|
Predicting prostate cancer radiotherapy complications: An integrated approach using radiomics, dosiomics, and machine learning
|
E. Sadati   , B. Hashemi , S.R. Mahdavi , A. Nikoufar , H. Abdollahi |
| Department of Medical Physics, Faculty of Medical Sciences, Tarbiat Modares University, Tehran, Iran , bhashemi@modares.ac.ir |
|
|
Abstract: (256 Views) |
Background: We aimed to develop a robust prognostic model for assessing the risk of complications associated with radiotherapy in prostate cancer patients using radiomics and dosiomics feature and machine learning. Materials and Methods: A cohort of 60 patients undergoing pelvic radiation therapy was analyzed. The patients’ radiomics and dosiomics features were extracted from segmented bladder and rectum regions in CT images, as well as 3D dose distribution data, respectively. Classifier algorithms, such as eXtreme Gradient Boosting (XGBoost), Decision Tree (DT), Support Vector Machines (SVM), K-Nearest Neighbor (KNN), Logistic Regression (LR), Random Forest (RF), and Multilayer Perceptron (MLP) were used for prediction modeling. A 5-fold cross-validation method was used to evaluate the predictive classification of patients with and without proctitis and cystitis. The area under the receiver operating characteristic curve (AUC) was used for comparing models’ performance, as well assessing their specificity and accuracy metrics. Results: Various combinations of feature selection and classifier algorithms evaluated on both training and test datasets revealed that for bladder toxicity, the Relief+KNN dosiomics model, Boruta+SVM radiomics model, and the combined radiomics and dosiomics model with ANOVA+XGBoost show the highest AUCs of 0.76, 0.68, and 0.67, respectively. Regarding the rectal toxicity, the best-performing models were Boruta+KNN for dosiomics (AUC 0.83), ANOVA+RF for radiomics (AUC 0.72), and ANOVA+XGBoost for the combined radiomics and dosiomics (AUC 0.71). Conclusion: Our study demonstrated the effectiveness of diverse algorithms leveraging quantitative features extracted from CT imaging and 3D dose distribution data in predicting post-radiotherapy complications in prostate cancer patients. |
|
| Keywords: Prostate cancer, radiotherapy, radiomics, dosiomics, machine-learning. |
|
|
Full-Text [PDF 800 kb]
(59 Downloads)
|
|
Type of Study: Original Research |
Subject:
Radiation Biology
|
|
|
|
|
|
|
| References |
1. 1. Liang B, Yan H, Tian Y, et al. (2019) Dosiomics: extracting 3D spatial features from dose distribution to predict incidence of radiation pneumonitis. Frontiers in Oncology, 9: 269. [ DOI:10.3389/fonc.2019.00269] 2. Murakami Y, Soyano T, Kozuka T, et al. (2022) Dose-based radiomic analysis (dosiomics) for intensity modulated radiation therapy in patients with prostate cancer: correlation between planned dose distribution and biochemical failure. Int J Radiat Oncol Biol Phys, 112(1): 247-59. [ DOI:10.1016/j.ijrobp.2021.07.1714] 3. Rossi L, Bijman R, Schillemans W, et al. (2018) Texture analysis of 3D dose distributions for predictive modelling of toxicity rates in radiotherapy. Radiotherapy and Oncology, 129(3): 548-53. [ DOI:10.1016/j.radonc.2018.07.027] 4. Wu A, Li Y, Qi M, et al. (2020) Dosiomics improves prediction of locoregional recurrence for intensity modulated radiotherapy treated head and neck cancer cases. Oral Oncology, 104: 104625. [ DOI:10.1016/j.oraloncology.2020.104625] 5. Huang Y, Feng A, Lin Y, et al. (2022) Radiation pneumonitis