Predicting Overall Survival with Deep Learning from 18F-FDG PET-CT Images in Patients with Hepatocellular Carcinoma before Liver Transplantation
Positron emission tomography and computed tomography with 18F-fluorodeoxyglucose (18F-FDG PET-CT) were used to predict outcomes after liver transplantation in patients with hepatocellular carcinoma (HCC). However, few approaches for prediction based on 18F-FDG PET-CT images that leverage automatic l...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-03-01
|
Series: | Diagnostics |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-4418/13/5/981 |
_version_ | 1797615512133304320 |
---|---|
author | Yung-Chi Lai Kuo-Chen Wu Chao-Jen Chang Yi-Jin Chen Kuan-Pin Wang Long-Bin Jeng Chia-Hung Kao |
author_facet | Yung-Chi Lai Kuo-Chen Wu Chao-Jen Chang Yi-Jin Chen Kuan-Pin Wang Long-Bin Jeng Chia-Hung Kao |
author_sort | Yung-Chi Lai |
collection | DOAJ |
description | Positron emission tomography and computed tomography with 18F-fluorodeoxyglucose (18F-FDG PET-CT) were used to predict outcomes after liver transplantation in patients with hepatocellular carcinoma (HCC). However, few approaches for prediction based on 18F-FDG PET-CT images that leverage automatic liver segmentation and deep learning were proposed. This study evaluated the performance of deep learning from 18F-FDG PET-CT images to predict overall survival in HCC patients before liver transplantation (LT). We retrospectively included 304 patients with HCC who underwent 18F-FDG PET/CT before LT between January 2010 and December 2016. The hepatic areas of 273 of the patients were segmented by software, while the other 31 were delineated manually. We analyzed the predictive value of the deep learning model from both FDG PET/CT images and CT images alone. The results of the developed prognostic model were obtained by combining FDG PET-CT images and combining FDG CT images (0.807 AUC vs. 0.743 AUC). The model based on FDG PET-CT images achieved somewhat better sensitivity than the model based on CT images alone (0.571 SEN vs. 0.432 SEN). Automatic liver segmentation from 18F-FDG PET-CT images is feasible and can be utilized to train deep-learning models. The proposed predictive tool can effectively determine prognosis (i.e., overall survival) and, thereby, select an optimal candidate of LT for patients with HCC. |
first_indexed | 2024-03-11T07:27:34Z |
format | Article |
id | doaj.art-5ffed6f7428b4b7d862a896c7da107a9 |
institution | Directory Open Access Journal |
issn | 2075-4418 |
language | English |
last_indexed | 2024-03-11T07:27:34Z |
publishDate | 2023-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Diagnostics |
spelling | doaj.art-5ffed6f7428b4b7d862a896c7da107a92023-11-17T07:30:49ZengMDPI AGDiagnostics2075-44182023-03-0113598110.3390/diagnostics13050981Predicting Overall Survival with Deep Learning from 18F-FDG PET-CT Images in Patients with Hepatocellular Carcinoma before Liver TransplantationYung-Chi Lai0Kuo-Chen Wu1Chao-Jen Chang2Yi-Jin Chen3Kuan-Pin Wang4Long-Bin Jeng5Chia-Hung Kao6Department of Nuclear Medicine, Feng Yuan Hospital, Ministry of Health and Welfare, Taichung 420210, TaiwanGraduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei 106319, TaiwanArtificial Intelligence Center, China Medical University Hospital, Taichung 404327, TaiwanArtificial Intelligence Center, China Medical University Hospital, Taichung 404327, TaiwanArtificial Intelligence Center, China Medical University Hospital, Taichung 404327, TaiwanOrgan Transplantation Center, China Medical University Hospital, Taichung 404327, TaiwanDepartment of Nuclear Medicine, PET Center, China Medical University Hospital, Taichung 404327, TaiwanPositron emission tomography and computed tomography with 18F-fluorodeoxyglucose (18F-FDG PET-CT) were used to predict outcomes after liver transplantation in patients with hepatocellular carcinoma (HCC). However, few approaches for prediction based on 18F-FDG PET-CT images that