The Use of MRI-Derived Radiomic Models in Prostate Cancer Risk Stratification: A Critical Review of Contemporary Literature

Developing a Predictive Model for Significant Prostate Cancer Detection in Prostatic Biopsies from Seven Clinical Variables: Is Machine Learning Superior to Logistic Regression?

Objective: This study compares machine learning (ML) and logistic regression (LR) algorithms in developing a predictive model for sPCa using the seven predictive variables from the Barcelona (BCN-MRI) predictive model. Method: A cohort of 5005 men suspected of having PCa who underwent MRI and targeted and/or systematic biopsies was used for training, testing, and validation. A feedforward neural network (FNN)-based SimpleNet model (GMV) and a logistic regression-based model (BCN) were developed. The models were evaluated for discrimination ability, precision-recall, net benefit, and clinical utility. Both models demonstrated strong predictive performance. Results: The GMV model achieved an area under the curve of 0.88 in training and 0.85 in test cohorts (95% CI: 0.83-0.90), while the BCN model reached 0.85 and 0.84 (95% CI: 0.82-0.87), respectively (p > 0.05). The GMV model exhibited higher recall, making it more suitable for clinical scenarios prioritizing sensitivity, whereas the BCN model demonstrated higher precision and specificity, optimizing the reduction of unnecessary biopsies. Both models provided similar clinical benefit over biopsying all men, reducing unnecessary procedures by 27.5-29% and 27-27.5% of prostate biopsies at 95% sensitivity, respectively (p > 0.05). Conclusions: Our findings suggest that both ML and LR models offer high accuracy in sPCa detection, with ML exhibiting superior recall and LR optimizing specificity. These results highlight the need for model selection based on clinical priorities.

Promising Results About the Possibility to Identify Prostate Cancer Patients Employing a Random Forest Classifier: A Preliminary Study Preoperative Patients Selection

Objective: This study evaluates the accuracy of a Machine Learning model of Random Forest (RF) type, using MRI data and radiomic features to predict lymph node involvement in prostate cancer (PCa). Methods: Ninety-five patients who underwent mp-MRI, prostatectomy, and lymphadenectomy at the Fondazione Policlinico Campus Bio-medico Radiological Department from 2016 to 2022 were analyzed. Radiomic features were extracted from T2-weighted, DWI, and ADC sequences and processed using a Random Forest (RF) model. Clinical data such as PSA levels and Gleason scores were also considered. Results: The RF model demonstrated significant accuracy in predicting lymph node involvement, achieving 84% accuracy for nodules in the peripheral zone (80% for predicting positive lymph node involvement and 85% for negative lymph node involvement) and 87% for those in the transitional zone (86% for predicting positive lymph node involvement and 88% for negative lymph node involvement). In the peripheral zone, key features included ADC shape maximum 2D diameter row and T2 noduloglcm difference variance, while in the transitional zone, DWI glcm difference average and DWI glcm Idm were important. DWI and ADC sequences were particularly crucial for accurate lymph node assessment. First-order features emerged as the most significant in whole-gland analysis, indicating fundamental differences in tumor composition and density critical for identifying malignancies with higher metastatic potential. Conclusions: AI-driven radiomic analysis, especially using DWI- and ADC-derived features, effectively predicts lymph node involvement in PCa patients, in particular in negative linfonode status patients, offering a promising tool for preoperative linfonode sparing patient selection. Further validation with larger cohorts is needed. Some limitations of this study are a relatively small sample size and it being a retrospective study.

Optimizing radiomics for prostate cancer diagnosis: feature selection strategies, machine learning classifiers, and MRI sequences

OBJECTIVES

Radiomics-based analyses encompass multiple steps, leading to ambiguity regarding the optimal approaches for enhancing model performance. This study compares the effect of several feature selection methods, machine learning (ML) classifiers, and sources of radiomic features, on models' performance for the diagnosis of clinically significant prostate cancer (csPCa) from bi-parametric MRI.

METHODS

Two multi-centric datasets, with 465 and 204 patients each, were used to extract 1246 radiomic features per patient and MRI sequence. Ten feature selection methods, such as Boruta, mRMRe, ReliefF, recursive feature elimination (RFE), random forest (RF) variable importance, L1-lasso, etc., four ML classifiers, namely SVM, RF, LASSO, and boosted generalized linear model (GLM), and three sets of radiomics features, derived from T2w images, ADC maps, and their combination, were used to develop predictive models of csPCa. Their performance was evaluated in a nested cross-validation and externally, using seven performance metrics.

RESULTS

In total, 480 models were developed. In nested cross-validation, the best model combined Boruta with Boosted GLM (AUC = 0.71, F1 = 0.76). In external validation, the best model combined L1-lasso with boosted GLM (AUC = 0.71, F1 = 0.47). Overall, Boruta, RFE, L1-lasso, and RF variable importance were the top-performing feature selection methods, while the choice of ML classifier didn't significantly affect the results. The ADC-derived features showed the highest discriminatory power with T2w-derived features being less informative, while their combination did not lead to improved performance.

CONCLUSION

The choice of feature selection method and the source of radiomic features have a profound effect on the models' performance for csPCa diagnosis.

CRITICAL RELEVANCE STATEMENT

This work may guide future radiomic research, paving the way for the development of more effective and reliable radiomic models; not only for advancing prostate cancer diagnostic strategies, but also for informing broader applications of radiomics in different medical contexts.

KEY POINTS

Radiomics is a growing field that can still be optimized. Feature selection method impacts radiomics models' performance more than ML algorithms. Best feature selection methods: RFE, LASSO, RF, and Boruta. ADC-derived radiomic features yield more robust models compared to T2w-derived radiomic features.

