Top

Published in:

Open Access 01-12-2024 | Caries | Research

Combining public datasets for automated tooth assessment in panoramic radiographs

Authors: Niels van Nistelrooij, Khalid El Ghoul, Tong Xi, Anindo Saha, Steven Kempers, Max Cenci, Bas Loomans, Tabea Flügge, Bram van Ginneken, Shankeeth Vinayahalingam

Published in: BMC Oral Health | Issue 1/2024

Abstract

Objective

Panoramic radiographs (PRs) provide a comprehensive view of the oral and maxillofacial region and are used routinely to assess dental and osseous pathologies. Artificial intelligence (AI) can be used to improve the diagnostic accuracy of PRs compared to bitewings and periapical radiographs. This study aimed to evaluate the advantages and challenges of using publicly available datasets in dental AI research, focusing on solving the novel task of predicting tooth segmentations, FDI numbers, and tooth diagnoses, simultaneously.

Materials and methods

Datasets from the OdontoAI platform (tooth instance segmentations) and the DENTEX challenge (tooth bounding boxes with associated diagnoses) were combined to develop a two-stage AI model. The first stage implemented tooth instance segmentation with FDI numbering and extracted regions of interest around each tooth segmentation, whereafter the second stage implemented multi-label classification to detect dental caries, impacted teeth, and periapical lesions in PRs. The performance of the automated tooth segmentation algorithm was evaluated using a free-response receiver-operating-characteristics (FROC) curve and mean average precision (mAP) metrics. The diagnostic accuracy of detection and classification of dental pathology was evaluated with ROC curves and F1 and AUC metrics.

Results

The two-stage AI model achieved high accuracy in tooth segmentations with a FROC score of 0.988 and a mAP of 0.848. High accuracy was also achieved in the diagnostic classification of impacted teeth (F1 = 0.901, AUC = 0.996), whereas moderate accuracy was achieved in the diagnostic classification of deep caries (F1 = 0.683, AUC = 0.960), early caries (F1 = 0.662, AUC = 0.881), and periapical lesions (F1 = 0.603, AUC = 0.974). The model’s performance correlated positively with the quality of annotations in the used public datasets. Selected samples from the DENTEX dataset revealed cases of missing (false-negative) and incorrect (false-positive) diagnoses, which negatively influenced the performance of the AI model.

Conclusions

The use and pooling of public datasets in dental AI research can significantly accelerate the development of new AI models and enable fast exploration of novel tasks. However, standardized quality assurance is essential before using the datasets to ensure reliable outcomes and limit potential biases.

FelsyPremila G, et al. Visual interpretation of panoramic radiographs in dental students using eye-tracking technology. J Dent Educ. Mar. 2022;86. https://doi.org/10.1002/jdd.12899.

Peretz B, Gotler M, Kaffe I. Common Errors in Digital Panoramic Radiographs of Patients with Mixed Dentition and Patients with Permanent Dentition. In: International journal of dentistry 2012Feb. (2012), p. 584138. https://doi.org/10.1155/2012/584138.

Susanne Perschbacher. Interpretation of panoramic radiographs. In: Australian dental journal 57 Suppl 1 (Mar. 2012), pp. 40–5. https://doi.org/10.1111/j.1834-7819.2011.01655.x.

Lei C, et al. Expert consensus on dental caries management. Int J Oral Sci. Dec. 2022;14. https://doi.org/10.1038/s41368-022-00167-3.

Akarslan ZZ et al. A comparison of the diagnostic accuracy of bitewing, periapical, unfiltered and filtered digital panoramic images for approximal caries detection in posterior teeth. In: Dentomaxillofacial Radiology 37.8 (2008). PMID: 19033431, pp. 458–463. 10.1259 / dmfr/84698143.

Junhua, Zhu, et al. Artificial intelligence in the diagnosis of dental diseases on panoramic radiographs: a preliminary study. BMC Oral Health. June 2023;23. 10.1186/ s12903-023-03027-6.

Geetha Chandrashekar E, Bumann, Lee Y. Collaborative deep learning model for tooth segmentation and identification using panoramic radiographs. Comput Biol Med. July 2022;148:105829. https://doi.org/10.1016/j.compbiomed.2022.105829.

Gil J et al. Oct. Deep Instance Segmentation of Teeth in Panoramic X-Ray Images. In: 2018, pp. 400–407. https://doi.org/10.1109/SIBGRAPI.2018.00058.

Rafic N et al. Aug. Automatic teeth segmentation on panoramic X-rays using deep neural networks. In: 2022, pp. 4299–4305. https://doi.org/10.1109/ICPR56361.2022.9956708.

10.

Burak, Dayı, et al. A Novel Deep Learning-Based Approach for Segmentation of different type caries lesions on panoramic radiographs. Diagnostics. Jan. 2023;13:202. https://doi.org/10.3390/diagnostics13020202.

