Evaluation of the effectiveness of novel single-intervention adaptive radiotherapy strategies based on daily dose accumulation.

Parotid gland (PG) shrinkage and neck volume reduction during radiotherapy of head and neck (H&N) cancer patients is a clinical issue that has prompted interest in adaptive radiotherapy (ART). This study focuses on the difference between planned dose and delivered dose and the possible effects of an efficient replanning strategy during the course of treatment. Six patients with H&N cancer treated by tomotherapy were retrospectively enrolled. Thirty daily dose distributions (DMVCT) were calculated on pretreatment megavoltage computed tomography (MVCT) scans. Deformable Image Registration which matched daily MVCT with treatment planning kilovoltage computed tomography was performed. Using the resulting deformation vector field, all daily DMVCT were deformed to the planning kilovoltage computed tomography and resulting doses were accumulated voxel per voxel. Cumulative DMVCT was compared to planned dose distribution performing γ-analysis (2 mm, 2% of 2.2 Gy). Two single-intervention ART strategies were executed on the 18th fraction whose previous data had suggested to be a suitable timepoint for a single replanning intervention: (1) replanning on the original target and deformed organ at risks (OARs) (a "safer" approach regarding tumor coverage) and (2) replanning on both deformed target and deformed OARs. DMVCT showed differences between planned and delivered doses (3D-γ 2mm/2%-passing rate = 85 ± 1%, p < 0.001). Voxel by voxel dose accumulation showed an increase in average dose of warped PG of 3.0 Gy ± 3.3 Gy. With ART the average dose of warped PG decreased by 3.2 Gy ± 1.7 Gy in comparison to delivered dose without replanning when both target and OARs were deformed. Average dose of warped PG decreased by 2.0 Gy ± 1.4 Gy when only OARs were deformed. Anatomical variations lead to increased doses to PGs. Efficient single-intervention ART-strategies with replanning on the 18th MVCT result a reduced PG dose. A strategy with deformation of both target and OAR resulted in the lowest PG dose, while formally maintaining PTV coverage. Deformation of only OAR nevertheless reduces PG dose and has less uncertainties regarding PTV coverage.

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.

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.