Search

Introduction: Deep learning (DL) models that use medical images to predict clinical outcomes are poised for clinical translation. For tumors that reside in organs that move, however, the impact of motion (i.e., degenerated object appearance or blur) on DL model accuracy remains unclear. We examine the impact of tumor motion on an image-based DL framework that predicts local failure risk after lung stereotactic body radiotherapy (SBRT)., Methods: We input pre-therapy free breathing (FB) computed tomography (CT) images from 849 patients treated with lung SBRT into a multitask deep neural network to generate an image fingerprint signature (or DL score) that predicts time-to-event local failure outcomes. The network includes a convolutional neural network encoder for extracting imaging features and building a task-specific fingerprint, a decoder for estimating handcrafted radiomic features, and a task-specific network for generating image signature for radiotherapy outcome prediction. The impact of tumor motion on the DL scores was then examined for a holdout set of 468 images from 39 patients comprising: (1) FB CT, (2) four-dimensional (4D) CT, and (3) maximum-intensity projection (MIP) images. Tumor motion was estimated using a 3D vector of the maximum distance traveled, and its association with DL score variance was assessed by linear regression., Findings: The variance and amplitude in 4D CT image-derived DL scores were associated with tumor motion (R 2  = 0.48 and 0.46, respectively). Specifically, DL score variance was deterministic and represented by sinusoidal undulations in phase with the respiratory cycle. DL scores, but not tumor volumes, peaked near end-exhalation. The mean of the scores derived from 4D CT images and the score obtained from FB CT images were highly associated (Pearson r = 0.99). MIP-derived DL scores were significantly higher than 4D- or FB-derived risk scores (p < 0.0001)., Interpretation: An image-based DL risk score derived from a series of 4D CT images varies in a deterministic, sinusoidal trajectory in a phase with the respiratory cycle. These results indicate that DL models of tumors in motion can be robust to fluctuations in object appearance due to movement and can guide standardization processes in the clinical translation of DL models for patients with lung cancer., (© 2022 American Association of Physicists in Medicine.)

Purpose: The equivalent square (ES) concept has been used for traditional radiation fields defined by the machine collimating system. For small fields, the concept S clin was introduced based on measuring dosimetric field width (full-width half maximum, FWHM) of the cardinal axis of the beam profiles. The pros and cons of this concept are evaluated in small fields and compared with the traditional ES using area and perimeter (4A/P) method based on geometric field size settings, for example, light field settings., Methods: One hundred thirty-seven square and rectangular fields from 5-50 mm with every possible permutation (keeping one jaw fixed and varying other jaw from 5 to 50 mm) were utilized to measure FWHM for the validation of S clin . Using a microSilicon detector and a scanning water tank, measurements were performed on an Elekta (Versa) machine with Agility head and a Varian TrueBeam with different MLC/Jaw design to evaluate the S clin concept and to understand the effect of exchange factor in small fields. Field output factors were also measured for all 137 fields., Results: The data fitting for fields ranging from 5-50 mm between the traditional 4A/P method and S clin shows differences and indicates a linear relationship with distinct separation of slope for Elekta and Varian machines. For Elekta Agility machine ES based on 4A/P < S clin and for the VarianTrueBeam  4A/P > S clin for square fields. Our measured data show that both methods are equally valid but does vary by the machine design. The field output factor is dependent on the elongation factor as well as machine design. For fields with sides ≥10 mm, the exchange factor is nearly identical in both machines with magnitude up to 4%, which is close to measurement uncertainty (±3%), but for small fields (< 10 mm), the Elekta machine has higher exchange factors compared to the Varian machine., Conclusion: The results demonstrate that the two concepts for defining equivalent field (S clin and 4A/P) are equivalent and can be directly related through an empirical equation. This study confirms that 4A/P is still valid for small fields except for very small fields (≤10 mm) where source occlusion is a dominating factor. The S clin method is potentially sensitive to measurement uncertainty due to measurement of FWHM which is machine-, detector- and user-dependent, while the 4A/P method relies mainly on geometry of the machine and has less dependency on type of machine, detector, and user. The exchange factors are comparable for both types of machines. The conclusion is based on data from an Elekta with Agility head and a Varian TrueBeam machine that may have potential for bias due to light field/collimator set up and alignment. Care should be taken in extrapolating these data to any other machine., (© 2022 American Association of Physicists in Medicine.)

Purpose: Statistical process control tools such as control charts were recommended by the American Association of Physicists in Medicine (AAPM) Task Group 218 for radiotherapy quality assurance. However, the tools needed to analyze multivariate, correlated data that are often encountered in treatment plan quality measures, are lacking. In this study, we develop quality control tools that can model multivariate plan quality measures with correlations and account for patient-specific risk factors, without adding a significant burden to clinical workflow., Methods and Materials: A multivariate, quality control chart is developed that includes a risk-adjustment model, Hotelling's T 2 statistic, and principal component analysis (PCA). Principal component analysis accounts for correlations among a set of organ-at-risk (OAR) dose-volume histogram (DVH) points that serves as proxies for plan quality. Risk-adjustment models estimate the principal components from PCA using a set of patient- and treatment-specific risk factors. The resulting residuals from the risk-adjustment models are used to compute the Hotelling's T 2 statistic; the corresponding multivariate control chart is then plotted based on the beta distribution followed by the statistic. Further, the box-cox transformation is used to account for non-normality in DVH points. We investigate the application of the proposed methodology via three multivariate control charts - a conventional chart that ignores risk-adjustment and PCA, a risk-adjusted chart ignoring PCA, and a PCA-based, risk-adjusted chart. These control charts are evaluated on 69 head-and-neck cases., Results: The conventional multivariate control chart fails to account for important patient-specific risk factors, including volumes and cross-sectional areas of the tumor and OARs and distances in-between. This failure leads to a larger number of false alarms. While the multivariate risk-adjusted control chart is able to reduce false alarms, it fails to account for correlations in DVH points. The multivariate PCA-based, risk-adjusted control chart can detect unusual plans after accounting for the correlations. By replanning, improvements are shown on an unusual plan identified by both risk-adjusted methods., Conclusions: The multivariate risk-adjusted control chart developed here enables quality control of plans prior to delivery. This methodology is generic and can be readily applied for other radiotherapy quality assurance protocols, such as gamma analysis pass rates., (© 2021 American Association of Physicists in Medicine.)