금속 음영이 포함된 CBCT 영상에서 딥러닝을 이용한 해부학적 구조물의 다중 클래스 분할 방법

Abstract

In order to perform preoperative surgical planning, accurate segmentation of anatomical structures in cone-beam computed tomography (CBCT) images is required. However, this image segmentation is often impeded by metal artifacts, and it takes a lot of time due to morphological variability in patients. In this paper, we proposed a deep learning based automatic multi-class segmentation method for anatomical structures in CBCT images containing metal artifacts. Four U-Net based deep learning models were used for anatomical structure segmentation. Each deep learning model was constructed by changing the encoder of U-Net architecture to the backbones (DenseNet121, VGGNet16, ResNet101, and EfficienNetB4). For training and testing our method, we used 20744 CBCT images containing metal artifacts from 30 patient datasets. Experimental results show that the segmentation performances of the mandible, midfacial bone, mandibular canal, and maxillary sinus were achieved F1 scores of 0.912±0.070, 0.880±0.080, 0.687±0.265, and 0.954±0.063 using DenseNet121 with Tversky loss, respectively. Furthermore, our method was able to perform robust and accurate segmentation of anatomical structures in CBCT images containing metal artifacts.