Detection of Elementary White Mucosal Lesions by an AI System: A Pilot Study
<b>Aim:</b> Accurately identifying primary lesions in oral medicine, particularly elementary white lesions, is a significant challenge, especially for trainee dentists. This study aimed to develop and evaluate a deep learning (DL) model for the detection and classification of elementary...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Oral |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-6373/4/4/43 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850060055473291264 |
|---|---|
| author | Gaetano La Mantia Federico Kiswarday Giuseppe Pizzo Giovanna Giuliana Giacomo Oteri Mario G. C. A. Cimino Olga Di Fede Giuseppina Campisi |
| author_facet | Gaetano La Mantia Federico Kiswarday Giuseppe Pizzo Giovanna Giuliana Giacomo Oteri Mario G. C. A. Cimino Olga Di Fede Giuseppina Campisi |
| author_sort | Gaetano La Mantia |
| collection | DOAJ |
| description | <b>Aim:</b> Accurately identifying primary lesions in oral medicine, particularly elementary white lesions, is a significant challenge, especially for trainee dentists. This study aimed to develop and evaluate a deep learning (DL) model for the detection and classification of elementary white mucosal lesions (EWMLs) using clinical images. <b>Materials and Methods:</b> A dataset was created by collecting photographs of various oral lesions, including oral leukoplakia, OLP plaque-like and reticular forms, OLL, oral candidiasis, and hyperkeratotic lesions from the Unit of Oral Medicine. The SentiSight.AI (Neurotechnology Co.<sup>®</sup>, Vilnius, Lithuania) AI platform was used for image labeling and model training. The dataset comprised 221 photos, divided into training (<i>n</i> = 179) and validation (<i>n</i> = 42) sets. <b>Results:</b> The model achieved an overall precision of 77.2%, sensitivity of 76.0%, F1 score of 74.4%, and mAP of 82.3%. Specific classes, such as condyloma and papilloma, demonstrated high performance, while others like leucoplakia showed room for improvement. <b>Conclusions:</b> The DL model showed promising results in detecting and classifying EWMLs, with significant potential for educational tools and clinical applications. Expanding the dataset and incorporating diverse image sources are essential for improving model accuracy and generalizability. |
| format | Article |
| id | doaj-art-e8a88d1bb887400d9d79007d189696ab |
| institution | DOAJ |
| issn | 2673-6373 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Oral |
| spelling | doaj-art-e8a88d1bb887400d9d79007d189696ab2025-08-20T02:50:42ZengMDPI AGOral2673-63732024-11-014455756610.3390/oral4040043Detection of Elementary White Mucosal Lesions by an AI System: A Pilot StudyGaetano La Mantia0Federico Kiswarday1Giuseppe Pizzo2Giovanna Giuliana3Giacomo Oteri4Mario G. C. A. Cimino5Olga Di Fede6Giuseppina Campisi7Unit of Oral Medicine and Dentistry for Fragile Patients, Department of Rehabilitation, Fragility and Continuity of Care University Hospital “Policlinico Paolo Giaccone”, 90127 Palermo, ItalyDegree in Dentistry, School of Medicine and Surgery, University of Palermo, 90127 Palermo, ItalyUnit of Oral Medicine and Dentistry for Fragile Patients, Department of Rehabilitation, Fragility and Continuity of Care University Hospital “Policlinico Paolo Giaccone”, 90127 Palermo, ItalyDepartment of Precision Medicine in Medical, Surgical and Critical Care (Me.Pre.C.C.), University of Palermo, 90127 Palermo, ItalyDepartment of Biomedical and Dental Sciences, Morphological and Functional Images, University of Messina, 98124 Messina, ItalyDepartment of Information Engineering, University of Pisa, 56122 Pisa, ItalyDepartment of Precision Medicine in Medical, Surgical and Critical Care (Me.Pre.C.C.), University of Palermo, 90127 Palermo, ItalyUnit of Oral Medicine and Dentistry for Fragile Patients, Department of Rehabilitation, Fragility and Continuity of Care University Hospital “Policlinico Paolo Giaccone”, 90127 Palermo, Italy<b>Aim:</b> Accurately identifying primary lesions in oral medicine, particularly elementary white lesions, is a significant challenge, especially for trainee dentists. This study aimed to develop and evaluate a deep learning (DL) model for the detection and classification of elementary white mucosal lesions (EWMLs) using clinical images. <b>Materials and Methods:</b> A dataset was created by collecting photographs of various oral lesions, including oral leukoplakia, OLP plaque-like and reticular forms, OLL, oral candidiasis, and hyperkeratotic lesions from the Unit of Oral Medicine. The SentiSight.AI (Neurotechnology Co.<sup>®</sup>, Vilnius, Lithuania) AI platform was used for image labeling and model training. The dataset comprised 221 photos, divided into training (<i>n</i> = 179) and validation (<i>n</i> = 42) sets. <b>Results:</b> The model achieved an overall precision of 77.2%, sensitivity of 76.0%, F1 score of 74.4%, and mAP of 82.3%. Specific classes, such as condyloma and papilloma, demonstrated high performance, while others like leucoplakia showed room for improvement. <b>Conclusions:</b> The DL model showed promising results in detecting and classifying EWMLs, with significant potential for educational tools and clinical applications. Expanding the dataset and incorporating diverse image sources are essential for improving model accuracy and generalizability.https://www.mdpi.com/2673-6373/4/4/43mouth diseaseoral keratosisoral leukokeratosisoral leukoplakiaArtificial Intelligence (AI)deep learning |
| spellingShingle | Gaetano La Mantia Federico Kiswarday Giuseppe Pizzo Giovanna Giuliana Giacomo Oteri Mario G. C. A. Cimino Olga Di Fede Giuseppina Campisi Detection of Elementary White Mucosal Lesions by an AI System: A Pilot Study Oral mouth disease oral keratosis oral leukokeratosis oral leukoplakia Artificial Intelligence (AI) deep learning |
| title | Detection of Elementary White Mucosal Lesions by an AI System: A Pilot Study |
| title_full | Detection of Elementary White Mucosal Lesions by an AI System: A Pilot Study |
| title_fullStr | Detection of Elementary White Mucosal Lesions by an AI System: A Pilot Study |
| title_full_unstemmed | Detection of Elementary White Mucosal Lesions by an AI System: A Pilot Study |
| title_short | Detection of Elementary White Mucosal Lesions by an AI System: A Pilot Study |
| title_sort | detection of elementary white mucosal lesions by an ai system a pilot study |
| topic | mouth disease oral keratosis oral leukokeratosis oral leukoplakia Artificial Intelligence (AI) deep learning |
| url | https://www.mdpi.com/2673-6373/4/4/43 |
| work_keys_str_mv | AT gaetanolamantia detectionofelementarywhitemucosallesionsbyanaisystemapilotstudy AT federicokiswarday detectionofelementarywhitemucosallesionsbyanaisystemapilotstudy AT giuseppepizzo detectionofelementarywhitemucosallesionsbyanaisystemapilotstudy AT giovannagiuliana detectionofelementarywhitemucosallesionsbyanaisystemapilotstudy AT giacomooteri detectionofelementarywhitemucosallesionsbyanaisystemapilotstudy AT mariogcacimino detectionofelementarywhitemucosallesionsbyanaisystemapilotstudy AT olgadifede detectionofelementarywhitemucosallesionsbyanaisystemapilotstudy AT giuseppinacampisi detectionofelementarywhitemucosallesionsbyanaisystemapilotstudy |