Expert system classifier for adaptive radiation therapy in prostate cancer.

A classifier-based expert system was developed to compare delivered and planned radiation therapy in prostate cancer patients. Its aim is to automatically identify patients that can benefit from an adaptive treatment strategy. The study predominantly addresses dosimetric uncertainties and critical issues caused by motion of hollow organs. 1200 MVCT images of 38 prostate adenocarcinoma cases were analyzed. An automatic daily re-contouring of structures (i.e. rectum, bladder and femoral heads), rigid/deformable registration and dose warping was carried out to simulate dose and volume variations during therapy. Support vector machine, K-means clustering algorithms and similarity index analysis were used to create an unsupervised predictive tool to detect incorrect setup and/or morphological changes as a consequence of inadequate patient preparation due to stochastic physiological changes, supporting clinical decision-making. After training on a dataset that was considered sufficiently dosimetrically stable, the system identified two equally sized macro clusters with distinctly different volumetric and dosimetric baseline properties and defined thresholds for these two clusters. Application to the test cohort resulted in 25% of the patients located outside the two macro clusters thresholds and which were therefore suspected to be dosimetrically unstable. In these patients, over the treatment course, mean volumetric changes of 30 and 40% for rectum and bladder were detected which possibly represents values justifying adjustment of patient preparation, frequent re-planning or a plan-of-the-day strategy. Based on our research, by combining daily IGRT images with rigid/deformable registration and dose warping, it is possible to apply a machine learning approach to the clinical setting obtaining useful information for a decision regarding an individualized adaptive strategy. Especially for treatments influenced by the movement of hollow organs, this could reduce inadequate treatments and possibly reduce toxicity, thereby increasing overall RT efficacy.

SIS epidemiological model for adaptive RT: Forecasting the parotid glands shrinkage during tomotherapy treatment.

PURPOSE: A susceptible-infected-susceptible (SIS) epidemic model was applied to radiation therapy (RT) treatments to predict morphological variations in head and neck (H&N) anatomy. METHODS: 360 daily MVCT images of 12 H&N patients treated by tomotherapy were analyzed in this retrospective study. Deformable image registration (DIR) algorithms, mesh grids, and structure recontouring, implemented in the RayStation treatment planning system (TPS), were applied to assess the daily organ warping. The parotid's warping was evaluated using the epidemiological approach considering each vertex as a single subject and its deformed vector field (DVF) as an infection. Dedicated IronPython scripts were developed to export daily coordinates and displacements of the region of interest (ROI) from the TPS. matlab tools were implemented to simulate the SIS modeling. Finally, the fully trained model was applied to a new patient. RESULTS: A QUASAR phantom was used to validate the model. The patients' validation was obtained setting 0.4 cm of vertex displacement as threshold and splitting susceptible (S) and infectious (I) cases. The correlation between the epidemiological model and the parotids' trend for further optimization of alpha and beta was carried out by Euclidean and dynamic time warping (DTW) distances. The best fit with experimental conditions across all patients (Euclidean distance of 4.09 ± 1.12 and DTW distance of 2.39 ± 0.66) was obtained setting the contact rate at 7.55 ± 0.69 and the recovery rate at 2.45 ± 0.26; birth rate was disregarded in this constant population. CONCLUSIONS: Combining an epidemiological model with adaptive RT (ART), the authors' novel approach could support image-guided radiation therapy (IGRT) to validate daily setup and to forecast anatomical variations. The SIS-ART model developed could support clinical decisions in order to optimize timing of replanning achieving personalized treatments.

A support vector machine tool for adaptive tomotherapy treatments: Prediction of head and neck patients criticalities.

