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

Abstract

ObjectivesThis study aims to develop and evaluate multiparametric MRI (MP-MRI)-based radiomic models as a noninvasive diagnostic method to predict several biological characteristics of prostate cancer.MethodsA total of 252 patients were retrospectively included who underwent radical prostatectomy and MP-MRI examinations. The prediction characteristics of this study were as follows: 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.ResultsRF 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 with MP-MRI models according to Delong’s tests.ConclusionsRadiomics 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.

Artificial intelligence in multiparametric magnetic resonance imaging: A review

“…In addition to the previously mentioned two tasks, machine learning methods have also been introduced to predict the biological characteristics of prostate cancer, which might be able to affect the treatment decision making. Extracapsular extension has been one frequently evaluated factor 209,212,218–220,227 . Other factors, including Ki‐67, S100, perineural invasion, and surgical margin, have also been investigated 218,227 .…”

“…Extracapsular extension has been one frequently evaluated factor. 209,212,[218][219][220]227 Other factors, including Ki-67, S100, perineural invasion, and surgical margin, have also been investigated. 218,227 Besides, there is one study predicting pelvic lymph node invasion for prostate cancer patients utilizing mpMRI-based radiomics models.…”

“…209,212,[218][219][220]227 Other factors, including Ki-67, S100, perineural invasion, and surgical margin, have also been investigated. 218,227 Besides, there is one study predicting pelvic lymph node invasion for prostate cancer patients utilizing mpMRI-based radiomics models. 226 To conclude this section, the identification of clinically significant prostate cancer is an important task that has been extensively investigated.…”

CT-based radiomics for predicting pathological grade in hepatocellular carcinoma

“…Our study's ROC curves indicated that the AP+VP model (without laboratory indices) was the best model for pathological grade prediction; therefore, radiomic features can be regarded as more important than other indices. As high-dimensional features, wavelet texture features cannot be easily deciphered by humans but can be used to detect tumor heterogeneity ( 34 , 35 ), whereas LoG-filtered texture features enhance image grayscale contrast and can also reflect tumor heterogeneity ( 36 , 37 ). Tumor heterogeneity reflected by wavelet texture features and LoG-filtered texture features explains why 12 wavelet texture features and 8 LoG-filtered texture features played leading roles in pathological grade prediction among the 24 features contained in the AP+VP model.…”

Combining androgen deprivation and radiation therapy in the treatment of localised prostate cancer: Summary of level 1 evidence and current gaps in knowledge

“…Other prognosis markers are currently being evaluated. For instance machine and deep learning [73] or radiomics, which consists in extracting data from imaging examination to lead to better diagnoses [74] might help to more precisely classify patients, in order to tailor the treatment strategy.…”