Journal of Oncology / 2021 / Article / Tab 5 / Review Article
Machine Learning: Applications and Advanced Progresses of Radiomics in Endocrine Neoplasms Table 5 Different clinical applications of radiomic models (features) in prostate cancer.
References Case numbers Radiomic method Results [147 ] 206 MRI The phenotype of clinically significant peripheral zone PCa lesions could be predicted by using radiomic features [148 ] 381 MRI Radiomic prediction model had an improved diagnostic ability when compared with the clinical model [149 ] 117 MRI Radiomic model was adaptive to detect dominant intraprostatic lesions in patients with PCa [150 ] 30 MRI Quantitative radiomic features based on MRI radiomics could be utilized to predict the localization of PCa [151 ] 50 US Quantitative radiomic features based on US radiomics could be utilized to predict the localization of PCa [144 ] 381 MRI MRI-based radiomic models had a reliable ability to distinguish PCa with non-PCa patients as well as assess the tumor aggressiveness [153 ] 73 MRI Radiomic features had the potential to predict risk stratification of PCa [156 ] 23 MRI The focal treatment plans formed by using the framework were decreased in dosage to the organs at risk and a boosted dose delivered to the cancerous lesions [158 ] 62 MRI Radiomic features had good classification performance for Gleason score of patients in PCa [159 ] 71 MRI Radiomic features had the potential to predict the prognosis of PCa [160 ] 107 MRI Radiomic features were predictive of biochemical recurrence after prostatectomy in PCa [161 ] 120 MRI Radiomic features can be predictive of PCa BCR and may help identify men who would benefit from adjuvant therapy [162 ] 91 MRI MRI-based radiomics could predict BCR of localized PCa after radiation therapy [163 ] 195 MRI MRI-based radiomic models had the potential to predict BCR of high-risk PCa