Artificial intelligence for classification and detection of oral mucosa lesions on photographs: a systematic review and meta-analysis

被引:12
作者
Rokhshad, Rata [1 ]
Mohammad-Rahimi, Hossein [1 ,2 ]
Price, Jeffery B. [3 ]
Shoorgashti, Reyhaneh [4 ]
Abbasiparashkouh, Zahra [5 ]
Esmaeili, Mahdieh [4 ]
Sarfaraz, Bita [2 ]
Rokhshad, Arad [4 ]
Motamedian, Saeed Reza [6 ,7 ]
Soltani, Parisa [8 ,10 ]
Schwendicke, Falk [1 ,9 ]
机构
[1] ITU WHO Focus Grp Hlth, Top Grp Dent Diagnost & Digital Dent, Berlin, Germany
[2] Shahid Beheshti Univ Med Sci, Sch Dent, Dept Orthodont, Daneshjoo Blvd,Evin,Shahid Chamran Highway, Tehran 1983963113, Iran
[3] Univ Maryland, Sch Dent, Dept Oncol & Diagnost Sci, 650 W Baltimore St, Baltimore, MD 21201 USA
[4] Islamic Azad Univ, Tehran Med Sci, Fac Dent, 9Th Neyestan, Tehran, Iran
[5] Univ British Columbia, Vancouver, BC V6T 1Z4, Canada
[6] Shahid Beheshti Univ Med Sci, Res Inst Dent Sci, Dentofacial Deform Res Ctr, Sch Dent, Daneshjoo Blvd,Evin,Shahid Chamran Highway, Tehran 1983963113, Iran
[7] Shahid Beheshti Univ Med Sci, Sch Dent, Dept Orthodont, Daneshjoo Blvd,Evin,Shahid Chamran Highway, Tehran 1983963113, Iran
[8] Isfahan Univ Med Sci, Dent Res Inst, Dent Implants Res Ctr, Sch Dent, Esfahan, Iran
[9] Charite Univ Med Berlin, Dept Oral Diagnost, Digital Hlth & Hlth Serv Res, Charitepl 1, D-10117 Berlin, Germany
[10] Univ Naples Federico II, Dept Neurosci Reprod & Odontostomatol Sci, Nepales, Italy
基金
英国科研创新办公室;
关键词
Artificial intelligence; Deep learning; Head and neck cancer; Machine learning; Oral cancer; Oral neoplasms; Precancerous conditions; POTENTIALLY MALIGNANT DISORDERS; NEURAL-NETWORKS; CANCER; PREDICTION;
D O I
10.1007/s00784-023-05475-4
中图分类号
R78 [口腔科学];
学科分类号
1003 ;
摘要
ObjectiveThis study aimed to review and synthesize studies using artificial intelligence (AI) for classifying, detecting, or segmenting oral mucosal lesions on photographs.Materials and methodInclusion criteria were (1) studies employing AI to (2) classify, detect, or segment oral mucosa lesions, (3) on oral photographs of human subjects. Included studies were assessed for risk of bias using Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). A PubMed, Scopus, Embase, Web of Science, IEEE, arXiv, medRxiv, and grey literature (Google Scholar) search was conducted until June 2023, without language limitation.ResultsAfter initial searching, 36 eligible studies (from 8734 identified records) were included. Based on QUADAS-2, only 7% of studies were at low risk of bias for all domains. Studies employed different AI models and reported a wide range of outcomes and metrics. The accuracy of AI for detecting oral mucosal lesions ranged from 74 to 100%, while that for clinicians un-aided by AI ranged from 61 to 98%. Pooled diagnostic odds ratio for studies which evaluated AI for diagnosing or discriminating potentially malignant lesions was 155 (95% confidence interval 23-1019), while that for cancerous lesions was 114 (59-221).ConclusionsAI may assist in oral mucosa lesion screening while the expected accuracy gains or further health benefits remain unclear so far.Clinical relevanceArtificial intelligence assists oral mucosa lesion screening and may foster more targeted testing and referral in the hands of non-specialist providers, for example. So far, it remains unclear if accuracy gains compared with specialized can be realized.
引用
收藏
页数:19
相关论文
共 69 条
[1]   Artificial Intelligence-Based Diagnosis of Oral Lichen Planus Using Deep Convolutional Neural Networks [J].
Achararit, Paniti ;
Manaspon, Chawan ;
Jongwannasiri, Chavin ;
Phattarataratip, Ekarat ;
Osathanon, Thanaphum ;
Sappayatosok, Kraisorn .
EUROPEAN JOURNAL OF DENTISTRY, 2023, 17 (04) :1275-1282
[2]   Deep Learning Predicts the Malignant-Transformation-Free Survival of Oral Potentially Malignant Disorders [J].
Adeoye, John ;
Koohi-Moghadam, Mohamad ;
Lo, Anthony Wing Ip ;
Tsang, Raymond King-Yin ;
Chow, Velda Ling Yu ;
Zheng, Li-Wu ;
Choi, Siu-Wai ;
Thomson, Peter ;
Su, Yu-Xiong .
CANCERS, 2021, 13 (23)
[3]   Malignant transformation of oral leukoplakia: Systematic review and meta-analysis of the last 5 years [J].
Aguirre-Urizar, Jose M. ;
Lafuente-Ibanez de Mendoza, Irene ;
Warnakulasuriya, Saman .
ORAL DISEASES, 2021, 27 (08) :1881-1895
[4]   The Effectiveness of Artificial Intelligence in Detection of Oral Cancer [J].
Al-Rawi, Natheer ;
Sultan, Afrah ;
Rajai, Batool ;
Shuaeeb, Haneen ;
Alnajjar, Mariam ;
Alketbi, Maryam ;
Mohammad, Yara ;
Shetty, Shishir Ram ;
Mashrah, Mubarak Ahmed .
INTERNATIONAL DENTAL JOURNAL, 2022, 72 (04) :436-447
[5]   Machine learning in oral squamous cell carcinoma: Current status, clinical concerns and prospects for future-A systematic review [J].
Alabi, Rasheed Omobolaji ;
Youssef, Omar ;
Pirinen, Matti ;
Elmusrati, Mohammed ;
Makitie, Antti A. ;
Leivo, Ilmo ;
Almangush, Alhadi .
ARTIFICIAL INTELLIGENCE IN MEDICINE, 2021, 115
[6]   Machine learning application for prediction of locoregional recurrences in early oral tongue cancer: a Web-based prognostic tool [J].
Alabi, Rasheed Omobolaji ;
Elmusrati, Mohammed ;
Sawazaki-Calone, Iris ;
Kowalski, Luiz Paulo ;
Haglund, Caj ;
Coletta, Ricardo D. ;
Makitie, Antti A. ;
Salo, Tuula ;
Leivo, Ilmo ;
Almangush, Alhadi .
VIRCHOWS ARCHIV, 2019, 475 (04) :489-497
[7]   Application of artificial intelligence and machine learning for prediction of oral cancer risk [J].
Alhazmi, Anwar ;
Alhazmi, Yaser ;
Makrami, Ali ;
Masmali, Amal ;
Salawi, Nourah ;
Masmali, Khulud ;
Patil, Shankargouda .
JOURNAL OF ORAL PATHOLOGY & MEDICINE, 2021, 50 (05) :444-450
[8]   Oral mucosal lesions in teenagers: a cross-sectional study [J].
Amadori, Francesca ;
Bardellini, Elena ;
Conti, Giulio ;
Majorana, Alessandra .
ITALIAN JOURNAL OF PEDIATRICS, 2017, 43
[9]  
Anantharaman R, 2018, IEEE INT C BIOINFORM, P2197, DOI 10.1109/BIBM.2018.8621112
[10]   Malignant transformation risk of oral lichen planus: A systematic review and comprehensive meta-analysis [J].
Angel Gonzalez-Moles, Miguel ;
Ruiz-Avila, Isabel ;
Gonzalez-Ruiz, Lucia ;
Ayen, Angela ;
Antonio Gil-Montoya, Jose ;
Ramos-Garcia, Pablo .
ORAL ONCOLOGY, 2019, 96 :121-130