Defining a radiomics feature selection method for predicting response to transarterial chemoembolization in hepatocellular carcinoma patients

Aim: To assess the utility of different radiomics feature selection methods in predicting transarterial chemoembolization (TACE) response in hepatocellular carcinoma (HCC) patients. Materials and methods: This study employed a dataset of 136 paired MR T1-weighted contrast-enhanced abdominal images w...

Full description

Saved in:
Bibliographic Details
Main Authors: Helen Zhang, Li Yang, Amanda Laguna, Jing Wu, Beiji Zou, Alireza Mohseni, Rajat S. Chandra, Tej I. Mehta, Hossam A. Zaki, Paul Zhang, Zhicheng Jiao, Ihab R. Kamel, Harrison X. Bai
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2024-03-01
Series:Meta-Radiology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2950162824000201
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846170003735314432
author Helen Zhang
Li Yang
Amanda Laguna
Jing Wu
Beiji Zou
Alireza Mohseni
Rajat S. Chandra
Tej I. Mehta
Hossam A. Zaki
Paul Zhang
Zhicheng Jiao
Ihab R. Kamel
Harrison X. Bai
author_facet Helen Zhang
Li Yang
Amanda Laguna
Jing Wu
Beiji Zou
Alireza Mohseni
Rajat S. Chandra
Tej I. Mehta
Hossam A. Zaki
Paul Zhang
Zhicheng Jiao
Ihab R. Kamel
Harrison X. Bai
author_sort Helen Zhang
collection DOAJ
description Aim: To assess the utility of different radiomics feature selection methods in predicting transarterial chemoembolization (TACE) response in hepatocellular carcinoma (HCC) patients. Materials and methods: This study employed a dataset of 136 paired MR T1-weighted contrast-enhanced abdominal images with liver tumor masks before and after TACE. TACE response for each image pair was classified by European Association for the Study of the Liver (EASL) and modified Response Evaluation Criteria in Solid Tumors (mRECIST) guidelines. 100D feature vectors were generated for the paired tumor areas. Eighteen existing feature selection methods were employed to select the top-k features to train and test a non-linear support vector machine (SVM) with a Gaussian kernel. Five-cross validation was performed to identify the highest performing feature selection methods. Results: For all benchmarks, a L0-based method selecting the top-5 or top-10 features achieved the highest performance. For images classified with EASL criteria that were analyzed with the L0-based method, the accuracy (ACC), area under curve (AUC), and balanced F score (F1-score) were 0.75 ​± ​0.06, 0.75 ​± ​0.09, and 0.80 ​± ​0.05, respectively. For images classified with mRECIST criteria that were analyzed with the L0-based method, the ACC, AUC, and F1-score were 0.75 ​± ​0.07, 0.71 ​± ​0.16, and 0.82 ​± ​0.04, respectively. Conclusion: A L0-based method that selected the top-5/10 most important features predicted TACE response in HCC patients with the highest accuracy under both EASL and mRECIST criteria. This proof-of-concept investigation represents a step forward in the development of a reliable clinical decision-making tool for management of intermediate HCC patients undergoing TACE.
format Article
id doaj-art-41f4dbda92a24c60b241fc4c5b00b4e1
institution Kabale University
issn 2950-1628
language English
publishDate 2024-03-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Meta-Radiology
spelling doaj-art-41f4dbda92a24c60b241fc4c5b00b4e12024-11-12T05:22:42ZengKeAi Communications Co., Ltd.Meta-Radiology2950-16282024-03-0121100067Defining a radiomics feature selection method for predicting response to transarterial chemoembolization in hepatocellular carcinoma patientsHelen Zhang0Li Yang1Amanda Laguna2Jing Wu3Beiji Zou4Alireza Mohseni5Rajat S. Chandra6Tej I. Mehta7Hossam A. Zaki8Paul Zhang9Zhicheng Jiao10Ihab R. Kamel11Harrison X. Bai12The Warren Alpert Medical School of Brown University, Providence, RI, USAThe Warren Alpert Medical School of Brown University, Providence, RI, USA; School of Informatics, Hunan University of Chinese Medicine, Changsha, PR ChinaThe Warren Alpert Medical School of Brown University, Providence, RI, USA; Johns Hopkins University, Baltimore, MD, USADepartment of Radiology, Second Xiangya Hospital, Changsha, PR ChinaSchool of Informatics, Hunan University of Chinese Medicine, Changsha, PR China; School of Computer Science and Engineering, Central South University, Changsha, PR ChinaJohns Hopkins University, Baltimore, MD, USAPerelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, USAJohns Hopkins University, Baltimore, MD, USAThe Warren Alpert Medical School of Brown University, Providence, RI, USADepartment of Pathology and Laboratory Medicine, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, USARhode Island Hospital, Providence, RI, USADepartment of Radiology, University of Colorado School of Medicine, Aurora, CO, USAJohns Hopkins University, Baltimore, MD, USA; Corresponding author.Aim: To assess the utility of different radiomics feature selection methods in predicting transarterial chemoembolization (TACE) response in hepatocellular carcinoma (HCC) patients. Materials and methods: This study employed a dataset of 136 paired MR T1-weighted contrast-enhanced abdominal images with liver tumor masks before and after TACE. TACE response for each image pair was classified by European Association for the Study of the Liver (EASL) and modified Response Evaluation Criteria in Solid Tumors (mRECIST) guidelines. 