Evaluating masked self-supervised learning frameworks for 3D dental model segmentation tasks
Abstract The application of deep learning using dental models is crucial for automated computer-aided treatment planning. However, developing highly accurate models requires a substantial amount of accurately labeled data. Obtaining this data is challenging, especially in the medical domain. Masked...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-01014-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850273415017005056 |
|---|---|
| author | Lucas Krenmayr Reinhold von Schwerin Daniel Schaudt Pascal Riedel Alexander Hafner Marc Geserick |
| author_facet | Lucas Krenmayr Reinhold von Schwerin Daniel Schaudt Pascal Riedel Alexander Hafner Marc Geserick |
| author_sort | Lucas Krenmayr |
| collection | DOAJ |
| description | Abstract The application of deep learning using dental models is crucial for automated computer-aided treatment planning. However, developing highly accurate models requires a substantial amount of accurately labeled data. Obtaining this data is challenging, especially in the medical domain. Masked self-supervised learning has shown great promise in overcoming the challenge of data scarcity. However, its effectiveness has not been well explored in the 3D domain, particularly on dental models. In this work, we investigate the applicability of the four recently published masked self-supervised learning frameworks-Point-BERT, Point-MAE, Point-GPT, and Point-M2AE-for improving downstream tasks such as tooth and brace segmentation. These frameworks were pre-trained on a proprietary dataset of over 4000 unlabeled 3D dental models and fine-tuned using the publicly available Teeth3DS dataset for tooth segmentation and a self-constructed braces segmentation dataset. Through a set of experiments we demonstrate that pre-training can enhance the performance of downstream tasks, especially when training data is scarce or imbalanced—a critical factor for clinical usability. Our results show that the benefits are most noticeable when training data is limited but diminish as more labeled data becomes available, providing insights into when and how this technique should be applied to maximize its effectiveness. |
| format | Article |
| id | doaj-art-17dd677bb1c44c8f9d1216df83e4c862 |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-17dd677bb1c44c8f9d1216df83e4c8622025-08-20T01:51:30ZengNature PortfolioScientific Reports2045-23222025-05-0115111510.1038/s41598-025-01014-1Evaluating masked self-supervised learning frameworks for 3D dental model segmentation tasksLucas Krenmayr0Reinhold von Schwerin1Daniel Schaudt2Pascal Riedel3Alexander Hafner4Marc Geserick5Cooperative Doctoral Program for Data Science and Analytics, University of UlmDepartment of Computer Science, University of Applied SciencesDepartment of Computer Science, University of Applied SciencesDepartment of Computer Science, University of Applied SciencesDepartment of Computer Science, University of Applied Sciencessmyl tp GmbHAbstract The application of deep learning using dental models is crucial for automated computer-aided treatment planning. However, developing highly accurate models requires a substantial amount of accurately labeled data. Obtaining this data is challenging, especially in the medical domain. Masked self-supervised learning has shown great promise in overcoming the challenge of data scarcity. However, its effectiveness has not been well explored in the 3D domain, particularly on dental models. In this work, we investigate the applicability of the four recently published masked self-supervised learning frameworks-Point-BERT, Point-MAE, Point-GPT, and Point-M2AE-for improving downstream tasks such as tooth and brace segmentation. These frameworks were pre-trained on a proprietary dataset of over 4000 unlabeled 3D dental models and fine-tuned using the publicly available Teeth3DS dataset for tooth segmentation and a self-constructed braces segmentation dataset. Through a set of experiments we demonstrate that pre-training can enhance the performance of downstream tasks, especially when training data is scarce or imbalanced—a critical factor for clinical usability. Our results show that the benefits are most noticeable when training data is limited but diminish as more labeled data becomes available, providing insights into when and how this technique should be applied to maximize its effectiveness.https://doi.org/10.1038/s41598-025-01014-1 |
| spellingShingle | Lucas Krenmayr Reinhold von Schwerin Daniel Schaudt Pascal Riedel Alexander Hafner Marc Geserick Evaluating masked self-supervised learning frameworks for 3D dental model segmentation tasks Scientific Reports |
| title | Evaluating masked self-supervised learning frameworks for 3D dental model segmentation tasks |
| title_full | Evaluating masked self-supervised learning frameworks for 3D dental model segmentation tasks |
| title_fullStr | Evaluating masked self-supervised learning frameworks for 3D dental model segmentation tasks |
| title_full_unstemmed | Evaluating masked self-supervised learning frameworks for 3D dental model segmentation tasks |
| title_short | Evaluating masked self-supervised learning frameworks for 3D dental model segmentation tasks |
| title_sort | evaluating masked self supervised learning frameworks for 3d dental model segmentation tasks |
| url | https://doi.org/10.1038/s41598-025-01014-1 |
| work_keys_str_mv | AT lucaskrenmayr evaluatingmaskedselfsupervisedlearningframeworksfor3ddentalmodelsegmentationtasks AT reinholdvonschwerin evaluatingmaskedselfsupervisedlearningframeworksfor3ddentalmodelsegmentationtasks AT danielschaudt evaluatingmaskedselfsupervisedlearningframeworksfor3ddentalmodelsegmentationtasks AT pascalriedel evaluatingmaskedselfsupervisedlearningframeworksfor3ddentalmodelsegmentationtasks AT alexanderhafner evaluatingmaskedselfsupervisedlearningframeworksfor3ddentalmodelsegmentationtasks AT marcgeserick evaluatingmaskedselfsupervisedlearningframeworksfor3ddentalmodelsegmentationtasks |