성균관의대 / 김수정, 최준영, 문승환*
Abstract
Positron emission tomography/computed tomography (PET/CT) with 18F-fluorodeoxyglucose (FDG) is widely used for management of nasopharyngeal carcinoma (NPC). Combining the radiomic features of pre- and post-treatment FDG PET images may improve tumor characterization and prognostic predication. We investigated prognostic value of radiomic features from pre- and post-radiotherapy FDG PET images in patients with NPC. Quantitative radiomic features of primary tumors were extracted from the FDG PET images of 145 NPC patients and the delta values were also calculated. The study population was divided randomly into two groups, the training and test sets (7:3). A random survival forest (RSF) model was adopted to perform analyses of progression-free survival (PFS) and overall survival (OS). There were 37 (25.5%) cases of recurrence and 16 (11.0%) cases of death during a median follow-up period of 54.5 months. Both RSF models with clinical variables and radiomic PET features for PFS and OS showed comparable predictive performance to RSF models with clinical variables and conventional PET parameters. Tumoral radiomic features of pre- and post-treatment FDG PET and the corresponding delta values may predict PFS and OS in patients with NPC.
Affiliations
Soo Jeong Kim # 1, Joon Young Choi # 2, Yong Chan Ahn 3, Myung-Ju Ahn 4, Seung Hwan Moon 5
1Department of Nuclear Medicine, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, 29, Saemunan-ro, Jongno-gu, Seoul, 03181, Republic of Korea.
2Department of Nuclear Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81, Irwon-ro, Gangnam-gu, Seoul, 06351, Republic of Korea.
3Department of Radiation Oncology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea.
4Division of Hematology-Oncology, Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea.
5Department of Nuclear Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81, Irwon-ro, Gangnam-gu, Seoul, 06351, Republic of Korea. seunghwan.moons.moon@samsung.com.
#Contributed equally.