Automatic craniomaxillofacial landmarks detection in CT images of individuals with dentomaxillofacial deformities by a two-stage deep learning model
Abstract Background Accurate cephalometric analysis plays a vital role in the diagnosis and subsequent surgical planning in orthognathic and orthodontics treatment. However, manual digitization of anatomical landmarks in computed tomography (CT) is subject to limitations such as low accuracy, poor r...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-11-01
|
| Series: | BMC Oral Health |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12903-023-03446-5 |
| _version_ | 1827707969528135680 |
|---|---|
| author | Leran Tao Meng Li Xu Zhang Mengjia Cheng Yang Yang Yijiao Fu Rongbin Zhang Dahong Qian Hongbo Yu |
| author_facet | Leran Tao Meng Li Xu Zhang Mengjia Cheng Yang Yang Yijiao Fu Rongbin Zhang Dahong Qian Hongbo Yu |
| author_sort | Leran Tao |
| collection | DOAJ |
| description | Abstract Background Accurate cephalometric analysis plays a vital role in the diagnosis and subsequent surgical planning in orthognathic and orthodontics treatment. However, manual digitization of anatomical landmarks in computed tomography (CT) is subject to limitations such as low accuracy, poor repeatability and excessive time consumption. Furthermore, the detection of landmarks has more difficulties on individuals with dentomaxillofacial deformities than normal individuals. Therefore, this study aims to develop a deep learning model to automatically detect landmarks in CT images of patients with dentomaxillofacial deformities. Methods Craniomaxillofacial (CMF) CT data of 80 patients with dentomaxillofacial deformities were collected for model development. 77 anatomical landmarks digitized by experienced CMF surgeons in each CT image were set as the ground truth. 3D UX-Net, the cutting-edge medical image segmentation network, was adopted as the backbone of model architecture. Moreover, a new region division pattern for CMF structures was designed as a training strategy to optimize the utilization of computational resources and image resolution. To evaluate the performance of this model, several experiments were conducted to make comparison between the model and manual digitization approach. Results The training set and the validation set included 58 and 22 samples respectively. The developed model can accurately detect 77 landmarks on bone, soft tissue and teeth with a mean error of 1.81 ± 0.89 mm. Removal of region division before training significantly increased the error of prediction (2.34 ± 1.01 mm). In terms of manual digitization, the inter-observer and intra-observer variations were 1.27 ± 0.70 mm and 1.01 ± 0.74 mm respectively. In all divided regions except Teeth Region (TR), our model demonstrated equivalent performance to experienced CMF surgeons in landmarks detection (p > 0.05). Conclusions The developed model demonstrated excellent performance in detecting craniomaxillofacial landmarks when considering manual digitization work of expertise as benchmark. It is also verified that the region division pattern designed in this study remarkably improved the detection accuracy. |
| first_indexed | 2024-03-10T16:56:02Z |
| format | Article |
| id | doaj.art-a297035143774c5f961f7f5d24f7c576 |
| institution | Directory Open Access Journal |
| issn | 1472-6831 |
| language | English |
| last_indexed | 2024-03-10T16:56:02Z |
| publishDate | 2023-11-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Oral Health |
| spelling | doaj.art-a297035143774c5f961f7f5d24f7c5762023-11-20T11:07:44ZengBMCBMC Oral Health1472-68312023-11-0123111110.1186/s12903-023-03446-5Automatic craniomaxillofacial landmarks detection in CT images of individuals with dentomaxillofacial deformities by a two-stage deep learning modelLeran Tao0Meng Li1Xu Zhang2Mengjia Cheng3Yang Yang4Yijiao Fu5Rongbin Zhang6Dahong Qian7Hongbo Yu8Department of Oral and Cranio-maxillofacial Surgery, Shanghai Ninth People’s Hospital, College of Stomatology, Shanghai Jiao Tong University School of MedicineDepartment of Oral and Cranio-maxillofacial Surgery, Shanghai Ninth People’s Hospital, College of Stomatology, Shanghai Jiao Tong University School of MedicineMechanical college, Shanghai Dianji UniversityDepartment of Oral and Cranio-maxillofacial Surgery, Shanghai Ninth People’s Hospital, College of Stomatology, Shanghai Jiao Tong University School of MedicineShanghai Lanhui Medical Technology Co., LtdCollege of Stomatology, Shanghai Jiao Tong University School of MedicineCollege of Stomatology, Shanghai Jiao Tong University School of MedicineSchool of Biomedical Engineering, Shanghai Jiao Tong UniversityDepartment of Oral and Cranio-maxillofacial Surgery, Shanghai Ninth People’s Hospital, College of Stomatology, Shanghai Jiao Tong University School of MedicineAbstract Background Accurate cephalometric analysis plays a vital role in the diagnosis and subsequent surgical planning in orthognathic and orthodontics treatment. However, manual digitization of anatomical landmarks in computed tomography (CT) is subject to limitations such as low accuracy, poor repeatability and excessive time consumption. Furthermore, the detection of landmarks has more difficulties on individuals with dentomaxillofacial deformities than normal individuals. Therefore, this study aims to develop a deep learning model to automatically detect landmarks in CT images of patients with dentomaxillofacial deformities. Methods Craniomaxillofacial (CMF) CT data of 80 patients with dentomaxillofacial deformities were collected for model development. 