PURPOSE: Adaptive radiation therapy (ART) is an advanced field of radiation oncology. Image-guided radiation therapy (IGRT) methods can support daily setup and assess anatomical variations during therapy, which could prevent incorrect dose distribution and unexpected toxicities. A re-planning to correct these anatomical variations should be done daily/weekly, but to be applicable to a large number of patients, still require time consumption and resources. Using unsupervised machine learning on retrospective data, we have developed a predictive network, to identify patients that would benefit of a re-planning. METHODS: 1200 MVCT of 40 head and neck (H&N) cases were re-contoured, automatically, using deformable hybrid registration and structures mapping. Deformable algorithm and MATLAB(®) homemade machine learning process, developed, allow prediction of criticalities for Tomotherapy treatments. RESULTS: Using retrospective analysis of H&N treatments, we have investigated and predicted tumor shrinkage and organ at risk (OAR) deformations. Support vector machine (SVM) and cluster analysis have identified cases or treatment sessions with potential criticalities, based on dose and volume discrepancies between fractions. During 1st weeks of treatment, 84% of patients shown an output comparable to average standard radiation treatment behavior. Starting from the 4th week, significant morpho-dosimetric changes affect 77% of patients, suggesting need for re-planning. The comparison of treatment delivered and ART simulation was carried out with receiver operating characteristic (ROC) curves, showing monotonous increase of ROC area. CONCLUSIONS: Warping methods, supported by daily image analysis and predictive tools, can improve personalization and monitoring of each treatment, thereby minimizing anatomic and dosimetric divergences from initial constraints.

Review of the results of the in vivo dosimetry during total skin electron beam therapy.

This work reviews results of in vivo dosimetry (IVD) for total skin electron beam (TSEB) therapy, focusing on new methods, data emerged within 2012. All quoted data are based on a careful review of the literature reporting IVD results for patients treated by means of TSEB therapy. Many of the reviewed papers refer mainly to now old studies and/or old guidelines and recommendations (by IAEA, AAPM and EORTC), because (due to intrinsic rareness of TSEB-treated pathologies) only a limited number of works and reports with a large set of numerical data and proper statistical analysis is up-to-day available in scientific literature. Nonetheless, a general summary of the results obtained by the now numerous IVD techniques available is reported; innovative devices and methods, together with areas of possible further and possibly multicenter investigations for TSEB therapies are highlighted.

IMRT-SIB with concurrent and neo-adjuvant platinum-based chemotherapy for locally advanced head and neck squamous cell cancer: analysis of clinical outcomes in a retrospective series of a single institution.

AIMS AND BACKGROUND: To evaluate results of an intensity-modulated radiotherapy with simultaneous integrated boost schedule with concurrent and neo-adjuvant platinum-based chemotherapy for the definitive treatment of locally advanced head and neck cancer in a retrospective series. METHODS AND STUDY DESIGN: Between May 2007 and February 2010, 28 consecutive patients with locally advanced head and neck cancer (stage II, 11%; III, 18%; IV, 71%) received intensity-modulated radiotherapy with simultaneous integrated boost with concurrent and neoadjuvant (20/28 patients) chemotherapy, at 1.8 G/die to 54 Gy to the elective volume and 66 Gy (2.2 Gy/die) to the tumor volume. Acute and late toxicities were scored according to RTOG/EORTC. A quality of life questionnaire for late xerostomia was also administered. Locoregional control and overall survival were estimated using Kaplan-Meier analysis. RESULTS: Median follow-up was 50 months, there was no grade 4 acute/late toxicity. Major acute toxicities were grade 2+ mucositis, 79%; grade 2+ xerostomia, 54%; grade 2+ dysphagia, 86%; 54% of patients required parenteral nutrition. The most relevant late reaction was grade 1 xerostomia (64%), which gradually recovered with time. A linear correlation between the RTOG/EORTC scale and the quality of life questionnaire value (P = 0.0120, r2 = 0.2641) was found, receiver operating characteristic analysis (ROC) confirmed sensitivity of the quality of life questionnaire to define grade 2 late salivary toxicity (P = 0.019). Five-year actuarial locoregional control and overall survival were 81% ± 7.7 SE and 82% ± 7.3 SE, respectively. CONCLUSIONS: A prospective trial of the intensity-modulated radiotherapy with simultaneous integrated boost schedule tested in this retrospective series with concurrent and neoadjuvant chemotherapy seems warranted in order to establish this approach as a standard regimen of intensity-modulated radiotherapy with simultaneous integrated boost chemoradiation.