prediction after stereotactic body radiation therapy based on 3D dose distribution: dosiomics and/or deep learning-based radiomics features. Radiation Oncology, 17(1): 188. [ DOI:10.1186/s13014-022-02154-8] 6. Shevach J, Weiner A, Morgans AK (2019) Quality of life-focused decision-making for prostate cancer. Current Urology Reports, 20: 1-7. [ DOI:10.1007/s11934-019-0924-2] 7. Leger S, Zwanenburg A, Pilz K, et al. (2017) A comparative study of machine learning methods for time-to-event survival data for radiomics risk modelling. Scientific Reports, 7(1): 13206. [ DOI:10.1038/s41598-017-13448-3] 8. Chan MF, Witztum A, Valdes G (2020) Integration of AI and machine learning in radiotherapy QA. Frontiers in Artificial Intelligence, 3: 577620. [ DOI:10.3389/frai.2020.577620] 9. Thor M, Olsson C, Oh JH, et al. (2016) Urinary bladder dose-response relationships for patient-reported genitourinary morbidity domains following prostate cancer radiotherapy. Radiotherapy and Oncology, 119(1): 117-22. [ DOI:10.1016/j.radonc.2016.01.013] 10. Viswanathan AN, Yorke ED, Marks LB, et al. (2010) Radiation dose-volume effects of the urinary bladder. Int J Radiat Oncol Biol Phys, 76(3): S116-S22. [ DOI:10.1016/j.ijrobp.2009.02.090] 11. Falahatpour Z, Geramifar P, Mahdavi SR, et al. (2022) Potential advantages of FDG‐PET radiomic feature map for target volume delineation in lung cancer radiotherapy. Journal of Applied Clinical Medical Physics, 23(9): e13696. [ DOI:10.1002/acm2.13696] 12. Fahrig A, Koch T, Lenhart M, et al. (2018) Lethal outcome after pelvic salvage radiotherapy in a patient with prostate cancer due to increased radiosensitivity. Strahlentherapie und Onkologie, 194(1): 60-6. [ DOI:10.1007/s00066-017-1207-9] 13. El Naqa I, Kerns SL, Coates J, et al. (2017) Radiogenomics and radiotherapy response modeling. Physics in Medicine & Biology, 62(16): R179. [ DOI:10.1088/1361-6560/aa7c55] 14. Parker C, Castro E, Fizazi K, et al. (2020) Prostate cancer: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up. Annals of Oncology, 31(9): 1119-34. [ DOI:10.1016/j.annonc.2020.06.011] 15. Gibson E, Bauman GS, Romagnoli C, et al. (2016) Toward prostate cancer contouring guidelines on magnetic resonance imaging: dominant lesion gross and clinical target volume coverage via accurate histology fusion. Int J Radiat Oncol Biol Phys, 96(1): 188-96. [ DOI:10.1016/j.ijrobp.2016.04.018] 16. Van Griethuysen JJ, Fedorov A, Parmar C, et al. (2017) Computational radiomics system to decode the radiographic phenotype. Cancer Research, 77(21): e104-e7. [ DOI:10.1158/0008-5472.CAN-17-0339] 17. Zhang X, Zhang Y, Zhang G, et al. (2022) Deep learning with radiomics for disease diagnosis and treatment: challenges and potential. Frontiers in Oncology, 12: 773840. [ DOI:10.3389/fonc.2022.773840] 18. Limkin EJ, Sun R, Dercle L, et al. (2017) Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology. Annals of Oncology, 28(6): 1191-206. [ DOI:10.1093/annonc/mdx034] 19. Bugata P and Drotar P (2020) On some aspects of minimum redundancy maximum relevance feature selection. Science China Information Sciences, 63(1): 112103. [ DOI:10.1007/s11432-019-2633-y] 20. Radovic M, Ghalwash M, Filipovic N, Obradovic Z (2017) Minimum redundancy maximum relevance feature selection approach for temporal gene expression data. BMC Bioinformatics, 18: 1-14. [ DOI:10.1186/s12859-016-1423-9] 21. Abdulsalam SO, Mohammed AA, Ajao JF, et al. (2020) Performance evaluation of ANOVA and RFE algorithms