지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 발행연도
- 2024.12
- 수록면
- 109 - 117 (9page)
이용수
초록· 키워드
오류제보하기
Purpose: Cone beam computed tomography (CBCT) is widely used to evaluate the tem- poromandibular joint (TMJ). For the three-dimensional (3D) assessment of the TMJ, seg- mentation of the mandibular condyle and articular fossa is essential. This study aimed to perform deep learning-based 3D segmentation of the mandibular condyle on CBCT im- ages and evaluate the performance of the segmentation.
Methods:Methods: CBCT scan data from 99 patients (mean age: 53.3±19.2 years) diagnosed with TMJ disorders were analyzed. From the CBCT images, sagittal, coronal, and axial planes showing the mandibular condyle were selected and combined to form two-dimensional (2D) images. The U-Net deep learning model was used to exclusively segment the man- dibular condyle area from the 2D images. From these results, 3D images of the mandibu- lar condyle were reconstructed. Accuracy, precision, recall, and the Dice coefficient were calculated to appraise segmentation performance in each plane.
Results:Results: The average Dice coefficient was 0.92 for the coronal and axial planes and 0.82 for the sagittal plane. The CBCT image-based segmentation performance of the mandibu- lar condyle in the coronal and axial planes exceeded that in the sagittal plane. The sharp- ness and uniformity of the 2D images affected segmentation performance, with segmen- tation errors more likely occurring in non-uniform images. Certain segmentation errors were corrected through software processing. Finally, the segmented mandibular condyle images were applied to the CBCT data to reconstruct a 3D TMJ model.
Conclusions:Conclusions: Mandibular condyle 3D segmentation on CBCT images using U-Net may help evaluate and diagnose TMJ disorders. The proposed segmentation method may assist clinicians in efficiently analyzing CBCT images, particularly in cases involving anatomi- cal abnormalities.
Methods:Methods: CBCT scan data from 99 patients (mean age: 53.3±19.2 years) diagnosed with TMJ disorders were analyzed. From the CBCT images, sagittal, coronal, and axial planes showing the mandibular condyle were selected and combined to form two-dimensional (2D) images. The U-Net deep learning model was used to exclusively segment the man- dibular condyle area from the 2D images. From these results, 3D images of the mandibu- lar condyle were reconstructed. Accuracy, precision, recall, and the Dice coefficient were calculated to appraise segmentation performance in each plane.
Results:Results: The average Dice coefficient was 0.92 for the coronal and axial planes and 0.82 for the sagittal plane. The CBCT image-based segmentation performance of the mandibu- lar condyle in the coronal and axial planes exceeded that in the sagittal plane. The sharp- ness and uniformity of the 2D images affected segmentation performance, with segmen- tation errors more likely occurring in non-uniform images. Certain segmentation errors were corrected through software processing. Finally, the segmented mandibular condyle images were applied to the CBCT data to reconstruct a 3D TMJ model.
Conclusions:Conclusions: Mandibular condyle 3D segmentation on CBCT images using U-Net may help evaluate and diagnose TMJ disorders. The proposed segmentation method may assist clinicians in efficiently analyzing CBCT images, particularly in cases involving anatomi- cal abnormalities.
목차
INTRODUCTION
MATERIALS AND METHODS
RESULTS
DISCUSSION
REFERENCES
참고문헌 (0)
참고문헌 신청이 논문과 함께 이용한 논문
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-151-25-02-091238148