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

Abstract

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.

Comparative Study of Eclipse and RayStation Multi-Criteria Optimization-Based Prostate Radiotherapy Treatment Planning Quality

“…The gastrointestinal toxicity of prostate RT is a well-known issue [ 7 ]. Although the Eclipse MCO function seems effective to address this issue, the associated trade-off, increase dose to bladder appears concerning because this can cause hematuria, urinary incontinence and painful urination after prostate RT treatment [ 17 , 41 ].…”

“…Use of artificial intelligence (AI) such as machine learning (ML) and deep learning has become popular in medical imaging [ 7 , 9 , 43 , 44 , 45 ]. Apart from the MCO, knowledge-based planning function based on ML technology (known as RapidPlan) has also become available in recent versions of Eclipse [ 46 ].…”

“…To achieve similar full bladder status, the patients were required to empty their bladders and then drink 400 cc of water one hour before the scans. They were all positioned in a supine position on a vacuum bag with both hands on chest for non-contrast CT scans with 120 kV, 350–450 mAs, 3 mm slice thickness, 60 cm field of view, 512 × 512 matrix size, 1.18 pixel spacing, and a standard convolutional kernel for image reconstruction as per routine protocol at Pamela Youde Nethersole Eastern Hospital [ 7 ]. This study was conducted in accordance with the Declaration of Helsinki and approved by the Institutional Review Board of Hong Kong Polytechnic University (approval number: HSEARS20230727002 and date of approval: 3 August 2023) and Research Ethics Committee of Hong Kong East Cluster of Hospital Authority of Government of Hong Kong Special Administrative Region (approval number: HKECREC-2023-009 and date of approval: 14 March 2023), and patient consent was waived due to the study’s retrospective nature.…”

“…The OARs, CTV and PTV were subsequently reviewed and approved by another radiation oncologist with associate consultant grade or above for clinical use previously. These arrangements enabled the OARs and target volumes segmentation being more standardized [ 7 , 8 , 9 ].…”

“…Although prostate RT is a relatively less invasive treatment, use of ionizing radiation in this treatment may result in adverse effects on the rectum such as pain, bleeding and increase of stool frequency [5][6][7]. RT planning plays a crucial role in minimizing the dose received by nearby healthy structures known as organs at risk (OARs), and hence the adverse effects, while accurately delivering the prescribed radiation amount to the Diagnostics 2024, 14, 465 2 of 12 tumor (planning target volume (PTV)) for effective treatment [8][9][10].…”