Cone-beam computed tomography-based radiomics in prostate cancer: a mono-institutional study

Autor: Letizia Deantonio, Maria Antonietta Piliero, Antonella Richetti, Mariacarla Valli, Linda C. van der Gaag, Davide Giovanni Bosetti, Stefano Presilla, Marco Bosetti, G. Pesce, Lorenzo Ruinelli
Rok vydání: 2020
Předmět:
Male
Biochemical recurrence
Cone beam computed tomography
medicine.medical_specialty
medicine.medical_treatment
Adenocarcinoma
030218 nuclear medicine & medical imaging
Machine Learning
03 medical and health sciences
Prostate cancer
0302 clinical medicine
Image Processing
Computer-Assisted
medicine
Humans
Radiology
Nuclear Medicine and imaging
Aged
Neoplasm Staging
Aged
80 and over
Receiver operating characteristic
business.industry
Radiotherapy Planning
Computer-Assisted
Computational Biology
Prostatic Neoplasms
Cancer
Cone-Beam Computed Tomography
Middle Aged
Prostate-Specific Antigen
medicine.disease
Radiation therapy
Logistic Models
ROC Curve
Oncology
Feature (computer vision)
Area Under Curve
030220 oncology & carcinogenesis
Kurtosis
Radiotherapy
Intensity-Modulated
Radiology
Neoplasm Grading
business
Zdroj: Strahlentherapie und Onkologie. 196:943-951
ISSN: 1439-099X
0179-7158
DOI: 10.1007/s00066-020-01677-x
Popis: The purpose of the reported study was to investigate the value of cone-beam computed tomography (CBCT)-based radiomics for risk stratification and prediction of biochemical relapse in prostate cancer. The study population consisted of 31 prostate cancer patients. Radiomics features were extracted from weekly CBCT scans performed for verifying treatment position. From the data, logistic-regression models were learned for establishing tumor stage, Gleason score, level of prostate-specific antigen, and risk stratification, and for predicting biochemical recurrence. Performance of the learned models was assessed using the area under the receiver operating characteristic curve (AUC-ROC) or the area under the precision-recall curve (AUC-PRC). Results suggest that the histogram-based Energy and Kurtosis features and the shape-based feature representing the standard deviation of the maximum diameter of the prostate gland during treatment are predictive of biochemical relapse and indicative of patients at high risk. Our results suggest the usefulness of CBCT-based radiomics for treatment definition in prostate cancer.
Databáze: OpenAIRE
Externí odkaz: