{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T18:30:27Z","timestamp":1767205827025,"version":"build-2238731810"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2021,3,5]],"date-time":"2021-03-05T00:00:00Z","timestamp":1614902400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To develop and validate a preliminary machine learning (ML) model aiding in the selection of intracavitary (IC) versus hybrid interstitial (IS) applicators for high-dose-rate (HDR) cervical brachytherapy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>From a dataset of 233 treatments using IC or IS applicators, a set of geometric features of the structure set were extracted, including the volumes of OARs (bladder, rectum, sigmoid colon) and HR-CTV, proximity of OARs to the HR-CTV, mean and maximum lateral and vertical HR-CTV extent, and offset of the HR-CTV centre-of-mass from the applicator tandem axis. Feature selection using an ANOVA F-test and mutual information removed uninformative features from this set. Twelve classification algorithms were trained and tested over 100 iterations to determine the highest performing individual models through nested 5-fold cross-validation. Three models with the highest accuracy were combined using soft voting to form the final model. This model was trained and tested over 1,000 iterations, during which the relative importance of each feature in the applicator selection process was determined.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Feature selection indicated that the mean and maximum lateral and vertical extent, volume, and axis offset of the HR-CTV were the most informative features and were thus provided to the ML models. Relative feature importances indicated that the HR-CTV volume and mean lateral extent were most important for applicator selection. From the comparison of the individual classification algorithms, it was found that the highest performing algorithms were tree-based ensemble methods \u2013 AdaBoost Classifier (ABC), Gradient Boosting Classifier (GBC), and Random Forest Classifier (RFC). The accuracy of the individual models was compared to the voting model for 100 iterations (ABC = 91.6 \u00b1 3.1%, GBC = 90.4 \u00b1 4.1%, RFC = 89.5 \u00b1 4.0%, Voting Model = 92.2 \u00b1 1.8%) and the voting model was found to have superior accuracy. Over the final 1,000 evaluation iterations, the final voting model demonstrated a high predictive accuracy (91.5 \u00b1 0.9%) and F1 Score (90.6 \u00b1 1.1%).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The presented model demonstrates high discriminative performance, highlighting the potential for utilization in informing applicator selection prospectively following further clinical validation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2021.611437","type":"journal-article","created":{"date-parts":[[2021,3,5]],"date-time":"2021-03-05T01:17:42Z","timestamp":1614907062000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Development of a Machine Learning Model for Optimal Applicator Selection in High-Dose-Rate Cervical Brachytherapy"],"prefix":"10.3389","volume":"11","author":[{"given":"Kailyn","family":"Stenhouse","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Roumeliotis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip","family":"Ciunkiewicz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robyn","family":"Banerjee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Svetlana","family":"Yanushkevich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip","family":"McGeachy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2021,3,5]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"394","DOI":"10.3322\/caac.21492","article-title":"Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"68","author":"Bray","year":"2018","journal-title":"CA Cancer J Clin"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.canrad.2014.06.008","article-title":"Cervix cancer brachytherapy: High dose rate","volume":"18","author":"Miglierini","year":"2014","journal-title":"Cancer Radiother"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.2147\/ijwh.s46247","article-title":"Brachytherapy in the treatment of cervical cancer: a review","volume":"6","author":"Banerjee","year":"2014","journal-title":"Int J Womens Health"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2013.05.033","article-title":"Trends in the Utilization of Brachytherapy in Cervical Cancer in the United States","volume":"87","author":"Han","year":"2013","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2010.10.030","article-title":"International Brachytherapy Practice Patterns: A Survey of the Gynecologic Cancer Intergroup (GCIG)","volume":"82","author":"Viswanathan","year":"2012","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B6","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.ijrobp.2006.04.041","article-title":"The