IJBTT

Prostate Cancer Detection using Radiomics-based Feature Analysis with ML Algorithms and MR Images

Prostate Cancer Detection using Radiomics-based Feature Analysis with ML Algorithms and MR Images
	© 2022 by IJETT Journal
	Volume-70 Issue-12
	Year of Publication : 2022
	Author : M. N. Rajesh, B. S. Chandrasekar, S. Shivakumar Swamy
	DOI : 10.14445/22315381/IJETT-V70I12P206

How to Cite?

M. N. Rajesh, B. S. Chandrasekar, S. Shivakumar Swamy, "Prostate Cancer Detection using Radiomics-based Feature Analysis with ML Algorithms and MR Images," International Journal of Engineering Trends and Technology, vol. 70, no. 12, pp. 42-58, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I12P206

Abstract
The study is aimed to understand and predict prostate lesions identification and classifications on magnetic resonance images (MRI) of the prostate using Radiomics based texture features analysis while applying Machine Learning (ML) algorithms. This study includes retrospective MR Images of patients with Prostate Cancer (PCa) from HealthCare Global (HCG), totalling 76 patients. From 207 prostate MRI images, 109 texture features were extracted using the python PyRadiomics library. Three sampling methods and various ML feature classification techniques are utilised to balance the dataset to develop the best diagnostic models for assessing these models' accuracy. The discriminative capability of all the models was evaluated by receiver operating characteristics (ROC) analysis. Eight different texture feature-based predictive models are developed by running the cross combination of all the dataset balancing and classification methods to identify and classify PCa malignancy from benign. Based on the test group's results, the majority of the models performed better with a larger area under the curve (AUC) (>0.80) and higher accuracy (>0.80). Support vector machine (SVM) classifier with AUC of 0.9744, 0.9759 accuracy and extreme gradient boosting (XGB) classifier with AUC of 0.963, accuracy with 0.9639 were the best model within the eight models, followed by decision trees (DT), light gradient boosting machine (LGBM) and random forest (RF) models. Extracting texture parameters from MRI images and combining the Radiomics approach with ML models can classify prostate lesions effectively.

Keywords
Prostate cancer, ROI Delineation, Feature extraction, Feature analysis, Machine learning.

