Machine learning-based radiomic models to predict intensity-modulated radiation therapy response, Gleason score and stage in prostate cancer
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.
KeywordsRadiomics Prostate cancer MRI IMRT Prediction
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
All procedures performed were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards.
Informed consent was obtained from all participants included in the study.
- 9.X-k Niu, Z-f Chen, Chen L, Li J, Peng T, Li X (2018) Clinical application of biparametric MRI texture analysis for detection and evaluation of high-grade prostate cancer in zone-specific regions. Am J Roentgenol 210(3):56–549Google Scholar
- 15.Mardor Y, Roth Y, Lidar Z, Jonas T, Pfeffer R, Maier SE et al (2001) Monitoring response to convection-enhanced taxol delivery in brain tumor patients using diffusion-weighted magnetic resonance imaging. Cancer Res 61(13):3–4971Google Scholar
- 23.Zhou M, Scott J, Chaudhury B, Hall L, Goldgof D, Yeom K et al (2018) Radiomics in brain tumor: image assessment, quantitative feature descriptors, and machine-learning approaches. Am J Neuroradiol 39(2):16–208Google Scholar
- 26.Wahba MH, Morad MM (2015) The role of diffusion-weighted MRI: in assessment of response to radiotherapy for prostate cancer. Egypt J Radiol Nucl Med 46(1):8–183Google Scholar
- 28.Khalil RF, Abdelhamid AEM, Darwish AMA, Hassan HHM (2017) Diffusion weighted imaging in early prediction of neoadjuvant chemotherapy response in breast cancer. Egypt J Radiol Nucl Med 48(2):35–529Google Scholar
- 31.Liu Z, Zhang X-Y, Shi Y-J, Wang L, Zhu H-T, Tang Z-C, et al. Radiomics analysis for evaluation of pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer. Clin Cancer Res. 2017:clincanres. 1038.2017Google Scholar
- 36.Cunliffe A, Armato SG III, Castillo R, Pham N, Guerrero T, Al-Hallaq HA (2015) Lung texture in serial thoracic computed tomography scans: correlation of radiomics-based features with radiation therapy dose and radiation pneumonitis development. Int J Radiat Oncol Biol Phys 91(5):56–1048CrossRefGoogle Scholar
- 44.Wibmer A, Hricak H, Gondo T, Matsumoto K, Veeraraghavan H, Fehr D et al (2015) Haralick texture analysis of prostate MRI: utility for differentiating non-cancerous prostate from prostate cancer and differentiating prostate cancers with different Gleason scores. Eur Radiol 25(10):50–2840CrossRefGoogle Scholar
- 46.Shiri I, Abdollahi H, Shaysteh S, Mahdavi SR (2017) Test-retest reproducibility and robustness analysis of recurrent glioblastoma MRI radiomics texture features. Iran J Radiol. https://doi.org/10.5812/iranjradiol.48035
- 47.Saeedi E, Dejkam A, Beigi J, Rastegar S, Yousei Z, Mehdipour A et al (2018) Radiomic feature robustness and reproducibility in quantitative bone radiography: a study on radiologic parameter changes. J Clin Densitom. https://doi.org/10.1016/j.jocd.2018.06.004