Machine learning based models of radiotherapy-induced skin induration for breast cancer patients
dc.contributor.author | Cicchetti, A. | |
dc.contributor.author | La Rocca, E. | |
dc.contributor.author | De Santis, M. C. | |
dc.contributor.author | Seibold, P. | |
dc.contributor.author | Azria, D. | |
dc.contributor.author | De Ruysscher, D. | |
dc.contributor.author | Valdagni, R. | |
dc.contributor.author | Dunning, A. M. | |
dc.contributor.author | Elliot, R. | |
dc.contributor.author | Gutierrez-Enriquez, S. | |
dc.contributor.author | Lambrecht, M. | |
dc.contributor.author | Sperk, E. | |
dc.contributor.author | Rancati, T. | |
dc.contributor.author | Rattay, T. | |
dc.contributor.author | Rosenstein, B. | |
dc.contributor.author | Talbot, C. | |
dc.contributor.author | Vega, A. | |
dc.contributor.author | Veldeman, L. | |
dc.contributor.author | Webb, A. | |
dc.contributor.author | Chang-Claude, J. | |
dc.contributor.author | West, Catharine M L | |
dc.date.accessioned | 2022-08-17T09:45:45Z | |
dc.date.available | 2022-08-17T09:45:45Z | |
dc.date.issued | 2022 | en |
dc.identifier.citation | Cicchetti A, La Rocca E, De Santis MC, Seibold P, Azria D, De Ruysscher D, et al. Machine learning based models of radiotherapy-induced skin induration for breast cancer patients. Radiotherapy and Oncology. 2022 May;170:S720-S1. PubMed PMID: WOS:000806764200348. | en |
dc.identifier.uri | http://hdl.handle.net/10541/625465 | |
dc.description.abstract | Purpose or Objective To use data from an international prospective cohort study of breast cancer patients (pts) to predict the risk of skin induration (SI) after radiotherapy (RT) using a machine learning algorithm that includes dosimetric/clinical/genetic factors. Materials and Methods Pts were treated after breast conserving surgery with conventional/moderate or ultra hypo-fractionated RT with or without a tumour bed boost based on clinical and pathological factors. Pts were enrolled in 7 countries in Europe/US; each centre followed local clinical practice, but the collection of data and genotyping was standardised and centralised. Our endpoint was late grade 1+ (G1+) SI 2 years after RT completion. Inclusion criteria were: no SI at baseline and availability of complete dosimetric and genetic data. For every pt, skin was defined as a 5-mm inner isotropic expansion from the outer body. To select a relevant portion of the skin DVH, we extracted the higher dose tail using different volume cutoffs (i.e. 25/50/100/150/200 cc volumes corresponding to 5x5-20x20cm2 areas). We corrected sub-DHVs for fractionation using two possible a/b values from the literature (1.8 Gy, Bentzen 1988 & Raza 2012; 3.6 Gy, Jones 2006 & Budach 2015). We calculated Equivalent Uniform Doses (EUDs) from corrected sub-DVHs, with n spanning from 1 to 0.05. We also considered the minimum dose of the selected DVH tail as an additional dose parameter (Dmin). Toxicity models were built using feed-forward neural networks (FNNs, 10 neurons and 1 hidden layer) following a wrapper method for feature selection. We used separate datasets for input: clinical/treatment/genetic features were constant, while the dosimetric factors (EUDs and Dmin) coming from sub-DVHs varied with volume cutoff and a/b .Results The 647 pts included in the analysis had a G1+ SI rate at 2 years of 29.4%. 281 variables were considered: 127 published SNPs (GWAS literature), 40 clinical factors, 93 treatment factors and 21 dosimetric variables (for each volume and a/b). For volume thresholds <200cc, no dosimetric feature was selected by the wrapper method. Therefore, we derived a predictive model (16 features, no dosimetric variable) for use before RT planning (Model 1). At sub-DVH_200cc, for a/b=3.6Gy only Dmin was selected (Model 2) as dosimetric variable, while for a/b=1.8Gy, EUD (n=0.5) and Dmin entered the FNN (Model 3). Conclusion A pre-planning SI model was derived that included information on genetics (6 SNPs), treatment (6 RT, 1 oncology) and clinical factors. Largest volume (200cc) sub-DVH allowed selection of dosimetric features, particularly with a/b=1.8Gy and EUD with n=0.5. Following validation, the model could be used to personalise use of new RT schedules, such as ultrahigh hypofractionation, to minimise risk of Sl. | en |
dc.language.iso | en | en |
dc.title | Machine learning based models of radiotherapy-induced skin induration for breast cancer patients | en |
dc.type | Meetings and Proceedings | en |
dc.contributor.department | Fondazione IRCCS Istituto Nazionale dei Tumori di Milano, Prostate Cancer Program, Milan, Italy | en |
dc.identifier.journal | Radiotherapy and Oncology | en |
dc.description.note | en] |