Data Science Opportunities To Improve Radiotherapy Planning and Clinical Decision Making

Radiotherapy aims to achieve a high tumor control probability while minimizing damage to normal tissues. Personalizing radiotherapy treatments for individual patients, therefore, depends on integrating physical treatment planning with predictive models of tumor control and normal tissue complications. Predictive models could be improved using a wide range of rich data sources, including tumor and normal tissue genomics, radiomics, and dosiomics. Deep learning will drive improvements in classifying normal tissue tolerance, predicting intra-treatment tumor changes, tracking accumulated dose distributions, and quantifying the tumor response to radiotherapy based on imaging. Mechanistic patient-specific computer simulations ('digital twins') could also be used to guide adaptive radiotherapy. Overall, we are entering an era where improved modeling methods will allow the use of newly available data sources to better guide radiotherapy treatments.

Prostate-Specific Membrane Antigen Positron Emission Tomography/Computed Tomography-Derived Radiomic Models in Prostate Cancer Prognostication

The clinical integration of prostate membrane specific antigen (PSMA) positron emission tomography and computed tomography (PET/CT) scans represents potential for advanced data analysis techniques in prostate cancer (PC) prognostication. Among these tools is the use of radiomics, a computer-based method of extracting and quantitatively analyzing subvisual features in medical imaging. Within this context, the present review seeks to summarize the current literature on the use of PSMA PET/CT-derived radiomics in PC risk stratification. A stepwise literature search of publications from 2017 to 2023 was performed. Of 23 articles on PSMA PET/CT-derived prostate radiomics, PC diagnosis, prediction of biopsy Gleason score (GS), prediction of adverse pathology, and treatment outcomes were the primary endpoints of 4 (17.4%), 5 (21.7%), 7 (30.4%), and 7 (30.4%) studies, respectively. In predicting PC diagnosis, PSMA PET/CT-derived models performed well, with receiver operator characteristic curve area under the curve (ROC-AUC) values of 0.85-0.925. Similarly, in the prediction of biopsy and surgical pathology results, ROC-AUC values had ranges of 0.719-0.84 and 0.84-0.95, respectively. Finally, prediction of recurrence, progression, or survival following treatment was explored in nine studies, with ROC-AUC ranging 0.698-0.90. Of the 23 studies included in this review, 2 (8.7%) included external validation. While explorations of PSMA PET/CT-derived radiomic models are immature in follow-up and experience, these results represent great potential for future investigation and exploration. Prior to consideration for clinical use, however, rigorous validation in feature reproducibility and biologic validation of radiomic signatures must be prioritized.

Computed Tomography-Based Radiomics for Long-Term Prognostication of High-Risk Localized Prostate Cancer Patients Received Whole Pelvic Radiotherapy

Given the high death rate caused by high-risk prostate cancer (PCa) (>40%) and the reliability issues associated with traditional prognostic markers, the purpose of this study is to investigate planning computed tomography (pCT)-based radiomics for the long-term prognostication of high-risk localized PCa patients who received whole pelvic radiotherapy (WPRT). This is a retrospective study with methods based on best practice procedures for radiomics research. Sixty-four patients were selected and randomly assigned to training (n = 45) and testing (n = 19) cohorts for radiomics model development with five major steps: pCT image acquisition using a Philips Big Bore CT simulator; multiple manual segmentations of clinical target volume for the prostate (CTVprostate) on the pCT images; feature extraction from the CTVprostate using PyRadiomics; feature selection for overfitting avoidance; and model development with three-fold cross-validation. The radiomics model and signature performances were evaluated based on the area under the receiver operating characteristic curve (AUC) as well as accuracy, sensitivity and specificity. This study's results show that our pCT-based radiomics model was able to predict the six-year progression-free survival of the high-risk localized PCa patients who received the WPRT with highly consistent performances (mean AUC: 0.76 (training) and 0.71 (testing)). These are comparable to findings of other similar studies including those using magnetic resonance imaging (MRI)-based radiomics. The accuracy, sensitivity and specificity of our radiomics signature that consisted of two texture features were 0.778, 0.833 and 0.556 (training) and 0.842, 0.867 and 0.750 (testing), respectively. Since CT is more readily available than MRI and is the standard-of-care modality for PCa WPRT planning, pCT-based radiomics could be used as a routine non-invasive approach to the prognostic prediction of WPRT treatment outcomes in high-risk localized PCa.

Research on texture images and radiomics in urology: a review of urological MR imaging applications

PURPOSE OF REVIEW

Tumor volume and heterogenicity are associated with diagnosis and prognosis of urological cancers, and assessed by conventional imaging. Quantitative imaging, Radiomics, using advanced mathematical analysis may contain information imperceptible to the human eye, and may identify imaging-based biomarkers, a new field of research for individualized medicine. This review summarizes the recent literature on radiomics in kidney and prostate cancers and the future perspectives.

RECENT FINDINGS

Radiomics studies have been developed and showed promising results in diagnosis, in characterization, prognosis, treatment planning and recurrence prediction in kidney tumors and prostate cancer, but its use in guiding clinical decision-making remains limited at present due to several limitations including lack of external validations in most studies, lack of prospective studies and technical standardization.

SUMMARY

Future challenges, besides developing prospective and validated studies, include automated segmentation using artificial intelligence deep learning networks and hybrid radiomics integrating clinical data, combining imaging modalities and genomic features. It is anticipated that these improvements may allow identify these noninvasive, imaging-based biomarkers, to enhance precise diagnosis, improve decision-making and guide tailored treatment.