Prediction of skin dose in low‐kV intraoperative radiotherapy using machine learning models trained on results of in vivo dosimetry

Abstract

Purpose The purpose of this study was to implement a machine learning model to predict skin dose from targeted intraoperative (TARGIT) treatment resulting in timely adoption of strategies to limit excessive skin dose. Methods A total of 283 patients affected by invasive breast carcinoma underwent TARGIT with a prescribed dose of 6 Gy at 1 cm, after lumpectomy. Radiochromic films were used to measure the dose to the skin for each patient. Univariate statistical analysis was performed to identify correlation of physical and patient variables with measured dose. After feature selection of predictors of in vivo skin dose, machine learning models stepwise linear regression (SLR), support vector regression (SVR), ensemble with bagging or boosting, and feed forward neural networks were trained on results of in vivo dosimetry to derive models to predict skin dose. Models were evaluated by tenfold cross validation and ranked according to root mean square error (RMSE) and adjusted correlation coefficient of true vs predicted values (adj‐R2). Results The predictors correlated with in vivo dosimetry were the distance of skin from source, depth‐dose in water at depth of the applicator in the breast, use of a replacement source, and irradiation time. The best performing model was SVR, which scored RMSE and adj‐R2, equal to 0.746 [95% confidence intervals (CI), 95% CI 0.737,0.756] and 0.481 (95% CI 0.468,0.494), respectively, on the tenfold cross validation. Conclusion The model trained on results of in vivo dosimetry can be used to predict skin dose during setup of patient for TARGIT and this allows for timely adoption of strategies to prevent of excessive skin dose.

Artificial Intelligence and the Medical Physicist: Welcome to the Machine

“…The dose distribution from radiation therapy treatment can be predicted by DL in order to speed up the optimization [82] or determine the best achievable dose distribution from the patient image [83]. ML was applied to predict dose in brachytherapy [84] and in vivo measured dose in intraoperative radiotherapy [85].…”

“…The test plan could consist, for example, of applying AI to a set of well-known clinical cases, for which ground truth data are available. Comparison of different ML methods on the same dataset is useful and can show which ML algorithms have the best performance and which are more prone to overfitting data for the task at hand [85,144]. A technique called adversarial ML, where attempts to deceive models are carried out with a number of crafted configurations of data, e.g., by adding noise to images, can be used for quality assessment of many classes of ML and DL algorithms [145,146].…”

Artificial Intelligence in Digital Pathology: What Is the Future? Part 1: From the Digital Slide Onwards

“…This is a too drastic a simplification of the complex nature of the diagnosis in this field. However, today, this is really not an issue; indeed, discrete variables (e.g., 1, 2, 3, 4) can be managed by machine learning, and there are also available methods based on regression machine learning for continuous variables, as reported in [ 29 ], for example.…”

Gold-nanoparticle-enriched breast tissue in breast cancer treatment using the INTRABEAM® system: a Monte Carlo study

“…91, 5.83, 3.96, and 2.14 Gy for 6-10, 10-15, 15-20, and 20-30 mm ASD values, respectively (Baziar et al 2018). Although the threshold dose for radiation-induced skin effects in IORT is 2 Gy, a radiation dose of 6 Gy is identified as a reasonable threshold for transient skin injury (Avanzo et al 2019;Fogg et al 2010;Geleijns and Wondergem 2005;Jaschke et al 2017;Moradi et al 2017a;Price et al 2013;Woodard and White 1986).…”