Technical Note: A feasibility study on deep learning‐based radiotherapy dose calculation

Abstract

Purpose Various dose calculation algorithms are available for radiation therapy for cancer patients. However, these algorithms are faced with the tradeoff between efficiency and accuracy. The fast algorithms are generally less accurate, while the accurate dose engines are often time consuming. In this work, we try to resolve this dilemma by exploring deep learning (DL) for dose calculation. Methods We developed a new radiotherapy dose calculation engine based on a modified Hierarchically Densely Connected U‐net (HD U‐net) model and tested its feasibility with prostate intensity‐modulated radiation therapy (IMRT) cases. Mapping from an IMRT fluence map domain to a three‐dimensional (3D) dose domain requires a deep neural network of complicated architecture and a huge training dataset. To solve this problem, we first project the fluence maps to the dose domain using a broad beam ray‐tracing (RT) algorithm, and then we use the HD U‐net to map the RT dose distribution into an accurate dose distribution calculated using a collapsed cone convolution/superposition (CS) algorithm. The model is trained on 70 patients with fivefold cross validation, and tested on a separate 8 patients. Results It takes about 1 s to compute a 3D dose distribution for a typical 7‐field prostate IMRT plan, which can be further reduced to achieve real‐time dose calculation by optimizing the network. The average Gamma passing rate between DL and CS dose distributions for the 8 test patients are 98.5% (±1.6%) at 1 mm/1% and 99.9% (±0.1%) at 2 mm/2%. For comparison of various clinical evaluation criteria (dose‐volume points) for IMRT plans between two dose distributions, the average difference for dose criteria is less than 0.25 Gy while for volume criteria is <0.16%, showing that the DL dose distributions are clinically identical to the CS dose distributions. Conclusions We have shown the feasibility of using DL for calculating radiotherapy dose distribution with high accuracy and efficiency.

Knowledge‐based radiation treatment planning: A data‐driven method survey

“…HD U‐Net combines DenseNet's efficient feature propagation and utilizes U‐Net's ability to infer both local and global features by connecting each layer to every other layer in a feed‐forward fashion, yielding better RAM usage, and better generalization of the model. To further simplify the 3D dose prediction problem and increase prediction accuracy, Xing et al projected the 2D fluence maps onto the 3D dose distribution using a fast and inexpensive ray‐tracing dose calculation algorithm and trained HD U‐Net to map the ray‐tracing low accuracy dose distribution (does not consider scatter effect) into an accurate dose distribution calculated using collapsed cone convolution/superposition algorithm 145 …”

“…To further simplify the 3D dose prediction problem and increase prediction accuracy, Xing et al projected the 2D fluence maps onto the 3D dose distribution using a fast and inexpensive ray‐tracing dose calculation algorithm and trained HD U‐Net to map the ray‐tracing low accuracy dose distribution (does not consider scatter effect) into an accurate dose distribution calculated using collapsed cone convolution/superposition algorithm. 145 …”

Artificial intelligence in radiation oncology

“…AI tools for automating treatment planning have two main steps: 1) predicting the optimal dose distribution; and 2) identifying the treatment machine parameters required to achieve that distribution. The results of several studies demonstrate the ability of deep learning algorithms to predict the optimal dose distributions for individual patients based on their anatomy [30][31][32] and to accelerate dose calculations 79 . In order for AI-based treatment-planning algorithms to generate a high-quality plan, information regarding the complex decision-making process needs to be included in the underlying model, similar to the approach used in the development of AI algorithms that are able to play Atari games 80 or the board game Go 81 .…”

Machine learning applications in radiation oncology

“…Subsequently, DVHs have been used to generate optimisation objectives, reducing the dependence on the user and leading to more consistent and efficient treatment plan optimisation [107][108][109][110][111][112][113]. More recently, prediction of full 3D dose distributions has been achieved through deep learning approaches [114][115][116][117][118][119][120][121]. In these methods, the input data for training includes 3D masks of target and OAR structures and/or CT image data with spatially associated 3D dose grids from manually created treatment plans.…”