100D feature vectors were generated for the paired tumor areas. Eighteen existing feature selection methods were employed to select the top-k features to train and test a non-linear support vector machine (SVM) with a Gaussian kernel. Five-cross validation was performed to identify the highest performing feature selection methods. Results: For all benchmarks, a L0-based method selecting the top-5 or top-10 features achieved the highest performance. For images classified with EASL criteria that were analyzed with the L0-based method, the accuracy (ACC), area under curve (AUC), and balanced F score (F1-score) were 0.75 ​± ​0.06, 0.75 ​± ​0.09, and 0.80 ​± ​0.05, respectively. For images classified with mRECIST criteria that were analyzed with the L0-based method, the ACC, AUC, and F1-score were 0.75 ​± ​0.07, 0.71 ​± ​0.16, and 0.82 ​± ​0.04, respectively. Conclusion: A L0-based method that selected the top-5/10 most important features predicted TACE response in HCC patients with the highest accuracy under both EASL and mRECIST criteria. This proof-of-concept investigation represents a step forward in the development of a reliable clinical decision-making tool for management of intermediate HCC patients undergoing TACE.http://www.sciencedirect.com/science/article/pii/S2950162824000201RadiomicsFeature selectionMachine learningHepatocellular carcinomaTransarterial chemoembolization
spellingShingle Helen Zhang
Li Yang
Amanda Laguna
Jing Wu
Beiji Zou
Alireza Mohseni
Rajat S. Chandra
Tej I. Mehta
Hossam A. Zaki
Paul Zhang
Zhicheng Jiao
Ihab R. Kamel
Harrison X. Bai
Defining a radiomics feature selection method for predicting response to transarterial chemoembolization in hepatocellular carcinoma patients
Meta-Radiology
Radiomics
Feature selection
Machine learning
Hepatocellular carcinoma
Transarterial chemoembolization
title Defining a radiomics feature selection method for predicting response to transarterial chemoembolization in hepatocellular carcinoma patients
title_full Defining a radiomics feature selection method for predicting response to transarterial chemoembolization in hepatocellular carcinoma patients
title_fullStr Defining a radiomics feature selection method for predicting response to transarterial chemoembolization in hepatocellular carcinoma patients
title_full_unstemmed Defining a radiomics feature selection method for predicting response to transarterial chemoembolization in hepatocellular carcinoma patients
title_short Defining a radiomics feature selection method for predicting response to transarterial chemoembolization in hepatocellular carcinoma patients
title_sort defining a radiomics feature selection method for predicting response to transarterial chemoembolization in hepatocellular carcinoma patients
topic Radiomics
Feature selection
Machine learning
Hepatocellular carcinoma
Transarterial chemoembolization
url http://www.sciencedirect.com/science/article/pii/S2950162824000201
work_keys_str_mv AT helenzhang definingaradiomicsfeatureselectionmethodforpredictingresponsetotransarterialchemoembolizationinhepatocellularcarcinomapatients
AT liyang definingaradiomicsfeatureselectionmethodforpredictingresponsetotransarterialchemoembolizationinhepatocellularcarcinomapatients
AT amandalaguna definingaradiomicsfeatureselectionmethodforpredictingresponsetotransarterialchemoembolizationinhepatocellularcarcinomapatients
AT jingwu definingaradiomicsfeatureselectionmethodforpredictingresponsetotransarterialchemoembolizationinhepatocellularcarcinomapatients
AT beijizou definingaradiomicsfeatureselectionmethodforpredictingresponsetotransarterialchemoembolizationinhepatocellularcarcinomapatients
AT alirezamohseni definingaradiomicsfeatureselectionmethodforpredictingresponsetotransarterialchemoembolizationinhepatocellularcarcinomapatients
AT rajatschandra definingaradiomicsfeatureselectionmethodforpredictingresponsetotransarterialchemoembolizationinhepatocellularcarcinomapatients
AT tejimehta definingaradiomicsfeatureselectionmethodforpredictingresponsetotransarterialchemoembolizationinhepatocellularcarcinomapatients
AT hossamazaki definingaradiomicsfeatureselectionmethodforpredictingresponsetotransarterialchemoembolizationinhepatocellularcarcinomapatients
AT paulzhang definingaradiomicsfeatureselectionmethodforpredictingresponsetotransarterialchemoembolizationinhepatocellularcarcinomapatients
AT zhichengjiao definingaradiomicsfeatureselectionmethodforpredictingresponsetotransarterialchemoembolizationinhepatocellularcarcinomapatients
AT ihabrkamel definingaradiomicsfeatureselectionmethodforpredictingresponsetotransarterialchemoembolizationinhepatocellularcarcinomapatients
AT harrisonxbai definingaradiomicsfeatureselectionmethodforpredictingresponsetotransarterialchemoembolizationinhepatocellularcarcinomapatients