서강대, 연세의대 / 이상원, 최용*, 윤미진*
Abstract
Purpose: This study was to develop a convolutional neural network (CNN) model with a residual learning framework to predict the full-time 18F-florbetaben (18F-FBB) PET/CT images from corresponding short-time scans.
Methods: In this retrospective study, we enrolled 22 cognitively normal subjects, 20 patients with mild cognitive impairment, and 42 patients with Alzheimer disease. Twenty minutes of list-mode PET/CT data were acquired and reconstructed as the ground-truth images. The short-time scans were made in either 1, 2, 3, 4, or 5 minutes. The CNN with a residual learning framework was implemented to predict the ground-truth images of 18F-FBB PET/CT using short-time scans with either a single-slice or a 3-slice input layer. Model performance was evaluated by quantitative and qualitative analyses. Additionally, we quantified the amyloid load in the ground-truth and predicted images using the SUV ratio.
Results: On quantitative analyses, with increasing scan time, the normalized root-mean-squared error and the SUV ratio differences between predicted and ground-truth images gradually decreased, and the peak signal-to-noise ratio increased. On qualitative analysis, the predicted images from the 3-slice CNN model showed better image quality than those from the single-slice model. The 3-slice CNN model with a short-time scan of at least 2 minutes achieved comparable, quantitative prediction of full-time 18F-FBB PET/CT images, with adequate to excellent image quality.
Conclusions: The 3-slice CNN model with a residual learning framework is promising for the prediction of full-time 18F-FBB PET/CT images from short-time scans.
Affiliations
Sangwon Lee 1 , Jin Ho Jung 2 , Dongwoo Kim 1 , Hyun Keong Lim 2 , Mi-Ae Park 3 , Garam Kim 2 , Minjae So 4 , Sun Kook Yoo 5 , Byoung Seok Ye 6 , Yong Choi 2 , Mijin Yun 1
1 From the Department of Nuclear Medicine, Yonsei University College of Medicine.
2 Department of Electronic Engineering, Sogang University, Seoul, Korea.
3 Department of Radiology, Brigham and Women's Hospital & Harvard Medical School, Boston, MA.
4 Yonsei University College of Medicine.
5 Departments of Medical Engineering.
6 Neurology, Yonsei University College of Medicine, Seoul, Korea.
편집위원
Amyloid PET 영상에 인공지능 기술을 도입하여 영상획득 시간을 단축하고도 영상의 질을 유지하는 기법에 대한 연구임. 인공지능을 이용한 핵의학 영상 개선에 대한 연구내용으로 핵의학 영상의 인공적용 적용을 연구하는 연구자 및 신경 핵의학 임상가에게 관심을 끌 연구로 생각됨.
2021-05-06 15:24:22
편집위원
Amyloid PET 영상에 인공지능 기술을 도입하여 영상획득 시간을 단축하고도 영상의 질을 유지하는 기법에 대한 연구임. 인공지능을 이용한 핵의학 영상 개선에 대한 연구내용으로 핵의학 영상의 인공적용 적용을 연구하는 연구자 및 신경 핵의학 임상가에게 관심을 끌 연구로 생각됨.
2021-05-06 15:25:34