;37(3):487-93. https://doi.org/10.1007/s11282-020-00485-4

Souza LL, Fonseca FP, Araújo ALD, Lopes MA, Vargas PA, Khurram AS, et al. Machine learning for detection and classification of oral potentially malignant disorders: a conceptual review. J Oral Pathol Med. 2023;52(3):197-205. https://doi.org/10.1111/jop.13414

Fang S, Wang Y, He Y, Yu T, Xie Y, Cai Y, et al. Machine learning model based on radiomics for preoperative differentiation of jaw cystic lesions. Otolaryngol Head Neck Surg. 2024;170(6):1561-9. https://doi.org/10.1002/ohn.744

Pakdemirli E. A preliminary glossary of artificial intelligence in radiology. Acta Radiol Open. 2019;8(7):2058460119863379. https://doi.org/10.1177/2058460119863379

Mahmood H, Shaban M, Indave BI, Santos-Silva AR, Rajpoot N, Khurram SA. Use of artificial intelligence in diagnosis of head and neck precancerous and cancerous lesions: a systematic review. Oral Oncol. 2020;110:104885. https://doi.org/10.1016/j.oraloncology.2020.104885

Moglia A, Georgiou K, Morelli L, Toutouzas K, Satava RM, Cuschieri A. Breaking down the silos of artificial intelligence in surgery: glossary of terms. Surg Endosc. 2022;36(11):7986-97. https://doi.org/10.1007/s00464-022-09371-y

Abdolali F, Zoroofi RA, Otake Y, Sato Y. Automated classification of maxillofacial cysts in cone beam CT images using contourlet transformation and Spherical Harmonics. Comput Methods Programs Biomed. 2017;139:197-207. https://doi.org/10.1016/j.cmpb.2016.10.024

Yilmaz E, Kayikcioglu T, Kayipmaz S. Computer-aided diagnosis of periapical cyst and keratocystic odontogenic tumor on cone beam computed tomography. Comput Methods Programs Biomed. 2017;146:91-100. https://doi.org/10.1016/j.cmpb.2017.05.012

Poedjiastoeti W, Suebnukarn S. Application of convolutional neural network in the diagnosis of jaw tumors. Healthc Inform Res. 2018;24(3):236-41. https://doi.org/10.4258/hir.2018.24.3.236

Ariji Y, Yanashita Y, Kutsuna S, Muramatsu C, Fukuda M, Kise Y, et al. Automatic detection and classification of radiolucent lesions in the mandible on panoramic radiographs using a deep learning object detection technique. Oral Surg Oral Med Oral Pathol Oral Radiol. 2019;128(4):424-30. https://doi.org/10.1016/j.oooo.2019.05.014

Lee JH, Kim DH, Jeong SN. Diagnosis of cystic lesions using panoramic and cone beam computed tomographic images based on deep learning neural network. Oral Dis. 2020;26(1):152-8. https://doi.org/10.1111/odi.13223

Lee A, Kim MS, Han SS, Park P, Lee C, Yun JP. Deep learning neural networks to differentiate Stafne's bone cavity from pathological radiolucent lesions of the mandible in heterogeneous panoramic radiography. PLoS One. 2021;16(7):e0254997. https://doi.org/10.1371/journal.pone.0254997

Okazaki S, Mine Y, Iwamoto Y, Urabe S, Mitsuhata C, Nomura R, et al. Analysis of the feasibility of using deep learning for multiclass classification of dental anomalies on panoramic radiographs. Dent Mater J. 2022;41(6):889-95. https://doi.org/10.4012/dmj.2022-098

Li W, Li Y, Liu X, Wang L, Chen W, Qian X, et al. Machine learning-based radiomics for predicting BRAF-V600E mutations in ameloblastoma. Front Immunol. 2023;14:1180908. https://doi.org/10.3389/fimmu.2023.1180908

Huang Z, Li B, Cheng Y, Kim J. Odontogenic cystic lesion segmentation on cone-beam CT using an auto-adapting multi-scaled UNet. Front Oncol. 2024;14:1379624. https://doi.org/10.3389/fonc.2024.137962

Liu W, Li X, Liu C, Gao G, Xiong Y, Zhu T, et al. Automatic classification and segmentation of multiclass jaw lesions in cone-beam CT using deep learning. Dentomaxillofac Radiol. 2024;53(7):439-46. https://doi.org/10.1093/dmfr/twae028

Song Y, Ma S, Mao B, Xu K, Liu Y, Ma J, et al. Application of machine learning in the preoperative radiomic diagnosis of ameloblastoma and odontogenic keratocyst based on cone-beam CT. Dentomaxillofac Radiol. 2024;53(5):316-24. https://doi.org/10.1093/dmfr/twae016

Eramian M, Daley M, Neilson D, Daley T. Segmentation of epithelium in H&E stained odontogenic cysts. J Microsc. 2011;244(3):273-92. https://doi.org/10.1111/j.1365-2818.2011.03535.x

Giraldo-Roldan D, Ribeiro ECC, Araújo ALD, Penafort PVM, Silva VM, Câmara J, et al. Deep learning applied to the histopathological diagnosis of ameloblastomas and ameloblastic carcinomas. J Oral Pathol Med. 2023;52(10):988-95. https://doi.org/10.1111/jop.13481

Mohanty S, Shivanna DB, Rao RS, Astekar M, Chandrashekar C, Radhakrishnan R, et al. Development of automated risk stratification for sporadic odontogenic keratocyst whole slide images with an attention-based image sequence analyzer. Diagnostics (Basel). 2023;13(23):3539. https://doi.org/10.3390/diagnostics13233539

Kim P, Seo B, Silva H. Concordance of clinician, Chat-GPT4, and ORAD diagnoses against histopathology in Odontogenic Keratocysts and tumours: a 15-year New Zealand retrospective study. Oral Maxillofac Surg. 2024;28(4):1557-69. https://doi.org/10.1007/s10006-024-01284-5

Zhang AB, Zhang JY, Liu YP, Wang S, Bai JY, Sun LS, et al. Clinicopathological characteristics and diagnostic accuracy of BRAF mutations in ameloblastoma: a Bayesian network analysis. J Oral Pathol Med. 2024;53(6):393-403. https://doi.org/10.1111/jop.13542

Mann M, Kumar C, Zeng WF, Strauss MT. Artificial intelligence for proteomics and biomarker discovery. Cell Syst. 2021;12(8):759-70. https://doi.org/10.1016/j.cels.2021.06.006