Predicting Local Failure after Partial Prostate Re-Irradiation Using a Dosiomic-Based Machine Learning Model

Abstract

The aim of this study is to predict local failure after partial prostate re-irradiation for the treatment of isolated locally recurrent prostate cancer by using a machine learning classifier based on radiomic features from pre-treatment computed tomography (CT), positron-emission tomography (PET) and biological effective dose distribution (BED) of the radiotherapy plan. The analysis was conducted on a monocentric dataset of 43 patients with evidence of isolated intraprostatic recurrence of prostate cancer after primary external beam radiotherapy. All patients received partial prostate re-irradiation delivered by volumetric modulated arc therapy. The gross tumor volume (GTV) of each patient was manually contoured from planning CT, choline-PET and dose maps. An ensemble machine learning pipeline including unbalanced data correction and feature selection was trained using the radiomic and dosiomic features as input for predicting occurrence of local failure. The model performance was assessed using sensitivity, specificity, accuracy and area under receiver operating characteristic curves of the score function in 10-fold cross validation repeated 100 times. Local failure was observed in 13 patients (30%), with a median time to recurrence of 36.7 months (range = 6.1-102.4 months). A four variables ensemble machine learning model resulted in accuracy of 0.62 and AUC 0.65. According to our results, a dosiomic machine learning classifier can predict local failure after partial prostate re-irradiation.

Keywords: dosiomics; machine learning; partial prostate re-irradiation; prostate cancer; radiomics; radiotherapy.

Figure 1

The radiomics framework depicts all the steps needed to build a radiomics model. After medical image acquisition and reconstruction, the region of interest (ROI) is segmented manually, semi-automatically or fully automatically. The feature extraction step, including post-processing of the acquired image, provides numerous quantitative biomarkers managed by means of artificial intelligence to achieve a clinical decision support system.

Figure 2

Axial view of 3D relative dose distribution (%). Blue line: PTV; brown line: rectum.

Figure 3

Model building and validation scheme. A repeated 10-fold cross-validation (CV) was performed to yield accuracy and area under curve with standard deviations in order to make model comparisons.

Figure 4

Model performance as a function of the increasing number of features.

Figure 5

ROC curve of the selected EML model after the 100-times-repeated 10-fold CV.

Figure 6

Histogram of the most frequently selected variables in the neighborhood component analysis feature selection during the 100-times-repeated 10-fold CV.