Machine learning-based radiomic models to predict intensity-modulated radiation therapy response, Gleason score and stage in prostate cancer

• DOI: 10.1007/s11547-018-0966-4
• Publication Date: 2019-01-02T23:24:37Z
• Authors: Hamid Abdollahi; Bahram Mofid; Isaac Shiri; Abolfazl Razzaghd...; Afshin Saadipoor; Arash Mahdavi; Hassan Maleki Gal...; Seied Rabi Mahdavi
• Keywords: Aged, 80 and over; Male; Prostatic Neoplasms; Middle Aged; Magnetic Resonance Imaging; 3. Good health; Machine Learning; 03 medical and health sciences; Treatment Outcome; 0302 clinical medicine; Predictive Value of Tests; Image Interpretation, Computer-Assisted; Humans; Prospective Studies; Radiotherapy, Intensity-Modulated; Neoplasm Grading; Aged; Neoplasm Staging

To develop different radiomic models based on the magnetic resonance imaging (MRI) radiomic features and machine learning methods to predict early intensity-modulated radiation therapy (IMRT) response, Gleason scores (GS) and prostate cancer (Pca) stages.Thirty-three Pca patients were included. All patients underwent pre- and post-IMRT T2-weighted (T2 W) and apparent diffusing coefficient (ADC) MRI. IMRT response was calculated in terms of changes in the ADC value, and patients were divided as responders and non-responders. A wide range of radiomic features from different feature sets were extracted from all T2 W and ADC images. Univariate radiomic analysis was performed to find highly correlated radiomic features with IMRT response, and a paired t test was used to find significant features between responders and non-responders. To find high predictive radiomic models, tenfold cross-validation as the criterion for feature selection and classification was applied on the pre-, post- and delta IMRT radiomic features, and area under the curve (AUC) of receiver operating characteristics was calculated as model performance value.Of 33 patients, 15 patients (45%) were found as responders. Univariate analysis showed 20 highly correlated radiomic features with IMRT response (20 ADC and 20 T2). Two and fifteen T2 and ADC radiomic features were found as significant (P-value ≤ 0.05) features between responders and non-responders, respectively. Several cross-combined predictive radiomic models were obtained, and post-T2 radiomic models were found as high predictive models (AUC 0.632) followed by pre-ADC (AUC 0.626) and pre-T2 (AUC 0.61). For GS prediction, T2 W radiomic models were found as more predictive (mean AUC 0.739) rather than ADC models (mean AUC 0.70), while for stage prediction, ADC models had higher prediction performance (mean AUC 0.675).Radiomic models developed by MR image features and machine learning approaches are noninvasive and easy methods for personalized prostate cancer diagnosis and therapy.