ABSTRACT
The extraction of positron emission tomography (PET) features has been regarded as a challenging task due to the metabolic interference of background issues, especially for patients with neurological disorders. In this paper, we proposed a computer-aided image subtraction technique for eliminating the metabolic interference of background issues and further highlighting lesions. To validate the feasibility of our technique, a study was conducted to review PET data before and after treatment in patients with anti-leucine-rich glioma-inactivated 1 (LGI1) encephalitis. The image subtraction procedure encompassed normalization, box out brain region, registration, and subtraction. The results demonstrated that the basal ganglia and medial temporal lobe were successfully extracted from 18F-FDG-PET images, which was also in agreement with clinical studies. This novel method was also proven to be effective for identifying changes in the metabolic rate of the brain before and after treatments for patients with anti-LGI1 encephalitis.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Additional information
Funding
Notes on contributors
Xuewei Mao
Xuewei Mao received a B.E. degree in measuring and controlling technologies and instruments and an M. E. degree in measuring technology and instrument from Tianjin University, Tianjin, China, in 2010 and 2013, respectively, and Ph.D. degrees in mechanical science and engineering from the Nagoya University, Nagoya, Japan, in 2017. She is currently an Assistant Professor at the Qingdao University of Automation. Her current research interests include artificial intelligence and the safety of human-wearable robot interaction.
Wei Shan
Wei Shan received his Ph.D. and M.D degrees at Nagoya University Japan in 2017. He is a physician in Beijing tian tan Hosptial. His current research interests include artificial intelligence and autoimmune encephalitis.
Wilson Fox
Wilson Fox got his Ph.D. degree at the National University of singpoo, and he currently is an engineer at Beijing Tiantan hospital and a co-work with Dr. Wei Shan.
Jinpeng Yu
Jinpeng Yu received a B.Sc. degree in automation from Qingdao University, Qingdao, China, in 2002, an M.Sc. degree in system engineering from Shandong University, Jinan, China, in 2006, and the Ph.D. degree from the Institute of Complexity Science, Qingdao University, in 2011. He is currently a Distinguished Professor at the School of Automation and Electrical Engineering, at Qingdao University. He is a recipient of the Shandong Province Taishan Scholar Special Project Fund and the Shandong Province Fund for Outstanding Young Scholars. His research interests include electrical energy conversion and motor control, applied nonlinear control, and intelligent systems.