3D reconstruction from 2D multi-view dental 2D images based on EfficientNetB0 model
Abstract Dental diseases are the primary cause of oral health concerns around the world, affecting millions of people. Therefore, recent developments in imaging technologies have transformed the detection and treatment of oral problems. Applying three-dimensional (3D) reconstruction from two-dimensi...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-12861-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849333411702898688 |
|---|---|
| author | Waleed Mohamed Nermeen Nader Yasmin M. Alsakar Naira Elazab Mohamed Ezzat Mohammed Elmogy |
| author_facet | Waleed Mohamed Nermeen Nader Yasmin M. Alsakar Naira Elazab Mohamed Ezzat Mohammed Elmogy |
| author_sort | Waleed Mohamed |
| collection | DOAJ |
| description | Abstract Dental diseases are the primary cause of oral health concerns around the world, affecting millions of people. Therefore, recent developments in imaging technologies have transformed the detection and treatment of oral problems. Applying three-dimensional (3D) reconstruction from two-dimensional (2D) dental images, such as X-rays, is a potential development field. 3D reconstruction technology converts real-world goals into mathematical models that are compatible with computer logic expressions. It’s been commonly used in dentistry. Particularly for patients with a vomiting reflex, 3D imaging techniques minimize patient discomfort and shorten the length of the examination or treatment. Therefore, this research paper proposes a new 3D reconstruction model from 2D multi-view dental images. The proposed framework consists of three stages. The first stage is the encoder stage, which extracts meaningful features from the 2D images. The second stage captures spatial and semantic information essential for the reconstruction task. The third stage is recurrence, which uses 3D long short-term memory (LSTM). It ensures that the information from various viewpoints is effectively integrated to produce a coherent representation of the 3D structure and decoder stage to translate the aggregated features from the LSTM into a fully reconstructed 3D model. When the proposed model was tested on the ShapeNet dataset, the suggested model achieved a maximum intersection over union (IoU) of 89.98% and an F1_score of 94.11%. A special case of 3D reconstruction, a dental dataset, has been created with the same structure as the ShapeNet dataset to evaluate our system. The proposed approach’s results show promising accomplishments compared to many state-of-the-art approaches, and they motivate the authors to make plans for further improvement. |
| format | Article |
| id | doaj-art-9350044e4d14422d82ad810ac8cb9192 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-9350044e4d14422d82ad810ac8cb91922025-08-20T03:45:52ZengNature PortfolioScientific Reports2045-23222025-08-0115111310.1038/s41598-025-12861-33D reconstruction from 2D multi-view dental 2D images based on EfficientNetB0 modelWaleed Mohamed0Nermeen Nader1Yasmin M. Alsakar2Naira Elazab3Mohamed Ezzat4Mohammed Elmogy5Computer Science Department, Faculty of Computers and InformationInformation Technology Department, Faculty of Computers and InformationInformation Technology Department, Faculty of Computers and InformationInformation Technology Department, Faculty of Computers and InformationDirectorate of Health in Dakahilia, Ministry of Health and PopulationInformation Technology Department, Faculty of Computers and InformationAbstract Dental diseases are the primary cause of oral health concerns around the world, affecting millions of people. Therefore, recent developments in imaging technologies have transformed the detection and treatment of oral problems. Applying three-dimensional (3D) reconstruction from two-dimensional (2D) dental images, such as X-rays, is a potential development field. 3D reconstruction technology converts real-world goals into mathematical models that are compatible with computer logic expressions. It’s been commonly used in dentistry. Particularly for patients with a vomiting reflex, 3D imaging techniques minimize patient discomfort and shorten the length of the examination or treatment. Therefore, this research paper proposes a new 3D reconstruction model from 2D multi-view dental images. The proposed framework consists of three stages. The first stage is the encoder stage, which extracts meaningful features from the 2D images. The second stage captures spatial and semantic information essential for the reconstruction task. The third stage is recurrence, which uses 3D long short-term memory (LSTM). It ensures that the information from various viewpoints is effectively integrated to produce a coherent representation of the 3D structure and decoder stage to translate the aggregated features from the LSTM into a fully reconstructed 3D model. When the proposed model was tested on the ShapeNet dataset, the suggested model achieved a maximum intersection over union (IoU) of 89.98% and an F1_score of 94.11%. A special case of 3D reconstruction, a dental dataset, has been created with the same structure as the ShapeNet dataset to evaluate our system. The proposed approach’s results show promising accomplishments compared to many state-of-the-art approaches, and they motivate the authors to make plans for further improvement.https://doi.org/10.1038/s41598-025-12861-3Dentistry3D reconstruction3D LSTMEfficientNetB02D multi-view dental images |
| spellingShingle | Waleed Mohamed Nermeen Nader Yasmin M. Alsakar Naira Elazab Mohamed Ezzat Mohammed Elmogy 3D reconstruction from 2D multi-view dental 2D images based on EfficientNetB0 model Scientific Reports Dentistry 3D reconstruction 3D LSTM EfficientNetB0 2D multi-view dental images |
| title | 3D reconstruction from 2D multi-view dental 2D images based on EfficientNetB0 model |
| title_full | 3D reconstruction from 2D multi-view dental 2D images based on EfficientNetB0 model |
| title_fullStr | 3D reconstruction from 2D multi-view dental 2D images based on EfficientNetB0 model |
| title_full_unstemmed | 3D reconstruction from 2D multi-view dental 2D images based on EfficientNetB0 model |
| title_short | 3D reconstruction from 2D multi-view dental 2D images based on EfficientNetB0 model |
| title_sort | 3d reconstruction from 2d multi view dental 2d images based on efficientnetb0 model |
| topic | Dentistry 3D reconstruction 3D LSTM EfficientNetB0 2D multi-view dental images |
| url | https://doi.org/10.1038/s41598-025-12861-3 |
| work_keys_str_mv | AT waleedmohamed 3dreconstructionfrom2dmultiviewdental2dimagesbasedonefficientnetb0model AT nermeennader 3dreconstructionfrom2dmultiviewdental2dimagesbasedonefficientnetb0model AT yasminmalsakar 3dreconstructionfrom2dmultiviewdental2dimagesbasedonefficientnetb0model AT nairaelazab 3dreconstructionfrom2dmultiviewdental2dimagesbasedonefficientnetb0model AT mohamedezzat 3dreconstructionfrom2dmultiviewdental2dimagesbasedonefficientnetb0model AT mohammedelmogy 3dreconstructionfrom2dmultiviewdental2dimagesbasedonefficientnetb0model |