leverage automatic liver segmentation and deep learning were proposed. This study evaluated the performance of deep learning from 18F-FDG PET-CT images to predict overall survival in HCC patients before liver transplantation (LT). We retrospectively included 304 patients with HCC who underwent 18F-FDG PET/CT before LT between January 2010 and December 2016. The hepatic areas of 273 of the patients were segmented by software, while the other 31 were delineated manually. We analyzed the predictive value of the deep learning model from both FDG PET/CT images and CT images alone. The results of the developed prognostic model were obtained by combining FDG PET-CT images and combining FDG CT images (0.807 AUC vs. 0.743 AUC). The model based on FDG PET-CT images achieved somewhat better sensitivity than the model based on CT images alone (0.571 SEN vs. 0.432 SEN). Automatic liver segmentation from 18F-FDG PET-CT images is feasible and can be utilized to train deep-learning models. The proposed predictive tool can effectively determine prognosis (i.e., overall survival) and, thereby, select an optimal candidate of LT for patients with HCC.https://www.mdpi.com/2075-4418/13/5/98118F-fluorodeoxyglucose (18F-FDG)positron emission tomography and computed tomography (PET-CT)hepatocellular carcinoma (HCC)liver transplantation (LT)deep learning |
spellingShingle | Yung-Chi Lai Kuo-Chen Wu Chao-Jen Chang Yi-Jin Chen Kuan-Pin Wang Long-Bin Jeng Chia-Hung Kao Predicting Overall Survival with Deep Learning from 18F-FDG PET-CT Images in Patients with Hepatocellular Carcinoma before Liver Transplantation Diagnostics 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography and computed tomography (PET-CT) hepatocellular carcinoma (HCC) liver transplantation (LT) deep learning |
title | Predicting Overall Survival with Deep Learning from 18F-FDG PET-CT Images in Patients with Hepatocellular Carcinoma before Liver Transplantation |
title_full | Predicting Overall Survival with Deep Learning from 18F-FDG PET-CT Images in Patients with Hepatocellular Carcinoma before Liver Transplantation |
title_fullStr | Predicting Overall Survival with Deep Learning from 18F-FDG PET-CT Images in Patients with Hepatocellular Carcinoma before Liver Transplantation |
title_full_unstemmed | Predicting Overall Survival with Deep Learning from 18F-FDG PET-CT Images in Patients with Hepatocellular Carcinoma before Liver Transplantation |
title_short | Predicting Overall Survival with Deep Learning from 18F-FDG PET-CT Images in Patients with Hepatocellular Carcinoma before Liver Transplantation |
title_sort | predicting overall survival with deep learning from 18f fdg pet ct images in patients with hepatocellular carcinoma before liver transplantation |
topic | 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography and computed tomography (PET-CT) hepatocellular carcinoma (HCC) liver transplantation (LT) deep learning |
url | https://www.mdpi.com/2075-4418/13/5/981 |
work_keys_str_mv | AT yungchilai predictingoverallsurvivalwithdeeplearningfrom18ffdgpetctimagesinpatientswithhepatocellularcarcinomabeforelivertransplantation AT kuochenwu predictingoverallsurvivalwithdeeplearningfrom18ffdgpetctimagesinpatientswithhepatocellularcarcinomabeforelivertransplantation AT chaojenchang predictingoverallsurvivalwithdeeplearningfrom18ffdgpetctimagesinpatientswithhepatocellularcarcinomabeforelivertransplantation AT yijinchen predictingoverallsurvivalwithdeeplearningfrom18ffdgpetctimagesinpatientswithhepatocellularcarcinomabeforelivertransplantation AT kuanpinwang predictingoverallsurvivalwithdeeplearningfrom18ffdgpetctimagesinpatientswithhepatocellularcarcinomabeforelivertransplantation AT longbinjeng predictingoverallsurvivalwithdeeplearningfrom18ffdgpetctimagesinpatientswithhepatocellularcarcinomabeforelivertransplantation AT chiahungkao predictingoverallsurvivalwithdeeplearningfrom18ffdgpetctimagesinpatientswithhepatocellularcarcinomabeforelivertransplantation |