Earticle

Accurate tooth segmentation from cone-beam computed tomography (CBCT) images is essential for dental diagnosis and treatment planning. This study presents a deep-learning approach for 3D tooth segmentation utilizing the SegMamba architecture enhanced with Squeeze-and-Excitation (SE) attention mechanisms in the skip connections. The proposed method leverages the strengths of state space models for capturing long-range dependencies while the SE attention blocks recalibrate feature representations to focus on the most informative channels and spatial regions. Our end-to-end framework directly processes 3D CBCT volumes to produce accurate tooth segmentation masks. Experimental evaluations demonstrate that our method achieves a high Dice score of 91.42%, outperforming current state-of-the-art approaches for tooth segmentation tasks.

본 논문에서는 딥러닝을 이용한 영상 분할에서 성능을 향상하기 위해 퍼지 논리를 적용하는 퍼지 딥러닝 모델인 퍼지 U-Net을 제안한다. 퍼지 논리를 이용한 퍼지 모듈을 영상 분할에서 우수한 성능을 보이는 딥러닝 모델인 U-Net에 결합하여 다양한 형태의 퍼지 모듈을 시뮬레이션하였다. 제안된 딥러닝 모델의 퍼지 모듈은 이미지의 특징맵과 해당 분 할 결과 사이의 본질적이고 복잡한 규칙을 학습다. 이를 위해 치아 CBCT 데이터에 적용하여 제안된 방법의 우수성을 입증하였다.　시뮬레이션 결과 제안된 퍼지 U-Net에서 더하기 스킵 연결을 사용한 모델의 ADD-RELU 퍼지 모듈 구조 의 성능이 시험용 데이터에 대해 0.7928로 가장 우수한 것을 볼 수 있다.

In this paper, we propose a fuzzy U-Net, a fuzzy deep learning model that applies fuzzy logic to improve performance in image segmentation using deep learning. Fuzzy modules using fuzzy logic were combined with U-Net, a deep learning model that showed excellent performance in image segmentation, and various types of fuzzy modules were simulated. The fuzzy module of the proposed deep learning model learns intrinsic and complex rules between feature maps of images and corresponding segmentation results. To this end, the superiority of the proposed method was demonstrated by applying it to dental CBCT data.　As a result of the simulation, it can be seen that the performance of the ADD-RELU fuzzy module structure of the model using the addition skip connection in the proposed fuzzy U-Net is 0.7928 for the test dataset and　the best.

In this paper, layered UNet with warmup and dropout tricks was used to segment teeth instantly by using data labeled for each individual tooth and increase performance of the result. The layered UNet proposed before showed very good performance in tooth segmentation without distinguishing tooth number. To do instance segmentation of teeth, we labeled teeth CBCT data according to tooth numbering system which is devised by FDI World Dental Federation notation. Colors for labeled teeth are like AI-Hub teeth dataset. Simulation results show that layered UNet does also segment very well for each tooth distinguishing tooth number by color. Layered UNet model using warmup trick was the best with IoU values of 0.80 and 0.77 for training, validation data. To increase the performance of instance segmentation of teeth, we need more labeled data later. The results of this paper can be used to develop medical software that requires tooth recognition, such as orthodontic treatment, wisdom tooth extraction, and implant surgery.

This paper describes an automatic 3-dimensional (3D) segmentation method for 3D CT (Computed Tomography) images using region growing (RG) and edge detection techniques. Specifically, an augmented RG method in which the contours of regions are extracted by a 3D digital edge detection filter is presented. The feature of this method is the capability of preventing the leakage of regions which is a defect of conventional RG method. Experimental results applied to the extraction of teeth from 3D CT data of jaw bones show that teeth are correctly extracted by the proposed method.

CT영상으로 골조직이나 특정 기관의 3차원 모델을 재구성하는 연구는 큰 진전을 이루어 현재는 진료나 치료계획 수립에 없어서는 안될 중요한 역할을 하고 있다. 그러나 기존의 방법으로는 교정이나 시술 시뮬레이션을 위해서는 치조골과 치아를 개별적으로 분리해서 모델링해야하는 치과분야의 요구를 만족시키는 데는 어려움이 있다. 치아와 치조골의 경계를 정확하게 분리하여 개별적으로 조작이 가능한 치아모델을 생성하기 위해서는 슬라스별로 두 영역을 분리할 수 있는 최적의 임계치가 결정되어야 한다. 본 연구에서는 좁은 간격으로 촬영한 연속적인 CT영상 슬라이스들 사이에서 치아들의 형태와 임계값이 점진적으로 변하는 성질을 이용하여 각 슬라스별로 최적의 임계치를 결정하여 치아영역을 분리하는 적응적인 최적 임계화 방안을 제안한다.