Computed Tomography-Based Radiomics for Long-Term Prognostication of High-Risk Localized Prostate Cancer Patients Received Whole Pelvic Radiotherapy

Given the high death rate caused by high-risk prostate cancer (PCa) (>40%) and the reliability issues associated with traditional prognostic markers, the purpose of this study is to investigate planning computed tomography (pCT)-based radiomics for the long-term prognostication of high-risk local...

Full description

Bibliographic Details
Main Authors: Leung, Vincent WS, Ng, Curtise, Lam, Sai-Kit, Wong, Po-Tsz, Ng, Ka-Yan, Tam, Cheuk-Hong, Lee, Tsz-Ching, Chow, Kin-Chun, Chow, Yan-Kate, Tam, Victor CW, Lee, Shara WY, Lim, Fiona MY, Wu, Jackie Q, Cai, Jing
Format: Journal Article
Published: MDPI AG 2023
Subjects:
Online Access:Government of Hong Kong Special Administrative Region Health and Medical Research Fund Research Fellowship Scheme 2021, grant number 06200137; and The Hong Kong Polytechnic University Project of Strategic Importance Fund 2021, grant number P0035421
http://hdl.handle.net/20.500.11937/93832
_version_ 1848765795903995904
author Leung, Vincent WS
Ng, Curtise
Lam, Sai-Kit
Wong, Po-Tsz
Ng, Ka-Yan
Tam, Cheuk-Hong
Lee, Tsz-Ching
Chow, Kin-Chun
Chow, Yan-Kate
Tam, Victor CW
Lee, Shara WY
Lim, Fiona MY
Wu, Jackie Q
Cai, Jing
author_facet Leung, Vincent WS
Ng, Curtise
Lam, Sai-Kit
Wong, Po-Tsz
Ng, Ka-Yan
Tam, Cheuk-Hong
Lee, Tsz-Ching
Chow, Kin-Chun
Chow, Yan-Kate
Tam, Victor CW
Lee, Shara WY
Lim, Fiona MY
Wu, Jackie Q
Cai, Jing
author_sort Leung, Vincent WS
building Curtin Institutional Repository
collection Online Access
description Given the high death rate caused by high-risk prostate cancer (PCa) (>40%) and the reliability issues associated with traditional prognostic markers, the purpose of this study is to investigate planning computed tomography (pCT)-based radiomics for the long-term prognostication of high-risk localized PCa patients who received whole pelvic radiotherapy (WPRT). This is a retrospective study with methods based on best practice procedures for radiomics research. Sixty-four patients were selected and randomly assigned to training (n = 45) and testing (n = 19) cohorts for radiomics model development with five major steps: pCT image acquisition using a Philips Big Bore CT simulator; multiple manual segmentations of clinical target volume for the prostate (CTVprostate) on the pCT images; feature extraction from the CTVprostate using PyRadiomics; feature selection for overfitting avoidance; and model development with three-fold cross-validation. The radiomics model and signature performances were evaluated based on the area under the receiver operating characteristic curve (AUC) as well as accuracy, sensitivity and specificity. This study’s results show that our pCT-based radiomics model was able to predict the six-year progression-free survival of the high-risk localized PCa patients who received the WPRT with highly consistent performances (mean AUC: 0.76 (training) and 0.71 (testing)). These are comparable to findings of other similar studies including those using magnetic resonance imaging (MRI)-based radiomics. The accuracy, sensitivity and specificity of our radiomics signature that consisted of two texture features were 0.778, 0.833 and 0.556 (training) and 0.842, 0.867 and 0.750 (testing), respectively. Since CT is more readily available than MRI and is the standard-of-care modality for PCa WPRT planning, pCT-based radiomics could be used as a routine non-invasive approach to the prognostic prediction of WPRT treatment outcomes in high-risk localized PCa.
first_indexed 2025-11-14T11:40:56Z
format Journal Article
id curtin-20.500.11937-93832
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T11:40:56Z
publishDate 2023
publisher MDPI AG
