연세의대 / 임정호, 이익재, 이호*
Objective: This study aimed to investigate the segmentation accuracy of organs at risk (OARs) when denoised computed tomography (CT) images are used as input data for a deep-learning-based auto-segmentation framework.
Methods: We used non-contrast enhanced planning CT scans from 40 patients with breast cancer. The heart, lungs, esophagus, spinal cord, and liver were manually delineated by two experienced radiation oncologists in a double-blind manner. The denoised CT images were used as input data for the AccuContourTM segmentation software to increase the signal difference between structures of interest and unwanted noise in non-contrast CT. The accuracy of the segmentation was assessed using the Dice similarity coefficient (DSC), and the results were compared with those of conventional deep-learning-based auto-segmentation without denoising.
Results: The average DSC outcomes were higher than 0.80 for all OARs except for the esophagus. AccuContourTM-based and denoising-based auto-segmentation demonstrated comparable performance for the lungs and spinal cord but showed limited performance for the esophagus. Denoising-based auto-segmentation for the liver was minimal but had statistically significantly better DSC than AccuContourTM-based auto-segmentation (p < 0.05).
Conclusions: Denoising-based auto-segmentation demonstrated satisfactory performance in automatic liver segmentation from non-contrast enhanced CT scans. Further external validation studies with larger cohorts are needed to verify the usefulness of denoising-based auto-segmentation.
저잡음 필터링을 이용한 딥러닝기반 자동분할 워크플로우
Jung Ho Im 1 , Ik Jae Lee 2 , Yeonho Choi 3 , Jiwon Sung 2 , Jin Sook Ha 3 , Ho Lee 2
1 CHA Bundang Medical Center, Department of Radiation Oncology, CHA University School of Medicine, Seongnam 13496, Korea.
2 Department of Radiation Oncology, Yonsei University College of Medicine, Seoul 03722, Korea.
3 Department of Radiation Oncology, Gangnam Severance Hospital, Seoul 06273, Korea.