Optimal Training Positive Sample Size Determination for Deep Learning with a Validation on CBCT Image Caries Recognition

Overview

Journal Diagnostics (Basel)

Specialty Radiology

Date 2024 Sep 28

PMID 39335759

Authors

Yanlin Wang

Gang Li

Xinyue Zhang

Yue Wang

Zhenhao Zhang

Jupeng Li

Junqi Ma

Linghang Wang

Affiliations

Soon will be listed here.

Abstract

: During deep learning model training, it is essential to consider the balance among the effects of sample size, actual resources, and time constraints. Single-arm objective performance criteria (OPC) was proposed to determine the optimal positive sample size for training deep learning models in caries recognition. : An expected sensitivity (P) of 0.6 and a clinically acceptable sensitivity (P) of 0.5 were applied to the single-arm OPC calculation formula, yielding an optimal training set comprising 263 carious teeth. U-Net, YOLOv5n, and CariesDetectNet were trained and validated using clinically self-collected cone-beam computed tomography (CBCT) images that included varying quantities of carious teeth. To assess performance, an additional dataset was utilized to evaluate the accuracy of caries detection by both the models and two dental radiologists. : When the number of carious teeth reached approximately 250, the models reached the optimal performance levels. U-Net demonstrated superior performance, achieving accuracy, sensitivity, specificity, F1-Score, and Dice similarity coefficients of 0.9929, 0.9307, 0.9989, 0.9590, and 0.9435, respectively. The three models exhibited greater accuracy in caries recognition compared to dental radiologists. : This study demonstrated that the positive sample size of CBCT images containing caries was predictable and could be calculated using single-arm OPC.

References

Chan H, Sahiner B, Wagner R, Petrick N . Classifier design for computer-aided diagnosis: effects of finite sample size on the mean performance of classical and neural network classifiers. Med Phys. 2000; 26(12):2654-68. DOI: 10.1118/1.598805. View

Li M, Mu C, Zhang J, Li G . [Application of Deep Learning in Differential Diagnosis of Ameloblastoma and Odontogenic Keratocyst Based on Panoramic Radiographs]. Zhongguo Yi Xue Ke Xue Yuan Xue Bao. 2023; 45(2):273-279. DOI: 10.3881/j.issn.1000-503X.15139. View

Seker O, Kamburoglu K, Sahin C, Eratam N, Cakmak E, Sonmez G . In vitro comparison of high-definition US, CBCT and periapical radiography in the diagnosis of proximal and recurrent caries. Dentomaxillofac Radiol. 2021; 50(8):20210026. PMC: 8611281. DOI: 10.1259/dmfr.20210026. View

Ezhov M, Gusarev M, Golitsyna M, Yates J, Kushnerev E, Tamimi D . Clinically applicable artificial intelligence system for dental diagnosis with CBCT. Sci Rep. 2021; 11(1):15006. PMC: 8298426. DOI: 10.1038/s41598-021-94093-9. View

Park S, Sukthankar R, Mummert L, Satyanarayanan M, Zheng B . Optimization of reference library used in content-based medical image retrieval scheme. Med Phys. 2007; 34(11):4331-9. PMC: 2211736. DOI: 10.1118/1.2795826. View

Gulum S, Kutal S, Cesur Aydin K, Akgun G, Akdag A . Effect of data size on tooth numbering performance via artificial intelligence using panoramic radiographs. Oral Radiol. 2023; 39(4):715-721. DOI: 10.1007/s11282-023-00689-4. View

Takebe K, Imai T, Kubota S, Nishimoto A, Amekawa S, Uzawa N . Deep learning model for the automated evaluation of contact between the lower third molar and inferior alveolar nerve on panoramic radiography. J Dent Sci. 2023; 18(3):991-996. PMC: 10316438. DOI: 10.1016/j.jds.2022.12.008. View

Li S, Liu J, Zhou Z, Zhou Z, Wu X, Li Y . Artificial intelligence for caries and periapical periodontitis detection. J Dent. 2022; 122:104107. DOI: 10.1016/j.jdent.2022.104107. View

Bui T, Hamamoto K, Paing M . Automated Caries Screening Using Ensemble Deep Learning on Panoramic Radiographs. Entropy (Basel). 2023; 24(10). PMC: 9601088. DOI: 10.3390/e24101358. View

10.

Sahiner B, Chan H, Petrick N, Wagner R, Hadjiiski L . Feature selection and classifier performance in computer-aided diagnosis: the effect of finite sample size. Med Phys. 2000; 27(7):1509-22. PMC: 5713476. DOI: 10.1118/1.599017. View

11.

Dayi B, Uzen H, Cicek I, Duman S . A Novel Deep Learning-Based Approach for Segmentation of Different Type Caries Lesions on Panoramic Radiographs. Diagnostics (Basel). 2023; 13(2). PMC: 9858411. DOI: 10.3390/diagnostics13020202. View

12.

Duan W, Chen Y, Zhang Q, Lin X, Yang X . Refined tooth and pulp segmentation using U-Net in CBCT image. Dentomaxillofac Radiol. 2021; 50(6):20200251. PMC: 8404523. DOI: 10.1259/dmfr.20200251. View

13.

Lee J, Kim D, Jeong S, Choi S . Detection and diagnosis of dental caries using a deep learning-based convolutional neural network algorithm. J Dent. 2018; 77:106-111. DOI: 10.1016/j.jdent.2018.07.015. View

14.

Lee S, Oh S, Jo J, Kang S, Shin Y, Park J . Deep learning for early dental caries detection in bitewing radiographs. Sci Rep. 2021; 11(1):16807. PMC: 8376948. DOI: 10.1038/s41598-021-96368-7. View

15.

Gomez J . Detection and diagnosis of the early caries lesion. BMC Oral Health. 2015; 15 Suppl 1:S3. PMC: 4580848. DOI: 10.1186/1472-6831-15-S1-S3. View

16.

Baydar O, Rozylo-Kalinowska I, Futyma-Gabka K, Saglam H . The U-Net Approaches to Evaluation of Dental Bite-Wing Radiographs: An Artificial Intelligence Study. Diagnostics (Basel). 2023; 13(3). PMC: 9914538. DOI: 10.3390/diagnostics13030453. View

17.

Widyaningrum R, Candradewi I, Aji N, Aulianisa R . Comparison of Multi-Label U-Net and Mask R-CNN for panoramic radiograph segmentation to detect periodontitis. Imaging Sci Dent. 2023; 52(4):383-391. PMC: 9807794. DOI: 10.5624/isd.20220105. View

18.

Chen I, Yang C, Chen M, Chen M, Weng R, Yeh C . Deep Learning-Based Recognition of Periodontitis and Dental Caries in Dental X-ray Images. Bioengineering (Basel). 2023; 10(8). PMC: 10451544. DOI: 10.3390/bioengineering10080911. View

19.

Zhu H, Cao Z, Lian L, Ye G, Gao H, Wu J . CariesNet: a deep learning approach for segmentation of multi-stage caries lesion from oral panoramic X-ray image. Neural Comput Appl. 2022; :1-9. PMC: 8736291. DOI: 10.1007/s00521-021-06684-2. View

20.

Mohammad-Rahimi H, Motamedian S, Rohban M, Krois J, Uribe S, Mahmoudinia E . Deep learning for caries detection: A systematic review. J Dent. 2022; 122:104115. DOI: 10.1016/j.jdent.2022.104115. View