11.

Arman H, et al. PaXNet: tooth segmentation and dental caries detection in panoramic X-ray using ensemble transfer learning and capsule classifier. Multimedia Tools Appl. Feb. 2023;82:1–21. https://doi.org/10.1007/s11042-023-14435-9.

12.

Haihua, Zhu, et al. CariesNet: a deep learning approach for segmentation of multi-stage caries lesion from oral panoramic X-ray image. Neural Comput Appl. Jan. 2022;35:1–9. https://doi.org/10.1007/s00521-021-06684-2.

13.

Yifan, Zhang, et al. Children’s dental panoramic radiographs dataset for caries segmentation and dental disease detection. Sci Data. June 2023;10. https://doi.org/10.1038/s41597-023-02237-5.

14.

Emel G, et al. Automatic segmentation of Teeth, Crown-Bridge restorations, Dental implants, restorative fillings, Dental Caries, residual roots, and Root Canal fillings on Orthopantomographs: Convenience and pitfalls. Diagnostics. Apr. 2023;13:1–10. https://doi.org/10.3390/diagnostics13081487.

15.

Soroush S et al. Deep Learning for Detection of Periapical Radiolucent Lesions: A Systematic Review and Meta-analysis of Diagnostic Test Accuracy. In: Journal of Endodontics 49.3 (2023), 248–261.e3. issn: 0099-2399. https://doi.org/10.1016/j.joen.2022.12.007.

16.

Manal H, Hamdan et al. The effect of a deep-learning tool on dentists’ performances in detecting apical radiolucencies on periapical radiographs. In: Dentomaxillofacial Radiology 51.7 (2022). PMID: 35980437, p. 20220122. https://doi.org/10.1259/dmfr.20220122.

17.

Julio César Mello Román. Panoramic Dental radiography image Enhancement using Multiscale Mathematical morphology. Sensors. 2021;21. https://doi.org/10.3390/s21093110.

18.

Abdi AH, Kasaei DDSS, Mehdizadeh M. Automatic segmentation of mandible in panoramic x-ray. J Med Imaging. 2015;2:044003. https://doi.org/10.1117/1.JMI.2.4.044003.CrossRef

19.

Bernardo Peters Menezes Silva. Boosting research on dental panoramic radiographs: a challenging data set, baselines, and a task central online platform for benchmark. Computer Methods Biomech Biomedical Engineering: Imaging Visualization. 2023;11:1327–47. https://doi.org/10.1080/21681163.2022.2157747.CrossRef

20.

Karen P, et al. Tufts Dental Database: a Multimodal Panoramic X-Ray dataset for Benchmarking Diagnostic systems. IEEE J Biomedical Health Informatics PP (Oct. 2021;1–1. https://doi.org/10.1109/JBHI.2021.3117575.

21.

Ibrahim Ethem, Hamamci et al. DENTEX: An Abnormal Tooth Detection with Dental Enumeration and Diagnosis Benchmark for Panoramic X-rays. 2023. arXiv: 2305.19112 [cs.CV].

22.

Falk S et al. Artificial intelligence in dental research: Checklist for authors, re- viewers, readers. In: Journal of Dentistry 107 (2021), p. 103610. issn: 0300–5712. doi: 10. 1016/j.jdent.2021.103610.

23.

Piotr Szymanśki and Tomasz Kajdanowicz. A scikit-based Python environment for performing multi-label classification. Feb. 2017. arXiv: 1702.01460 [cs.LG].

24.

Sezgin Er A. 2023. https://doi.org/10.5281/zenodo.7812323.

25.

Feng, Li et al. Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation. 2022. arXiv: 2206.02777 [cs.CV].

26.

Kai, Chen et al. MMDetection: Open MMLab Detection Toolbox and Benchmark. 2019. arXiv: 1906.07155 [cs.CV].

27.

Adam, Paszke et al. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In: Advances in Neural Information Processing Systems 32. Curran Associates, Inc., 2019, pp. 8024–8035. url: http://papers.neurips.cc/paper/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf.

28.

Kaiming, He. Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016, pp. 770–778. 10.1109/ CVPR.2016.90.

29.

Tsung-Yi, Lin et al. Microsoft COCO: Common Objects in Context. 2015. arXiv: 1405.0312 [cs.CV].

30.

Ilya Loshchilov and Frank Hutter. Decoupled Weight Decay Regularization. 2019. arXiv: 1711. 05101 [cs.LG].

31.

Golnaz G et al. Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation. 2021. arXiv: 2012.07177 [cs.CV].

32.

