Elekta (United States)

Objective. To develop and evaluate a deep learning based fast volumetric modulated arc therapy (VMAT) plan generation method for prostate radiotherapy. Approach. A customized 3D U-Net was trained and validated to predict initial segments at 90 evenly distributed control points of an arc, linked to our research treatment planning system (TPS) for segment shape optimization (SSO) and segment weight optimization (SWO). For 27 test patients, the VMAT plans generated based on the deep learning prediction (VMATDL) were compared with VMAT plans generated with a previously validated automated treatment planning method (VMATref). For all test cases, the deep learning prediction accuracy, plan dosimetric quality, and the planning efficiency were quantified and analyzed. Main results. For all 27 test cases, the resulting plans were clinically acceptable. The V 95% for the PTV2 was greater than 99%, and the V 107% was below 0.2%. Statistically significant difference in target coverage was not observed between the VMATref and VMATDL plans (P = 0.3243 > 0.05). The dose sparing effect to the OARs between the two groups of plans was similar. Small differences were only observed for the Dmean of rectum and anus. Compared to the VMATref, the VMATDL reduced 29.3% of the optimization time on average. Significance. A fully automated VMAT plan generation method may result in significant improvement in prostate treatment planning efficiency. Due to the clinically acceptable dosimetric quality and high efficiency, it could potentially be used for clinical planning application and real-time adaptive therapy application after further validation.

This paper presents the Population Learning followed by One Shot Learning (PLOSL) pulmonary image registration method. PLOSL is a fast unsupervised learning-based framework for 3D-CT pulmonary image registration algorithm based on combining population learning (PL) and one-shot learning (OSL). The PLOSL image registration has the advantages of the PL and OSL approaches while reducing their respective drawbacks. The advantages of PLOSL include improved performance over PL, substantially reducing OSL training time and reducing the likelihood of OSL getting stuck in local minima. PLOSL pulmonary image registration uses tissue volume preserving and vesselness constraints for registration of inspiration-to-expiration and expiration-to-inspiration pulmonary CT images. A coarse-to-fine convolution encoder-decoder CNN architecture is used to register large and small shape features. During training, the sum of squared tissue volume difference (SSTVD) compensates for intensity differences between inspiration and expiration computed tomography (CT) images and the sum of squared vesselness measure difference (SSVMD) helps match the lung vessel tree. Results show that the PLOSL (SSTVD+SSVMD) algorithm achieved subvoxel landmark error while preserving pulmonary topology on the SPIROMICS data set, the public DIR-LAB COPDGene and 4DCT data sets.

The EVIDENCE (EValuatIng connecteD sENsor teChnologiEs) checklist was developed by a multidisciplinary group of content experts convened by the Digital Medicine Society, representing the clinical sciences, data management, technology development, and biostatistics. The aim of EVIDENCE is to promote high quality reporting in studies where the primary objective is an evaluation of a digital measurement product or its constituent parts. Here we use the terms digital measurement product and connected sensor technology interchangeably to refer to tools that process data captured by mobile sensors using algorithms to generate measures of behavioral and/or physiological function. EVIDENCE is applicable to 5 types of evaluations: (1) proof of concept; (2) verification, (3) analytical validation, and (4) clinical validation as defined by the V3 framework; and (5) utility and usability assessments. Using EVIDENCE, those preparing, reading, or reviewing studies evaluating digital measurement products will be better equipped to distinguish necessary reporting requirements to drive high-quality research. With broad adoption, the EVIDENCE checklist will serve as a much-needed guide to raise the bar for quality reporting in published literature evaluating digital measurements products.