References
[1] Hyuna Sung et al., "Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries," CA: A Cancer Journal for Clinicians, vol. 71, no. 3, pp. 209–249, 2021. Crossref, http://doi.org/10.3322/caac.21660
[2] Freddie Bray et al., "Global Cancer Statistics 2018: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries," CA: A Cancer Journal for Clinicians, vol. 68, no. 6, pp. 394-424, 2018. Crossref, http://doi.org/10.3322/caac.21492
[3] Ahmad Chaddad et al., "Magnetic Resonance Imaging-Based Radiomic Models of Prostate Cancer: A Narrative Review," Cancers, vol. 13, no. 3, p. 552, 2021. Crossref, http://doi.org/10.3390/cancers13030552
[4] Giuseppe Cutaia et al., “Radiomics and Prostate MRI: Current Role and Future Applications,” Journal of Imaging, vol. 7, no. 2, p. 34, 2021. Crossref, http://doi.org/10.3390/jimaging7020034
[5] Femke C.R. Staal et al., "Radiomics for the Prediction of Treatment Outcome and Survival in Patients with Colorectal Cancer: A Systematic Review," Clinical Colorectal Cancer, vol. 20, no. 1, pp. 52-71, 2021. Crossref, http://doi.org/10.1016/j.clcc.2020.11.001
[6] Parnian Afshary et al., "From Hand-Crafted to Deep Learning-based Cancer Radiomics: Challenges and Opportunities," IEEE Signal Processing Magazine, vol. 36, no. 4, pp. 132-160, 2019. Crossref, http://doi.org/10.1109/MSP.2019.2900993
[7] Leandro Donisi et al., "A Combined Radiomics and Machine Learning Approach to Distinguish Clinically Significant Prostate Lesions on a Publicly Available MRI Dataset," Journal of Imaging, vol. 7, no. 10, p. 215, 2021. Crossref, https://doi.org/10.3390/jimaging7100215
[8] Simon Bernatz et al., "Comparison of Machine Learning Algorithms to Predict Clinically Significant Prostate Cancer of the Peripheral Zone with Multiparametric MRI Using Clinical Assessment Categories and Radiomic Features," European Radiology, vol. 30, no. 12, pp. 6757– 6769, 2020. Crossref, https://doi.org/10.1007/s00330-020-07064-5
[9] Jing Wang et al., "Machine Learning-Based Analysis of MR Radiomics Can Help to Improve the Diagnostic Performance of PI-RADS V2 in Clinically Relevant Prostate Cancer," European Radiology, vol. 27, no. 10, pp. 4082–4090, 2017. Crossref, https://doi.org/10.1007/s00330- 017-4800-5
[10] Stefanie J. Hectors et al., "Magnetic Resonance Imaging Radiomics-Based Machine Learning Prediction of Clinically Significant Prostate Cancer in Equivocal PI-RADS 3 Lesions," Journal of Magnetic Resonance Imaging, vol. 54, no. 5, pp. 1466-1473, 2021. Crossref, https://doi.org/10.1002/jmri.27692
[11] Xiangde Mina et al., "Multi-Parametric MRI Based Radiomics Signature for Discriminating Between Clinically Significant and Insignificant Prostate Cancer: Cross-Validation of a Machine Learning Method," European Journal of Radiology, vol. 115, pp. 16-21, 2019. Crossref, https://doi.org/10.1016/j.ejrad.2019.03.010
[12] Bino Varghese et al., "Objective Risk Stratification of Prostate Cancer Using Machine Learning and Radiomics Applied to Multiparametric Magnetic Resonance Images," Scientific Reports, vol. 9, pp. 1-10, 2019. Crossref, https://doi.org/10.1038/s41598-018-38381-x
[13] B. Liu et al., "Prediction of Prostate Cancer Aggressiveness with a Combination of Radiomics and Machine Learning-Based Analysis of Dynamic Contrast-Enhanced MRI," Clinical Radiology, vol. 74, no. 11, pp. 896.e1-e896.e8, 2019. Crossref, https://doi.org/10.1016/j.crad.2019.07.011
[14] Valentina Brancato et al., “Evaluation of a Multiparametric MRI Radiomic‑Based Approach for Stratification of Equivocal PI‑RADS 3 and Upgraded PI‑RADS 4 Prostatic Lesions,” Scientific Reports, vol. 11, no. 643, pp. 1-10, 2021. Crossref, https://doi.org/10.1038/s41598-020- 80749-5
[15] Anjana Gosain, and Saanchi Sardana, "Handling Class Imbalance Problem using Oversampling Techniques: A Review," International Conference on Advances in Computing, Communications and Informatics, pp. 79-85, 2017. Crossref, https://doi.org/10.1109/ICACCI.2017.8125820
[16] Jingmei Liu, Yuanbo Gao, and Fengjie Hu, "A Fast Network Intrusion Detection System Using Adaptive Synthetic Oversampling and Light GBM," Computers & Security, vol. 106, no. 102289, 2021. Crossref, https://doi.org/10.1016/j.cose.2021.102289
[17] V.P. Amadi, N.D Nwiabu, and V. I. E. Anireh, "Case-Based Reasoning System for the Diagnosis and Treatment of Breast, Cervical and Prostate Cancer," SSRG International Journal of Computer Science and Engineering, vol. 8, no. 8, pp. 13-20, 2021. Crossref, https://doi.org/10.14445/23488387/IJCSE-V8I8P103
[18] Hui Ding et al., "Identification of Bacteriophage Virion Proteins with the ANOVA Feature Selection and Analysis," Molecular Bio Systems, vol. 10, no. 8, pp. 2229-2235, 2014. Crossref, https://doi.org/10.1039/c4mb00316k
[19] Ke Yana, and David Zhang, "Feature Selection and Analysis on Correlated Gas Sensor Data with Recursive Feature Elimination," Sensors and Actuators B: Chemical, vol. 212, pp. 353–363, 2015. Crossref, https://doi.org/10.1016/j.snb.2015.02.025
[20] R. Surendiran et al., "Exploring the Cervical Cancer Prediction by Machine Learning and Deep Learning with Artificial Intelligence Approaches," International Journal of Engineering Trends and Technology, vol. 70, no. 7, pp. 94-107, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I7P211
[21] Navoneel Chakrabarty et al., "Flight Arrival Delay Prediction Using Gradient Boosting Classifier," Emerging Technologies in Data Mining and Information Security, pp. 651–659, 2018. Crossref, https://doi.org/10.1007/978-981-13-1498-8_57
[22] C Narmatha, and Prasad M Surendra, "A Review on Prostate Cancer Detection using Deep Learning Techniques," Journal of Computational Science and Intelligent Technologies, vol. 1, no. 2, pp. 26-33, 2020. Crossref, https://doi.org/10.53409/mnaa.jcsit20201204
[23] S. Manimurugan, "IoT-Fog-Cloud model for Anomaly Detection Using Improved Naive Bayes and Principal Component Analysis," Journal of Ambient Intelligence and Humanized Computing, pp. 1-10, 2021. Crossref, https://doi.org/10.1007/s12652-020-02723-3
[24] S. Rinesh et al., "Investigations on Brain Tumor Classification Using Hybrid Machine Learning Algorithms," Journal of Healthcare Engineering, vol. 2022, pp. 1-9, 2022. Crossref, https://doi.org/10.1155/2022/2761847
[25] T. Rajendran, K.P. Sridhar, and S. Deepa, "Performance Analysis of Fuzzy Multilayer Support Vector Machine for Epileptic Seizure Disorder Classification Using Auto Regression Features," The open Biomedical Engineering Journal, vol. 13, pp. 103-113, 2019. Crossref, https://doi.org/10.2174/1874120701913010103
[26] Jorge R. Vergara, and Pablo A. Estévez, "A Review of Feature Selection Methods Based on Mutual Information," Neural Computing and Applications, vol. 24, pp. 175–186, 2014. Crossref, https://doi.org/10.1007/s00521-013-1368-0