Xinlong, Wang et al. SOLOv2: Dynamic and Fast Instance Segmentation. In: Advances in Neural Information Processing Systems. Ed. by H. Larochelle Vol. 33. Curran Associates, Inc., 2020, pp. 17721–17732. url: https://proceedings.neurips.cc/paper_files/paper/2020/file/cd3afef9b8b89558cd56638c3631868a-Paper.pdf.

33.

MMPreTrain C. OpenMMLab’s Pre-training Toolbox and Benchmark. https://github.com/open-mmlab/mmpretrain. 2023.

34.

Ze, Liu et al. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. 2021. arXiv: 2103.14030 [cs.CV].

35.

Jia D et al. Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. Ieee. 2009, pp. 248–255. 10.1109/ CVPR.2009.5206848.

36.

Zhenda, Xie et al. SimMIM: A Simple Framework for Masked Image Modeling. 2022. arXiv: 2111.09886 [cs.CV].

37.

Fabian I, et al. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. Feb. 2021;18:1–9. https://doi.org/10.1038/s41592-020-01008-z.

38.

Christian S et al. Rethinking the Inception Architecture for Computer Vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Soci- ety, 2016, pp. 2818–2826. https://doi.org/10.1109/CVPR.2016.308.

39.

Li Shen Z, Lin, Huang Q. Relay backpropagation for effective learning of deep convolutional neural networks. In: Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part VII 14. Springer. 2016, pp. 467–482. https://doi.org/10.1007/978-3-319-46478-7_29.

40.

Ke Zhu and Jianxin Wu. Residual Attention: A Simple but Effective Method for Multi-Label Recognition. 2021. arXiv: 2108.02456 [cs.CV].

41.

Agrim Gupta P, Dollár, Girshick R. LVIS: A Dataset for Large Vocabulary Instance Segmentation. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2019, pp. 5351–5359. https://doi.org/10.1109/CVPR.2019.00550.

42.

Tsung-Yi, Lin et al. Focal Loss for Dense Object Detection. 2018. arXiv: 1708.02002 [cs.CV].

43.

Fahad Umer S, Habib, Adnan N. Application of deep learning in teeth identification tasks on panoramic radiographs. Dentomaxillofacial Radiol. 2022;51:20210504. https://doi.org/10.1259/dmfr.20210504. PMID: 35143260.CrossRef

44.

Mingming, Xu et al. Robust automated teeth identification from dental radiographs using deep learning. In: Journal of Dentistry 136 (2023), p. 104607. issn: 0300–5712. doi: 10. 1016/j.jdent.2023.104607.

45.

Lukasz Zadrozńy et al. Artificial Intelligence Application in Assessment of Panoramic Radiographs. In: Diagnostics 12.1 (2022). issn: 2075–4418. https://doi.org/10.3390/diagnostics12010224.

46.

Shankeeth V, et al. Classification of caries in third molars on panoramic radiographs using deep learning. Sci Rep. June 2021;11. https://doi.org/10.1038/s41598-021-92121-2.

47.

Ibrahim B et al. A U-Net Approach to Apical Lesion Segmentation on Panoramic Radiographs. In: BioMed Research International 2022 (Jan. 2022), pp. 1–7. 10.1155/ 2022/7035367.

48.

Babak EB, et al. Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in women with breast Cancer. (Dec. 2017. https://doi.org/10.1001/jama.2017.14585.CrossRef

Title: Combining public datasets for automated tooth assessment in panoramic radiographs
Authors: Niels van Nistelrooij
Khalid El Ghoul
Tong Xi
Anindo Saha
Steven Kempers
Max Cenci
Bas Loomans
Tabea Flügge
Bram van Ginneken
Shankeeth Vinayahalingam
Publication date: 01-12-2024
Publisher: BioMed Central
Keywords: Caries
Artificial Intelligence
Published in: BMC Oral Health / Issue 1/2024
Electronic ISSN: 1472-6831
DOI: https://doi.org/10.1186/s12903-024-04129-5

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Combining public datasets for automated tooth assessment in panoramic radiographs

Abstract

Objective

Materials and methods

Results

Conclusions

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Objective

Materials and methods

Results

Conclusions

Please log in to get access to this content

Other articles of this Issue 1/2024

Cephalometric and digital model analysis of dentoskeletal effects of infrazygomatic miniscrew vs. Essix- anchored Carriere Motion appliance for distalization of maxillary buccal segment: a randomized clinical trial

Evaluating flexure properties, hardness, roughness and microleakage of high-strength injectable dental composite: an in vitro study

Correction: A scoping review on the links between sustainable development goal 14 and early childhood caries

Comparative analysis of stress distribution in residual roots with different canal morphologies: evaluating CAD/CAM glass fiber and other post-core materials

Effect of cevimeline and different concentration of gum arabic on parotid salivary gland function in methotrexate-induced xerostomia: a comparative study

Effects of different patterns of movement for correcting a deep curve of Spee with clear aligners on the anterior teeth: a finite element analysis