18 F-FDG-PET/CT-based deep learning model for fully automated prediction of pathological grading for pancreatic ductal adenocarcinoma before surgery.

Autor: Zhang G; Medical School of Chinese PLA, Beijing, China.; Faculty of Hepato-Biliary-Pancreatic Surgery, The First Medical Center of Chinese People's Liberation Army (PLA) General Hospital, 28 Fuxing Road, Beijing, 100853, China., Bao C; School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, China.; Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, Jiangsu, China., Liu Y; Faculty of Hepato-Biliary-Pancreatic Surgery, The First Medical Center of Chinese People's Liberation Army (PLA) General Hospital, 28 Fuxing Road, Beijing, 100853, China., Wang Z; Senior Department of Hepatology, The Fifth Medical Center of Chinese People's Liberation Army (PLA) General Hospital, Beijing, China., Du L; Department of Nuclear Medicine, The First Medical Center of Chinese People's Liberation Army (PLA) General Hospital, Beijing, China., Zhang Y; School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, China.; Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, Jiangsu, China., Wang F; Faculty of Hepato-Biliary-Pancreatic Surgery, The First Medical Center of Chinese People's Liberation Army (PLA) General Hospital, 28 Fuxing Road, Beijing, 100853, China., Xu B; Department of Nuclear Medicine, The First Medical Center of Chinese People's Liberation Army (PLA) General Hospital, Beijing, China. xbx301@126.com., Zhou SK; School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, China. skevinzhou@ustc.edu.cn.; Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, Jiangsu, China. skevinzhou@ustc.edu.cn., Liu R; Faculty of Hepato-Biliary-Pancreatic Surgery, The First Medical Center of Chinese People's Liberation Army (PLA) General Hospital, 28 Fuxing Road, Beijing, 100853, China. liurong301@126.com.
Jazyk: angličtina
Zdroj: EJNMMI research [EJNMMI Res] 2023 May 25; Vol. 13 (1), pp. 49. Date of Electronic Publication: 2023 May 25.
DOI: 10.1186/s13550-023-00985-4
Abstrakt: Background: The determination of pathological grading has a guiding significance for the treatment of pancreatic ductal adenocarcinoma (PDAC) patients. However, there is a lack of an accurate and safe method to obtain pathological grading before surgery. The aim of this study is to develop a deep learning (DL) model based on 18 F-fluorodeoxyglucose-positron emission tomography/computed tomography ( 18 F-FDG-PET/CT) for a fully automatic prediction of preoperative pathological grading of pancreatic cancer.
Methods: A total of 370 PDAC patients from January 2016 to September 2021 were collected retrospectively. All patients underwent 18 F-FDG-PET/CT examination before surgery and obtained pathological results after surgery. A DL model for pancreatic cancer lesion segmentation was first developed using 100 of these cases and applied to the remaining cases to obtain lesion regions. After that, all patients were divided into training set, validation set, and test set according to the ratio of 5:1:1. A predictive model of pancreatic cancer pathological grade was developed using the features computed from the lesion regions obtained by the lesion segmentation model and key clinical characteristics of the patients. Finally, the stability of the model was verified by sevenfold cross-validation.
Results: The Dice score of the developed PET/CT-based tumor segmentation model for PDAC was 0.89. The area under curve (AUC) of the PET/CT-based DL model developed on the basis of the segmentation model was 0.74, with an accuracy, sensitivity, and specificity of 0.72, 0.73, and 0.72, respectively. After integrating key clinical data, the AUC of the model improved to 0.77, with its accuracy, sensitivity, and specificity boosted to 0.75, 0.77, and 0.73, respectively.
Conclusion: To the best of our knowledge, this is the first deep learning model to end-to-end predict the pathological grading of PDAC in a fully automatic manner, which is expected to improve clinical decision-making.
(© 2023. The Author(s).)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje