Multimodal deep learning for cephalometric landmark detection and treatment prediction
Abstract In orthodontics and maxillofacial surgery, accurate cephalometric analysis and treatment outcome prediction are critical for clinical decision-making. Traditional approaches rely on manual landmark identification, which is time-consuming and subject to inter-observer variability, while exis...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-06229-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849333275480293376 |
|---|---|
| author | Fei Gao Yulong Tang |
| author_facet | Fei Gao Yulong Tang |
| author_sort | Fei Gao |
| collection | DOAJ |
| description | Abstract In orthodontics and maxillofacial surgery, accurate cephalometric analysis and treatment outcome prediction are critical for clinical decision-making. Traditional approaches rely on manual landmark identification, which is time-consuming and subject to inter-observer variability, while existing automated methods typically utilize single imaging modalities with limited accuracy. This paper presents DeepFuse, a novel multi-modal deep learning framework that integrates information from lateral cephalograms, CBCT volumes, and digital dental models to simultaneously perform landmark detection and treatment outcome prediction. The framework employs modality-specific encoders, an attention-guided fusion mechanism, and dual-task decoders to leverage complementary information across imaging techniques. Extensive experiments on three clinical datasets demonstrate that DeepFuse achieves a mean radial error of 1.21 mm for landmark detection, representing a 13% improvement over state-of-the-art methods, with a clinical acceptability rate of 92.4% at the 2 mm threshold. For treatment outcome prediction, the framework attains an overall accuracy of 85.6%, significantly outperforming both conventional prediction models and experienced clinicians. The proposed approach enhances diagnostic precision and treatment planning while providing interpretable visualization of decision factors, demonstrating significant potential for clinical integration in orthodontic and maxillofacial practice. |
| format | Article |
| id | doaj-art-27f67df121b141f0b2aa3564c067cbe5 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-27f67df121b141f0b2aa3564c067cbe52025-08-20T03:45:55ZengNature PortfolioScientific Reports2045-23222025-07-0115111810.1038/s41598-025-06229-wMultimodal deep learning for cephalometric landmark detection and treatment predictionFei Gao0Yulong Tang1Department of Stomatology, General Hospital of PLA Northern Theater CommandDepartment of Stomatology, General Hospital of PLA Northern Theater CommandAbstract In orthodontics and maxillofacial surgery, accurate cephalometric analysis and treatment outcome prediction are critical for clinical decision-making. Traditional approaches rely on manual landmark identification, which is time-consuming and subject to inter-observer variability, while existing automated methods typically utilize single imaging modalities with limited accuracy. This paper presents DeepFuse, a novel multi-modal deep learning framework that integrates information from lateral cephalograms, CBCT volumes, and digital dental models to simultaneously perform landmark detection and treatment outcome prediction. The framework employs modality-specific encoders, an attention-guided fusion mechanism, and dual-task decoders to leverage complementary information across imaging techniques. Extensive experiments on three clinical datasets demonstrate that DeepFuse achieves a mean radial error of 1.21 mm for landmark detection, representing a 13% improvement over state-of-the-art methods, with a clinical acceptability rate of 92.4% at the 2 mm threshold. For treatment outcome prediction, the framework attains an overall accuracy of 85.6%, significantly outperforming both conventional prediction models and experienced clinicians. The proposed approach enhances diagnostic precision and treatment planning while providing interpretable visualization of decision factors, demonstrating significant potential for clinical integration in orthodontic and maxillofacial practice.https://doi.org/10.1038/s41598-025-06229-wCephalometric analysisMulti-modal deep learningLandmark detectionTreatment outcome predictionAttention mechanismOrthodontics |
| spellingShingle | Fei Gao Yulong Tang Multimodal deep learning for cephalometric landmark detection and treatment prediction Scientific Reports Cephalometric analysis Multi-modal deep learning Landmark detection Treatment outcome prediction Attention mechanism Orthodontics |
| title | Multimodal deep learning for cephalometric landmark detection and treatment prediction |
| title_full | Multimodal deep learning for cephalometric landmark detection and treatment prediction |
| title_fullStr | Multimodal deep learning for cephalometric landmark detection and treatment prediction |
| title_full_unstemmed | Multimodal deep learning for cephalometric landmark detection and treatment prediction |
| title_short | Multimodal deep learning for cephalometric landmark detection and treatment prediction |
| title_sort | multimodal deep learning for cephalometric landmark detection and treatment prediction |
| topic | Cephalometric analysis Multi-modal deep learning Landmark detection Treatment outcome prediction Attention mechanism Orthodontics |
| url | https://doi.org/10.1038/s41598-025-06229-w |
| work_keys_str_mv | AT feigao multimodaldeeplearningforcephalometriclandmarkdetectionandtreatmentprediction AT yulongtang multimodaldeeplearningforcephalometriclandmarkdetectionandtreatmentprediction |