Cargando…

Assessing PD-L1 Expression Level via Preoperative MRI in HCC Based on Integrating Deep Learning and Radiomics Features

To assess if quantitative integrated deep learning and radiomics features can predict the PD-L1 expression level in preoperative MRI of hepatocellular carcinoma (HCC) patients. The data in this study consist of 103 hepatocellular carcinoma patients who received immunotherapy in a single center. Thes...

Descripción completa

Detalles Bibliográficos
Autores principales: Tian, Yuchi, Komolafe, Temitope Emmanuel, Zheng, Jian, Zhou, Guofeng, Chen, Tao, Zhou, Bo, Yang, Xiaodong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8534850/
https://www.ncbi.nlm.nih.gov/pubmed/34679573
http://dx.doi.org/10.3390/diagnostics11101875
_version_ 1784587642843693056
author Tian, Yuchi
Komolafe, Temitope Emmanuel
Zheng, Jian
Zhou, Guofeng
Chen, Tao
Zhou, Bo
Yang, Xiaodong
author_facet Tian, Yuchi
Komolafe, Temitope Emmanuel
Zheng, Jian
Zhou, Guofeng
Chen, Tao
Zhou, Bo
Yang, Xiaodong
author_sort Tian, Yuchi
collection PubMed
description To assess if quantitative integrated deep learning and radiomics features can predict the PD-L1 expression level in preoperative MRI of hepatocellular carcinoma (HCC) patients. The data in this study consist of 103 hepatocellular carcinoma patients who received immunotherapy in a single center. These patients were divided into a high PD-L1 expression group (30 patients) and a low PD-L1 expression group (73 patients). Both radiomics and deep learning features were extracted from their MRI sequence of T2-WI, which were merged into an integrative feature space for machine learning for the prediction of PD-L1 expression. The five-fold cross-validation was adopted to validate the performance of the model, while the AUC was used to assess the predictive ability of the model. Based on the five-fold cross-validation, the integrated model achieved the best prediction performance, with an AUC score of 0.897 ± 0.084, followed by the deep learning-based model with an AUC of 0.852 ± 0.043 then the radiomics-based model with AUC of 0.794 ± 0.035. The feature set integrating radiomics and deep learning features is more effective in predicting PD-L1 expression level than only one feature type. The integrated model can achieve fast and accurate prediction of PD-L1 expression status in preoperative MRI of HCC patients.
format Online
Article
Text
id pubmed-8534850
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-85348502021-10-23 Assessing PD-L1 Expression Level via Preoperative MRI in HCC Based on Integrating Deep Learning and Radiomics Features Tian, Yuchi Komolafe, Temitope Emmanuel Zheng, Jian Zhou, Guofeng Chen, Tao Zhou, Bo Yang, Xiaodong Diagnostics (Basel) Article To assess if quantitative integrated deep learning and radiomics features can predict the PD-L1 expression level in preoperative MRI of hepatocellular carcinoma (HCC) patients. The data in this study consist of 103 hepatocellular carcinoma patients who received immunotherapy in a single center. These patients were divided into a high PD-L1 expression group (30 patients) and a low PD-L1 expression group (73 patients). Both radiomics and deep learning features were extracted from their MRI sequence of T2-WI, which were merged into an integrative feature space for machine learning for the prediction of PD-L1 expression. The five-fold cross-validation was adopted to validate the performance of the model, while the AUC was used to assess the predictive ability of the model. Based on the five-fold cross-validation, the integrated model achieved the best prediction performance, with an AUC score of 0.897 ± 0.084, followed by the deep learning-based model with an AUC of 0.852 ± 0.043 then the radiomics-based model with AUC of 0.794 ± 0.035. The feature set integrating radiomics and deep learning features is more effective in predicting PD-L1 expression level than only one feature type. The integrated model can achieve fast and accurate prediction of PD-L1 expression status in preoperative MRI of HCC patients. MDPI 2021-10-12 /pmc/articles/PMC8534850/ /pubmed/34679573 http://dx.doi.org/10.3390/diagnostics11101875 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Tian, Yuchi
Komolafe, Temitope Emmanuel
Zheng, Jian
Zhou, Guofeng
Chen, Tao
Zhou, Bo
Yang, Xiaodong
Assessing PD-L1 Expression Level via Preoperative MRI in HCC Based on Integrating Deep Learning and Radiomics Features
title Assessing PD-L1 Expression Level via Preoperative MRI in HCC Based on Integrating Deep Learning and Radiomics Features
title_full Assessing PD-L1 Expression Level via Preoperative MRI in HCC Based on Integrating Deep Learning and Radiomics Features
title_fullStr Assessing PD-L1 Expression Level via Preoperative MRI in HCC Based on Integrating Deep Learning and Radiomics Features
title_full_unstemmed Assessing PD-L1 Expression Level via Preoperative MRI in HCC Based on Integrating Deep Learning and Radiomics Features
title_short Assessing PD-L1 Expression Level via Preoperative MRI in HCC Based on Integrating Deep Learning and Radiomics Features
title_sort assessing pd-l1 expression level via preoperative mri in hcc based on integrating deep learning and radiomics features
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8534850/
https://www.ncbi.nlm.nih.gov/pubmed/34679573
http://dx.doi.org/10.3390/diagnostics11101875
work_keys_str_mv AT tianyuchi assessingpdl1expressionlevelviapreoperativemriinhccbasedonintegratingdeeplearningandradiomicsfeatures
AT komolafetemitopeemmanuel assessingpdl1expressionlevelviapreoperativemriinhccbasedonintegratingdeeplearningandradiomicsfeatures
AT zhengjian assessingpdl1expressionlevelviapreoperativemriinhccbasedonintegratingdeeplearningandradiomicsfeatures
AT zhouguofeng assessingpdl1expressionlevelviapreoperativemriinhccbasedonintegratingdeeplearningandradiomicsfeatures
AT chentao assessingpdl1expressionlevelviapreoperativemriinhccbasedonintegratingdeeplearningandradiomicsfeatures
AT zhoubo assessingpdl1expressionlevelviapreoperativemriinhccbasedonintegratingdeeplearningandradiomicsfeatures
AT yangxiaodong assessingpdl1expressionlevelviapreoperativemriinhccbasedonintegratingdeeplearningandradiomicsfeatures