CT imaging markers to improve radiation toxicity prediction in prostate cancer radiotherapy by stacking regression algorithm

• Published in: Radiologia medica Vol. 125; no. 1; pp. 87 - 97
• Main Authors: Mostafaei, Shayan, Abdollahi, Hamid, Kazempour Dehkordi, Shiva, Shiri, Isaac, Razzaghdoust, Abolfazl, Zoljalali Moghaddam, Seyed Hamid, Saadipoor, Afshin, Koosha, Fereshteh, Cheraghi, Susan, Mahdavi, Seied Rabi
• Format: Journal Article
• Language: English
• Published: Milan Springer Milan 01.01.2020; Springer Nature B.V
• Subjects: Aged; Algorithms; Area Under Curve; Bladder; Computed tomography; Cystitis - etiology; Diagnostic Radiology; Feature extraction; Goodness of fit; Humans; Imaging; Interventional Radiology; Logistic Models; Male; Mathematical models; Medical imaging; Medicine; Medicine & Public Health; Middle Aged; Modelling; Neuroradiology; Oncology Imaging; Parameters; Performance prediction; Proctitis - etiology; Prospective Studies; Prostate cancer; Prostatic Neoplasms - radiotherapy; Radiation effects; Radiation Injuries - diagnostic imaging; Radiation Injuries - etiology; Radiation therapy; Radiation Tolerance; Radiology; Radiotherapy Dosage; Rectum - diagnostic imaging; Rectum - radiation effects; ROC Curve; Stacking; Tomography, X-Ray Computed - methods; Toxicity; Ultrasound; Urinary Bladder - diagnostic imaging; Urinary Bladder - radiation effects; Tomography; Stacking ensemble algorithm; Radiotherapy; Toxicity; Prostate cancer

Purpose Radiomic features, clinical and dosimetric factors have the potential to predict radiation-induced toxicity. The aim of this study was to develop prediction models of radiotherapy-induced toxicities in prostate cancer patients based on computed tomography (CT) radiomics, clinical and dosimet...