The application of deep learning in early enamel demineralization detection
Objective The study aims to develop a diagnostic model using intraoral photographs to accurately detect and classify early detection of enamel demineralization on tooth surfaces. Methods A retrospective analysis was conducted with 208 patients aged 14 to 44. A total of 624 high-quality digital image...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2025-01-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/18593.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841560264449720320 |
|---|---|
| author | Ketai He Rongxiu Zhang Muchun Liang Keyue Tian Kaihui Luo Ruoshi Chen Jianpeng Ren Jiajun Wang Juan Li |
| author_facet | Ketai He Rongxiu Zhang Muchun Liang Keyue Tian Kaihui Luo Ruoshi Chen Jianpeng Ren Jiajun Wang Juan Li |
| author_sort | Ketai He |
| collection | DOAJ |
| description | Objective The study aims to develop a diagnostic model using intraoral photographs to accurately detect and classify early detection of enamel demineralization on tooth surfaces. Methods A retrospective analysis was conducted with 208 patients aged 14 to 44. A total of 624 high-quality digital images captured under standardized conditions were used to construct a deep learning model based on the Mask region-based convolutional neural network (Mask R-CNN). The model was trained to automate the detection of enamel demineralization. Its performance was compared to two junior dentists’ diagnostic abilities. Results The model achieved an F1-score of 0.856 for detecting demineralized teeth on the validation set, a metric that reflects comprehensive diagnostic performance, demonstrating performance close to that of senior dentists. With the the model’s assistance, the junior dentists’ average F1-scores improved significantly—from 0.713 and 0.689 to 0.897 and 0.949, respectively (p < 0.05). The model accurately segmented tooth surfaces and detected demineralized areas, allowing for precise detection of demineralized areas and monitoring of lesion progression. Conclusion Deep learning can accurately segment tooth surfaces and lesion contours, enhancing the precision, accuracy, and efficiency of enamel demineralization diagnosis and area delineation. |
| format | Article |
| id | doaj-art-4479eb2341ec4a2496460e3da7626a58 |
| institution | Kabale University |
| issn | 2167-8359 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj-art-4479eb2341ec4a2496460e3da7626a582025-01-04T15:05:20ZengPeerJ Inc.PeerJ2167-83592025-01-0113e1859310.7717/peerj.18593The application of deep learning in early enamel demineralization detectionKetai He0Rongxiu Zhang1Muchun Liang2Keyue Tian3Kaihui Luo4Ruoshi Chen5Jianpeng Ren6Jiajun Wang7Juan Li8State Key Laboratory of Oral Diseases & National Center for Stomatology & National Clinical Research Center for Oral Diseases, West China Hospital of Stomatology, Sichuan University, Chengdu, ChinaDepartment of Stomatology, The First Affiliated Hospital of Bengbu Medical University, Chengdu, ChinaState Key Laboratory of Oral Diseases & National Center for Stomatology & National Clinical Research Center for Oral Diseases, West China Hospital of Stomatology, Sichuan University, Chengdu, ChinaState Key Laboratory of Oral Diseases & National Center for Stomatology & National Clinical Research Center for Oral Diseases, West China Hospital of Stomatology, Sichuan University, Chengdu, ChinaState Key Laboratory of Oral Diseases & National Center for Stomatology & National Clinical Research Center for Oral Diseases, West China Hospital of Stomatology, Sichuan University, Chengdu, ChinaChengdu Boltzmann Intelligence Technology Co., Ltd, Chengdu, ChinaChengdu Boltzmann Intelligence Technology Co., Ltd, Chengdu, ChinaCollege of Software, Sichuan University, Chengdu, ChinaState Key Laboratory of Oral Diseases & National Center for Stomatology & National Clinical Research Center for Oral Diseases, West China Hospital of Stomatology, Sichuan University, Chengdu, ChinaObjective The study aims to develop a diagnostic model using intraoral photographs to accurately detect and classify early detection of enamel demineralization on tooth surfaces. Methods A retrospective analysis was conducted with 208 patients aged 14 to 44. A total of 624 high-quality digital images captured under standardized conditions were used to construct a deep learning model based on the Mask region-based convolutional neural network (Mask R-CNN). The model was trained to automate the detection of enamel demineralization. Its performance was compared to two junior dentists’ diagnostic abilities. Results The model achieved an F1-score of 0.856 for detecting demineralized teeth on the validation set, a metric that reflects comprehensive diagnostic performance, demonstrating performance close to that of senior dentists. With the the model’s assistance, the junior dentists’ average F1-scores improved significantly—from 0.713 and 0.689 to 0.897 and 0.949, respectively (p < 0.05). The model accurately segmented tooth surfaces and detected demineralized areas, allowing for precise detection of demineralized areas and monitoring of lesion progression. Conclusion Deep learning can accurately segment tooth surfaces and lesion contours, enhancing the precision, accuracy, and efficiency of enamel demineralization diagnosis and area delineation.https://peerj.com/articles/18593.pdfArtificial intelligenceDiagnostic imagingDeep learningTooth demineralization |
| spellingShingle | Ketai He Rongxiu Zhang Muchun Liang Keyue Tian Kaihui Luo Ruoshi Chen Jianpeng Ren Jiajun Wang Juan Li The application of deep learning in early enamel demineralization detection PeerJ Artificial intelligence Diagnostic imaging Deep learning Tooth demineralization |
| title | The application of deep learning in early enamel demineralization detection |
| title_full | The application of deep learning in early enamel demineralization detection |
| title_fullStr | The application of deep learning in early enamel demineralization detection |
| title_full_unstemmed | The application of deep learning in early enamel demineralization detection |
| title_short | The application of deep learning in early enamel demineralization detection |
| title_sort | application of deep learning in early enamel demineralization detection |
| topic | Artificial intelligence Diagnostic imaging Deep learning Tooth demineralization |
| url | https://peerj.com/articles/18593.pdf |
| work_keys_str_mv | AT ketaihe theapplicationofdeeplearninginearlyenameldemineralizationdetection AT rongxiuzhang theapplicationofdeeplearninginearlyenameldemineralizationdetection AT muchunliang theapplicationofdeeplearninginearlyenameldemineralizationdetection AT keyuetian theapplicationofdeeplearninginearlyenameldemineralizationdetection AT kaihuiluo theapplicationofdeeplearninginearlyenameldemineralizationdetection AT ruoshichen theapplicationofdeeplearninginearlyenameldemineralizationdetection AT jianpengren theapplicationofdeeplearninginearlyenameldemineralizationdetection AT jiajunwang theapplicationofdeeplearninginearlyenameldemineralizationdetection AT juanli theapplicationofdeeplearninginearlyenameldemineralizationdetection AT ketaihe applicationofdeeplearninginearlyenameldemineralizationdetection AT rongxiuzhang applicationofdeeplearninginearlyenameldemineralizationdetection AT muchunliang applicationofdeeplearninginearlyenameldemineralizationdetection AT keyuetian applicationofdeeplearninginearlyenameldemineralizationdetection AT kaihuiluo applicationofdeeplearninginearlyenameldemineralizationdetection AT ruoshichen applicationofdeeplearninginearlyenameldemineralizationdetection AT jianpengren applicationofdeeplearninginearlyenameldemineralizationdetection AT jiajunwang applicationofdeeplearninginearlyenameldemineralizationdetection AT juanli applicationofdeeplearninginearlyenameldemineralizationdetection |