for classifying microarray dataset using SVM. In: Information Systems: 17th European, Mediterranean, and Middle Eastern Conference, EMCIS 2020, Dubai, United Arab Emirates, p. 480-92. Springer. [ DOI:10.1007/978-3-030-63396-7_32] 22. Way TW, Sahiner B, Hadjiiski LM, Chan HP (2010) Effect of finite sample size on feature selection and classification: a simulation study. Medical Physics, 37(2): 907-20. [ DOI:10.1118/1.3284974] 23. Hsu WC, Liu CC, Chang F, Chen SS (2013) Selecting genes for cancer classification using SVM: an adaptive multiple features scheme. International Journal of Intelligent Systems, 28(12): 1196-213. [ DOI:10.1002/int.21625] 24. Wainer J and Cawley G (2021) Nested cross-validation when selecting classifiers is overzealous for most practical applications. Expert Systems with Applications, 182: 115222. [ DOI:10.1016/j.eswa.2021.115222] 25. Van Dijk LV, Brouwer CL, Van der Laan HP, et al. (2017) Geometric image biomarker changes of the parotid gland are associated with late xerostomia. Int J Radiat Oncol Biol Phys, 99(5): 1101-10. [ DOI:10.1016/j.ijrobp.2017.08.003] 26. Kraus KM, Oreshko M, Bernhardt D, et al. (2023) Dosiomics and radiomics to predict pneumonitis after thoracic stereotactic body radiotherapy and immune checkpoint inhibition. Frontiers in Oncology, 13: 1124592. [ DOI:10.3389/fonc.2023.1124592] 27. Yang Q, Sun J, Guo Y, et al. (2022) Radiomics Features on Computed Tomography Combined With Clinical-Radiological Factors Predicting Progressive Hemorrhage of Cerebral Contusion. Frontiers in Neurology, 13: 839784. [ DOI:10.3389/fneur.2022.839784] 28. Song J, Yin Y, Wang H, et al. (2020) A review of original articles published in the emerging field of radiomics. European Journal of Radiology, 127: 108991. [ DOI:10.1016/j.ejrad.2020.108991] 29. Bourbonne V, Da-Ano R, Jaouen V, et al. (2021) Radiomics analysis of 3D dose distributions to predict toxicity of radiotherapy for lung cancer. Radiotherapy and Oncology, 155: 144-50. [ DOI:10.1016/j.radonc.2020.10.040] 30. Bradshaw TJ, Boellaard R, Dutta J, et al. (2022) Nuclear medicine and artificial intelligence: best practices for algorithm development. Journal of Nuclear Medicine, 63(4): 500-10. [ DOI:10.2967/jnumed.121.262567] 31. Fan Z, Sun Z, Fang S, et al. (2021) Preoperative Radiomics Analysis of 1p/19q Status in WHO Grade II Gliomas. Frontiers in Oncology, 11: 616740. [ DOI:10.3389/fonc.2021.616740] 32. Coates J and El Naqa I (2016) Outcome modeling techniques for prostate cancer radiotherapy: Data, models, and validation. Physica Medica, 32(3): 512-20. [ DOI:10.1016/j.ejmp.2016.02.014] 33. Mostafaei S, Abdollahi H, Kazempour Dehkordi S, et al. (2020) CT imaging markers to improve radiation toxicity prediction in prostate cancer radiotherapy by stacking regression algorithm. La Radiologia Medica, 125: 87-97. [ DOI:10.1007/s11547-019-01082-0] 34. Saeedi E, Dezhkam A, Beigi J, et al. (2019) Radiomic feature robustness and reproducibility in quantitative bone radiography: a study on radiologic parameter changes. Journal of Clinical Densitometry, 22(2): 203-13. [ DOI:10.1016/j.jocd.2018.06.004] |
|
| Send email to the article author |
|
|
|
| Add your comments about this article |
|
|
|
|
Sadati E, Hashemi B, Mahdavi S, Nikoufar A, Abdollahi H. Predicting prostate cancer radiotherapy complications: An integrated approach using radiomics, dosiomics, and machine learning. Int J Radiat Res 2025; 23 (1) :239-244 URL: http://ijrr.com/article-1-6067-en.html
|
