Biochemical recurrence prediction after radiotherapy for prostate cancer with T2w magnetic resonance imaging radiomic features

Abstract

Background and purpose: High-risk prostate cancer patients are frequently treated with external-beam radiotherapy (EBRT). Of all patients receiving EBRT, 15-35% will experience biochemical recurrence (BCR) within five years. Magnetic resonance imaging (MRI) is commonly acquired as part of the diagnostic procedure and imaging-derived features have shown promise in tumour characterisation and biochemical recurrence prediction. We investigated the value of imaging features extracted from pre-treatment T2w anatomical MRI to predict five year biochemical recurrence in high-risk patients treated with EBRT. Materials and methods: In a cohort of 120 high-risk patients, imaging features were extracted from the wholeprostate and a margin surrounding it. Intensity, shape and textural features were extracted from the original and filtered T2w-MRI scans. The minimum-redundancy maximum-relevance algorithm was used for feature selection. Random forest and logistic regression classifiers were used in our experiments. The performance of a logistic regression model using the patient's clinical features was also investigated. To assess the prediction accuracy we used stratified 10-fold cross validation and receiver operating characteristic analysis, quantified by the area under the curve (AUC). Results: A logistic regression model built using whole-prostate imaging features obtained an AUC of 0.63 in the prediction of BCR, outperforming a model solely based on clinical variables (AUC = 0.51). Combining imaging and clinical features did not outperform the accuracy of imaging alone. Conclusions: These results illustrate the potential of imaging features alone to distinguish patients with an increased risk of recurrence, even in a clinically homogeneous cohort.

Evaluation of a multiparametric MRI radiomic-based approach for stratification of equivocal PI-RADS 3 and upgraded PI-RADS 4 prostatic lesions

“…Another aspect to highlight is that also delineations of prostatic lesions are prone to inter-observer variability. In fact, it should be considered that we delineated only the prostatic lesion for feature extraction, and it is well-recognized that small volumes might lead to uncertainties in feature extraction [60][61][62][63] .…”

Automatic evaluation of contours in radiotherapy planning utilising conformity indices and machine learning

“…To mitigate this effect, the dataset should be applied to more than one model to establish which is the most appropriate [18] . The models considered were Decision Tree, Logistic Regression, Support Vector Machine (SVM), K-Nearest Neighbour (KNN) and Ensemble (summarised in Table S1 ), as these have been used in previous radiation oncology related studies [19] , [20] , [21] .…”

Advanced Imaging of Biochemical Recurrent Prostate Cancer With PET, MRI, and Radiomics

“… Graphical schema of the radiomics process that involves lesion identification, drawing regions of interest, image preprocessing followed by radiomic feature extraction and classification that provides the imaging biomarker for predicting biochemical recurrence. Reused from Fernandes et al ( 28 ) under the Creative Commons License. …”