Background: Fast dose calculation is critical for online and real-time adaptive therapy workflows. While modern physics-based dose algorithms must compromise accuracy to achieve low computation times, deep learning models can potentially perform dose prediction tasks with both high fidelity and speed. Purpose: We present a deep learning algorithm that, exploiting synergies between transformer and convolutional layers, accurately predicts broad photon beam dose distributions in few milliseconds. Methods: The proposed improved Dose Transformer Algorithm (iDoTA) maps arbitrary patient geometries and beam information (in the form of a 3D projected shape resulting from a simple ray tracing calculation) to their corresponding 3D dose distribution. Treating the 3D CT input and dose output volumes as a sequence of 2D slices along the direction of the photon beam, iDoTA solves the dose prediction task as sequence modeling. The proposed model combines a Transformer backbone routing long-range information between all elements in the sequence, with a series of 3D convolutions extracting local features of the data. We train iDoTA on a dataset of 1700 beam dose distributions, using 11 clinical volumetric modulated arc therapy (VMAT) plans (from prostate, lung, and head and neck cancer patients with 194–354 beams per plan) to assess its accuracy and speed. Results: iDoTA predicts individual photon beams in ≈50 ms with a high gamma pass rate of (Formula presented.) (2 mm, 2%). Furthermore, estimating full VMAT dose distributions in 6–12 s, iDoTA achieves state-of-the-art performance with a (Formula presented.) (2 mm, 2%) pass rate and an average relative dose error of 0.75 ± 0.36%. Conclusions: Offering the millisecond speed prediction per beam angle needed in online and real-time adaptive treatments, iDoTA represents a new state of the art in data-driven photon dose calculation. The proposed model can massively speed-up current photon workflows, reducing calculation times from few minutes to just a few seconds.

Objective. In radiotherapy, the internal movement of organs between treatment sessions causes errors in the final radiation dose delivery. To assess the need for adaptation, motion models can be used to simulate dominant motion patterns and assess anatomical robustness before delivery. Traditionally, such models are based on principal component analysis (PCA) and are either patient-specific (requiring several scans per patient) or population-based, applying the same set of deformations to all patients. We present a hybrid approach which, based on population data, allows to predict patient-specific inter-fraction variations for an individual patient. Approach. We propose a deep learning probabilistic framework that generates deformation vector fields warping a patient's planning computed tomography (CT) into possible patient-specific anatomies. This daily anatomy model (DAM) uses few random variables capturing groups of correlated movements. Given a new planning CT, DAM estimates the joint distribution over the variables, with each sample from the distribution corresponding to a different deformation. We train our model using dataset of 312 CT pairs with prostate, bladder, and rectum delineations from 38 prostate cancer patients. For 2 additional patients (22 CTs), we compute the contour overlap between real and generated images, and compare the sampled and ‘ground truth’ distributions of volume and center of mass changes. Results. With a DICE score of 0.86 ± 0.05 and a distance between prostate contours of 1.09 ± 0.93 mm, DAM matches and improves upon previously published PCA-based models, using as few as 8 latent variables. The overlap between distributions further indicates that DAM’s sampled movements match the range and frequency of clinically observed daily changes on repeat CTs. Significance. Conditioned only on planning CT values and organ contours of a new patient without any pre-processing, DAM can accurately deformations seen during following treatment sessions, enabling anatomically robust treatment planning and robustness evaluation against inter-fraction anatomical changes.

Functionally graded scaffold (FGS) is designed to mimic the morphology, mechanical and biological properties of natural bone closely. Porosity variation strategy between different regions in FGS plays a crucial role in influencing its mechanical and biological performance. A combination of modeling tool and scripting language can effectively enhance the ability to optimize FGS design. This study was aimed at determining the effect of porosity variation strategy on the mechanical performance and permeability of the as-built and as-heat-treated FGSs. Ti-6Al-4V FGSs with sizes of 10 × 10 × 15 mm and diamond lattice structures were designed and fabricated by means of selective laser melting. A wide range of porosities in the FGSs (38–75%) were achieved by applying six different porosity variation strategies. The elastic modulus (3.7–5.7 GPa) and yield strength (27.1–84.7 MPa) of the as-built FGSs were found to vary between the corresponding mechanical properties of cancellous bone and cortical bone. Heat treatment reduced the strengths by 13–56%. Porosity variation strategy strongly affected the deformation behavior and failure mechanisms of the FGSs. The sigmoid function-controlled FGSs showed gradual failure behavior and sample Sigk0.5b8 showed superior overall performance. The results demonstrated that porosity variation strategy is a feasible means for tailor design of FGS.