Vienna applicator for combined intracavitary and interstitial brachytherapy of cervical cancer: Clinical feasibility and preliminary results","volume":"66","author":"Dimopoulos","year":"2006","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2009.01.043","article-title":"Three-Dimensional Imaging in Gynecologic Brachytherapy: A Survey of the American Brachytherapy Society","volume":"76","author":"Viswanathan","year":"2010","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2014.07.017","article-title":"National Cancer Data Base Analysis of Radiation Therapy Consolidation Modality for Cervical Cancer: The Impact of New Technological Advancements","volume":"90","author":"Gill","year":"2014","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2008.03.032","article-title":"Image-Guided Radiotherapy for Cervix Cancer: High-Tech External Beam Therapy Versus High-Tech Brachytherapy","volume":"71","author":"Georg","year":"2008","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.brachy.2016.09.011","article-title":"Differences in outcome for cervical cancer patients treated with or without brachytherapy","volume":"16","author":"Karlsson","year":"2017","journal-title":"Brachytherapy"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2006.01.036","article-title":"The Vienna applicator for combined intracavitary and interstitial brachytherapy of cervical cancer: Design, application, treatment planning, and dosimetric results","volume":"65","author":"Kirisits","year":"2006","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2011.04.044","article-title":"Clinical Use of the Utrecht Applicator for Combined Intracavitary\/Interstitial Brachytherapy Treatment in Locally Advanced Cervical Cancer","volume":"82","author":"Nomden","year":"2012","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B13","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1016\/j.radonc.2005.11.014","article-title":"Recommendations from gynaecological (GYN) GEC ESTRO working group (II): Concepts and terms in 3D image-based treatment planning in cervix cancer brachytherapy\u20143D dose volume parameters and aspects of 3D image-based anatomy, radiation physics, radiobiology","volume":"78","author":"P\u00f6tter","year":"2006","journal-title":"Radiother Oncol"},{"key":"B14","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.brachy.2011.07.002","article-title":"American Brachytherapy Society consensus guidelines for locally advanced carcinoma of the cervix. Part II: High-dose-rate brachytherapy","volume":"11","author":"Viswanathan","year":"2012","journal-title":"Brachytherapy"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1097\/igc.0b013e31823ae3c9","article-title":"The Quality of Cervical Cancer Brachytherapy Implantation and the Impact on Local Recurrence and Disease-Free Survival in Radiation Therapy Oncology Group Prospective Trials 0116 and 0128","volume":"22","author":"Viswanathan","year":"2012","journal-title":"Int J Gynecol Cancer"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2005.04.035","article-title":"Patterns of brachytherapy practice for patients with carcinoma of the cervix (1996\u20131999): A Patterns of Care Study","volume":"63","author":"Erickson","year":"2005","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B17","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1006\/gyno.1994.1137","article-title":"Technically Accurate Intracavitary Insertions Improve Pelvic Control and Survival among Patients with Locally Advanced Carcinoma of the Uterine Cervix","volume":"53","author":"Corn","year":"1994","journal-title":"Gynecol Oncol"},{"key":"B18","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1007\/978-3-319-18305-3","volume-title":"Machine Learning in Radiation Oncology: Theory and Applications","author":"El Naqa","year":"2015"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24571-3_50","article-title":"Automatic prostate brachytherapy preplanning using joint sparse analysis","volume":"9350","author":"Nouranian","year":"2015","journal-title":"Med Image Comput Comput Assist Interv"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2018.09.003","article-title":"MRI-based automated detection of implanted low dose rate (LDR) brachytherapy seeds using quantitative susceptibility mapping (QSM) and unsupervised machine learning (ML)","volume":"129","author":"Nosrati","year":"2018","journal-title":"Radiother Oncol"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2016.11.036","article-title":"Evaluation of a Machine-Learning Algorithm for Treatment Planning in Prostate Low-Dose-Rate Brachytherapy","volume":"97","author":"Nicolae","year":"2017","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B22","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1016\/j.ijrobp.2018.03.001","article-title":"Salvage HDR Brachytherapy: Multiple Hypothesis Testing Versus Machine Learning Analysis","volume":"101","author":"Valdes","year":"2018","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1016\/j.brachy.2019.04.004","article-title":"Hrycushko B. A machine-learning-based prediction model of fistula formation after interstitial brachytherapy for locally advanced gynecological malignancies","volume":"18","author":"Tian","year":"2019","journal-title":"Brachytherapy"},{"key":"B24","doi-asserted-by":"publisher","first-page":"215003","DOI":"10.1088\/1361-6560\/ab3fcb","article-title":"Deep-learning assisted automatic digitization of interstitial needles in 3D CT image based high dose-rate brachytherapy of gynecological cancer","volume":"64","author":"Jung","year":"2019","journal-title":"Phys Med Biol"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1016\/j.brachy.2019.06.003","article-title":"Deep-learning\u2013assisted automatic digitization of applicators in 3D CT image-based high-dose-rate brachytherapy of gynecological cancer","volume":"18","author":"Jung","year":"2019","journal-title":"Brachytherapy"},{"key":"B26","doi-asserted-by":"publisher","first-page":"115013","DOI":"10.1088\/1361-6560\/ab18bf","article-title":"Intelligent inverse treatment planning via deep reinforcement learning, a proof-of-principle study in high dose-rate brachytherapy for cervical cancer","volume":"64","author":"Shen","year":"2019","journal-title":"Phys Med Biol"},{"key":"B27","first-page":"823\u20134","article-title":"Active learning for class imbalance problem. Special Interest Group in Information Retrieval","author":"Ertekin","year":"2007"},{"key":"B28","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.ctro.2018.01.001","article-title":"The EMBRACE II study: The outcome and prospect of two decades of evolution within the GEC-ESTRO GYN working group and the EMBRACE studies","volume":"9","author":"P\u00f6tter","year":"2018","journal-title":"Clin Transl Radiat Oncol"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"B30","first-page":"368","volume-title":"Classification and regression trees","author":"Breiman","year":"1984"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12967","article-title":"Machine learning algorithms for outcome prediction in (chemo)radiotherapy: An empirical comparison of classifiers","volume":"45","author":"Deist","year":"2018","journal-title":"Med Phys"},{"key":"B32","doi-asserted-by":"crossref","first-page":"745","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The Elements of Statistical Learning: Data Mining, Inference, and Prediction","author":"Hastie","year":"2009"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.5555\/1756006.1859921","article-title":"On over-fitting in model selection and subsequent selection bias in performance evaluation","volume":"11","author":"Cawley","year":"2010","journal-title":"J Mach Learn Res"},{"key":"B34","unstructured":"Scikit-Learn: Machine Learning in Python. sklearn.ensemble.VotingClassifier2020"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2016.03.020","article-title":"Image guided adaptive brachytherapy with combined intracavitary and interstitial technique improves the therapeutic ratio in locally advanced cervical cancer: analysis from the retroEMBRACE study","volume":"120","author":"Fokdal","year":"2016","journal-title":"Radiother Oncol"},{"key":"B36","doi-asserted-by":"publisher","first-page":"S21","DOI":"10.1016\/j.brachy.2016.04.010","article-title":"Image guided brachytherapy in cervical cancer: a comparison between intracavitary and combined intracavitary\/interstitial brachytherapy in regard to doses to HR CTV, OARs and late morbidity \u2013 early results from the embrace study in 999 patients","volume":"15","author":"Fortin","year":"2016","journal-title":"Brachytherapy"},{"key":"B37","doi-asserted-by":"publisher","first-page":"115013","DOI":"10.1088\/1361-6560\/ab1378","article-title":"Deformable image registration for dose mapping between external beam radiotherapy and brachytherapy images of cervical cancer","volume":"64","author":"Rigaud","year":"2019","journal-title":"Phys Med Biol"}],"updated-by":[{"DOI":"10.3389\/fonc.2021.730375","type":"corrigendum","label":"Corrigendum","source":"publisher","updated":{"date-parts":[[2021,7,6]],"date-time":"2021-07-06T00:00:00Z","timestamp":1625529600000}}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2021.611437\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,6]],"date-time":"2021-07-06T05:01:17Z","timestamp":1625547677000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2021.611437\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,5]]},"references-count":37,"alternative-id":["10.3389\/fonc.2021.611437"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2021.611437","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,5]]},"article-number":"611437"}}