Magnetic resonance imaging (MRI)-guided radiation therapy (RT) treatment planning is limited by the fact that the electron density distribution required for dose calculation is not readily provided by MR imaging. We compare a selection of novel synthetic CT generation algorithms recently reported in the literature, including segmentation-based, atlas-based and machine learning techniques, using the same cohort of patients and quantitative evaluation metrics. Six MRI-guided synthetic CT generation algorithms were evaluated: one segmentation technique into a single tissue class (water-only), four atlas-based techniques, namely, median value of atlas images (ALMedian), atlas-based local weighted voting (ALWV), bone enhanced atlas-based local weighted voting (ALWV-Bone), iterative atlas-based local weighted voting (ALWV-Iter), and a machine learning technique using deep convolution neural network (DCNN). Organ auto-contouring from MR images was evaluated for bladder, rectum, bones, and body boundary. Overall, DCNN exhibited higher segmentation accuracy resulting in Dice indices (DSC) of 0.93±0.17, 0.90±0.04, and 0.93±0.02 for bladder, rectum, and bones, respectively. On the other hand, ALMedian showed the lowest accuracy with DSC of 0.82±0.20, 0.81±0.08, and 0.88±0.04, respectively. DCNN reached the best performance in terms of accurate derivation of synthetic CT values within each organ, with a mean absolute error within the body contour of 32.7±7.9HU, followed by the advanced atlas-based methods (ALWV: 40.5±8.2HU, ALWV-Iter: 42.4±8.1HU, ALWV-Bone: 44.0±8.9HU). ALMedian led to the highest error (52.1±11.1HU). Considering the dosimetric evaluation results, ALWV-Iter, ALWV, DCNN and ALWV-Bone led to similar mean dose estimation within each organ at risk and target volume with less than 1% dose discrepancy. However, the two-dimensional gamma analysis demonstrated higher pass rates for ALWV-Bone, DCNN, ALMedian and ALWV-Iter at 1%/1mm criterion with 94.99±5.15%, 94.59±5.65%, 93.68±5.53% and 93.10±5.99% success, respectively, while ALWV and water-only resulted in 86.91±13.50% and 80.77±12.10%, respectively. Overall, machine learning and advanced atlas-based methods exhibited promising performance by achieving reliable organ segmentation and synthetic CT generation. DCNN appears to have slightly better performance by achieving accurate automated organ segmentation and relatively small dosimetric errors (followed closely by advanced atlas-based methods, which in some cases achieved similar performance). However, the DCNN approach showed higher vulnerability to anatomical variation, where a greater number of outliers was observed with this method. Considering the dosimetric results obtained from the evaluated methods, the challenge of electron density estimation from MR images can be resolved with a clinically tolerable error.

The purpose of this study was to acquire beam data for an MR-linac, with and without a 1.5T magnetic field, by using a variety of commercially available detectors to assess their relative response in the magnetic field. The impact of the magnetic field on the measured dose distribution was also assessed. An MR-safe 3D scanning water phantom was used to measure output factors, depth dose curves, and off-axis profiles for various depths and for field sizes between 2×2cm2 and 22×22cm2 for an Elekta MR-linac beam with the orthogonal 1.5T magnetic field on or off. An on-board MV portal imaging system was used to ensure that the reproducibility of the detector position, both with and without the magnetic field, was within 0.1mm. The detectors used included ionization chambers with large, medium, and small sensitive volumes; a diamond detector; a shielded diode; and an unshielded diode. The offset of the effective point of measurement of the ionization chambers was found to be reduced by at least half for each chamber in the direction parallel with the beam. A lateral shift of similar magnitude was also introduced to the chambers' effective point of measurement toward the average direction of the Lorentz force. A similar lateral shift (but in the opposite direction) was also observed for the diamond and diode detectors. The measured lateral shift in the dose distribution was independent of depth and field size for each detector for fields between 2×2cm2 and 10×10cm2 . The shielded diode significantly misrepresented the dose distribution in the lateral direction perpendicular to the magnetic field, making it seem more symmetric. The percentage depth dose was generally found to be lower with the magnetic field than without, but this difference was reduced as field size increased. The depth of maximum dose showed little dependence on field size in the presence of the magnetic field, with values from 1.2cm to 1.3cm between the 2×2cm2 and 22×22cm2 fields. Output factors measured in the magnetic field at the center of the beam profile produced a larger spread of values between detectors for fields smaller than 10×10cm2 (with a spread of 2% at 3×3cm2 ). The spread of values was more consistent when the output factors were measured at the point of peak intensity of the lateral dose distribution instead (except for the shielded diode which differed by up to 2% depending on field size). The magnetic field of the MR-linac alters the effective point of measurement of ionization chambers, shifting it both downstream and laterally. Shielded diodes produce incorrect and misleading dose profiles. The output factor measured at the point of peak intensity in the lateral dose distribution is more robust than the conventional output factor (measured at central axis). Diodes are not recommended for output factor measurements in the magnetic field.