77 anatomical landmarks digitized by experienced CMF surgeons in each CT image were set as the ground truth. 3D UX-Net, the cutting-edge medical image segmentation network, was adopted as the backbone of model architecture. Moreover, a new region division pattern for CMF structures was designed as a training strategy to optimize the utilization of computational resources and image resolution. To evaluate the performance of this model, several experiments were conducted to make comparison between the model and manual digitization approach. Results The training set and the validation set included 58 and 22 samples respectively. The developed model can accurately detect 77 landmarks on bone, soft tissue and teeth with a mean error of 1.81 ± 0.89 mm. Removal of region division before training significantly increased the error of prediction (2.34 ± 1.01 mm). In terms of manual digitization, the inter-observer and intra-observer variations were 1.27 ± 0.70 mm and 1.01 ± 0.74 mm respectively. In all divided regions except Teeth Region (TR), our model demonstrated equivalent performance to experienced CMF surgeons in landmarks detection (p > 0.05). Conclusions The developed model demonstrated excellent performance in detecting craniomaxillofacial landmarks when considering manual digitization work of expertise as benchmark. It is also verified that the region division pattern designed in this study remarkably improved the detection accuracy.https://doi.org/10.1186/s12903-023-03446-5Dentomaxillofacial deformityCephalometric analysisDeep learningLandmarks detectionComputer-assisted surgery design. |
| spellingShingle | Leran Tao Meng Li Xu Zhang Mengjia Cheng Yang Yang Yijiao Fu Rongbin Zhang Dahong Qian Hongbo Yu Automatic craniomaxillofacial landmarks detection in CT images of individuals with dentomaxillofacial deformities by a two-stage deep learning model BMC Oral Health Dentomaxillofacial deformity Cephalometric analysis Deep learning Landmarks detection Computer-assisted surgery design. |
| title | Automatic craniomaxillofacial landmarks detection in CT images of individuals with dentomaxillofacial deformities by a two-stage deep learning model |
| title_full | Automatic craniomaxillofacial landmarks detection in CT images of individuals with dentomaxillofacial deformities by a two-stage deep learning model |
| title_fullStr | Automatic craniomaxillofacial landmarks detection in CT images of individuals with dentomaxillofacial deformities by a two-stage deep learning model |
| title_full_unstemmed | Automatic craniomaxillofacial landmarks detection in CT images of individuals with dentomaxillofacial deformities by a two-stage deep learning model |
| title_short | Automatic craniomaxillofacial landmarks detection in CT images of individuals with dentomaxillofacial deformities by a two-stage deep learning model |
| title_sort | automatic craniomaxillofacial landmarks detection in ct images of individuals with dentomaxillofacial deformities by a two stage deep learning model |
| topic | Dentomaxillofacial deformity Cephalometric analysis Deep learning Landmarks detection Computer-assisted surgery design. |
| url | https://doi.org/10.1186/s12903-023-03446-5 |
| work_keys_str_mv | AT lerantao automaticcraniomaxillofaciallandmarksdetectioninctimagesofindividualswithdentomaxillofacialdeformitiesbyatwostagedeeplearningmodel AT mengli automaticcraniomaxillofaciallandmarksdetectioninctimagesofindividualswithdentomaxillofacialdeformitiesbyatwostagedeeplearningmodel AT xuzhang automaticcraniomaxillofaciallandmarksdetectioninctimagesofindividualswithdentomaxillofacialdeformitiesbyatwostagedeeplearningmodel AT mengjiacheng automaticcraniomaxillofaciallandmarksdetectioninctimagesofindividualswithdentomaxillofacialdeformitiesbyatwostagedeeplearningmodel AT yangyang automaticcraniomaxillofaciallandmarksdetectioninctimagesofindividualswithdentomaxillofacialdeformitiesbyatwostagedeeplearningmodel AT yijiaofu automaticcraniomaxillofaciallandmarksdetectioninctimagesofindividualswithdentomaxillofacialdeformitiesbyatwostagedeeplearningmodel AT rongbinzhang automaticcraniomaxillofaciallandmarksdetectioninctimagesofindividualswithdentomaxillofacialdeformitiesbyatwostagedeeplearningmodel AT dahongqian automaticcraniomaxillofaciallandmarksdetectioninctimagesofindividualswithdentomaxillofacialdeformitiesbyatwostagedeeplearningmodel AT hongboyu automaticcraniomaxillofaciallandmarksdetectioninctimagesofindividualswithdentomaxillofacialdeformitiesbyatwostagedeeplearningmodel |