AUTHOR=Fan Xuhui , Xie Ni , Chen Jingwen , Li Tiewen , Cao Rong , Yu Hongwei , He Meijuan , Wang Zilin , Wang Yihui , Liu Hao , Wang Han , Yin Xiaorui 

TITLE=Multiparametric MRI and Machine Learning Based Radiomic Models for Preoperative Prediction of Multiple Biological Characteristics in Prostate Cancer

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.839621

DOI=10.3389/fonc.2022.839621

ISSN=2234-943X

ABSTRACT=Objectives: To develop and evaluate multi-parametric MRI (MP-MRI) based radiomic models as a non-invasive diagnostic method to predict several biological characteristics of prostate cancer.
Methods: 252 patients were retrospectively included who underwent radical prostatectomy and MP-MRI examinations. The prediction characteristics of this study were: Ki67, S100, extracapsular extension (ECE), perineural invasion (PNI) and surgical margin (SM). Patients were divided into training cohorts and validation cohorts in the ratio of 4:1 for each group. After lesion segmentation manually, radiomic features were extracted from MP-MRI images and some clinical factors were also included. Max relevance min redundancy (mRMR) and recursive feature elimination (RFE) based on random forest (RF) were adopted to select features. Six classifiers were included (SVM, KNN, RF, decision tree, logistic regression, XGBOOST) to find the best diagnostic performance among them. The diagnostic efficiency of the construction models was evaluated by ROC curves and quantified by AUC.
Results: RF performed best among the six classifiers for the four groups according to AUC values (Ki67=0.87, S100=0.80, ECE=0.85, PNI=0.82). The performance of SVM was relatively the best for SM (AUC=0.77). The number and importance of DCE features ranked first in the models of each group. The combined models of MP-MRI and clinical characteristics showed no significant difference compared to MP-MRI models according to Delong's tests.
Conclusions: Radiomics models based on MP-MRI have the potential to predict biological characteristics and are expected to be a noninvasive method to evaluate the risk stratification of prostate cancer.