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-938322024-01-15T03:26:03Z Computed Tomography-Based Radiomics for Long-Term Prognostication of High-Risk Localized Prostate Cancer Patients Received Whole Pelvic Radiotherapy Leung, Vincent WS Ng, Curtise Lam, Sai-Kit Wong, Po-Tsz Ng, Ka-Yan Tam, Cheuk-Hong Lee, Tsz-Ching Chow, Kin-Chun Chow, Yan-Kate Tam, Victor CW Lee, Shara WY Lim, Fiona MY Wu, Jackie Q Cai, Jing Artificial Intelligence Biomarker Machine Learning Malignancy Medical Imaging Prognosis Progression-Free Survival Radiation Therapy Recurrence Tumor Given the high death rate caused by high-risk prostate cancer (PCa) (>40%) and the reliability issues associated with traditional prognostic markers, the purpose of this study is to investigate planning computed tomography (pCT)-based radiomics for the long-term prognostication of high-risk localized PCa patients who received whole pelvic radiotherapy (WPRT). This is a retrospective study with methods based on best practice procedures for radiomics research. Sixty-four patients were selected and randomly assigned to training (n = 45) and testing (n = 19) cohorts for radiomics model development with five major steps: pCT image acquisition using a Philips Big Bore CT simulator; multiple manual segmentations of clinical target volume for the prostate (CTVprostate) on the pCT images; feature extraction from the CTVprostate using PyRadiomics; feature selection for overfitting avoidance; and model development with three-fold cross-validation. The radiomics model and signature performances were evaluated based on the area under the receiver operating characteristic curve (AUC) as well as accuracy, sensitivity and specificity. This study’s results show that our pCT-based radiomics model was able to predict the six-year progression-free survival of the high-risk localized PCa patients who received the WPRT with highly consistent performances (mean AUC: 0.76 (training) and 0.71 (testing)). These are comparable to findings of other similar studies including those using magnetic resonance imaging (MRI)-based radiomics. The accuracy, sensitivity and specificity of our radiomics signature that consisted of two texture features were 0.778, 0.833 and 0.556 (training) and 0.842, 0.867 and 0.750 (testing), respectively. Since CT is more readily available than MRI and is the standard-of-care modality for PCa WPRT planning, pCT-based radiomics could be used as a routine non-invasive approach to the prognostic prediction of WPRT treatment outcomes in high-risk localized PCa. 2023 Journal Article http://hdl.handle.net/20.500.11937/93832 10.3390/jpm13121643 Government of Hong Kong Special Administrative Region Health and Medical Research Fund Research Fellowship Scheme 2021, grant number 06200137; and The Hong Kong Polytechnic University Project of Strategic Importance Fund 2021, grant number P0035421 http://creativecommons.org/licenses/by/4.0/ MDPI AG fulltext
spellingShingle Artificial Intelligence
Biomarker
Machine Learning
Malignancy
Medical Imaging
Prognosis
Progression-Free Survival
Radiation Therapy
Recurrence
Tumor
Leung, Vincent WS
Ng, Curtise
Lam, Sai-Kit
Wong, Po-Tsz
Ng, Ka-Yan
Tam, Cheuk-Hong
Lee, Tsz-Ching
Chow, Kin-Chun
Chow, Yan-Kate
Tam, Victor CW
Lee, Shara WY
Lim, Fiona MY
Wu, Jackie Q
Cai, Jing
Computed Tomography-Based Radiomics for Long-Term Prognostication of High-Risk Localized Prostate Cancer Patients Received Whole Pelvic Radiotherapy
title Computed Tomography-Based Radiomics for Long-Term Prognostication of High-Risk Localized Prostate Cancer Patients Received Whole Pelvic Radiotherapy
title_full Computed Tomography-Based Radiomics for Long-Term Prognostication of High-Risk Localized Prostate Cancer Patients Received Whole Pelvic Radiotherapy
title_fullStr Computed Tomography-Based Radiomics for Long-Term Prognostication of High-Risk Localized Prostate Cancer Patients Received Whole Pelvic Radiotherapy
title_full_unstemmed Computed Tomography-Based Radiomics for Long-Term Prognostication of High-Risk Localized Prostate Cancer Patients Received Whole Pelvic Radiotherapy
title_short Computed Tomography-Based Radiomics for Long-Term Prognostication of High-Risk Localized Prostate Cancer Patients Received Whole Pelvic Radiotherapy
title_sort computed tomography-based radiomics for long-term prognostication of high-risk localized prostate cancer patients received whole pelvic radiotherapy
topic Artificial Intelligence
Biomarker
Machine Learning
Malignancy
Medical Imaging
Prognosis
Progression-Free Survival
Radiation Therapy
Recurrence
Tumor
url Government of Hong Kong Special Administrative Region Health and Medical Research Fund Research Fellowship Scheme 2021, grant number 06200137; and The Hong Kong Polytechnic University Project of Strategic Importance Fund 2021, grant number P0035421
http://hdl.handle.net/20.500.11937/93832