1
|
Vasudevan V, Shen L, Huang C, Chuang C, Islam MT, Ren H, Yang Y, Dong P, Xing L. Implicit neural representation for radiation therapy dose distribution. Phys Med Biol 2022; 67. [DOI: 10.1088/1361-6560/ac6b10] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/20/2022] [Accepted: 04/27/2022] [Indexed: 11/12/2022]
Abstract
Abstract
Objective. Dose distribution data plays a pivotal role in radiotherapy treatment planning. The data is typically represented using voxel grids, and its size ranges from 106 to 108. A concise representation of the treatment plan is of great value in facilitating treatment planning and downstream applications. This work aims to develop an implicit neural representation of 3D dose distribution data. Approach. Instead of storing the dose values at each voxel, in the proposed approach, the weights of a multilayer perceptron (MLP) are employed to characterize the dosimetric data for plan representation and subsequent applications. We train a coordinate-based MLP with sinusoidal activations to map the voxel spatial coordinates to the corresponding dose values. We identify the best architecture for a given parameter budget and use that to train a model for each patient. The trained MLP is evaluated at each voxel location to reconstruct the dose distribution. We perform extensive experiments on dose distributions of prostate, spine, and head and neck tumor cases to evaluate the quality of the proposed representation. We also study the change in representation quality by varying model size and activation function. Main results. Using coordinate-based MLPs with sinusoidal activations, we can learn implicit representations that achieve a mean-squared error of 10−6 and peak signal-to-noise ratio greater than 50 dB at a target bitrate of ∼1 across all the datasets, with a compression ratio of ∼32. Our results also show that model sizes with a bitrate of 1–2 achieve optimal accuracy. For smaller bitrates, performance starts to drop significantly. Significance. The proposed model provides a low-dimensional, implicit, and continuous representation of 3D dose data. In summary, given a dose distribution, we systematically show how to find a compact model to fit the data accurately. This study lays the groundwork for future applications of neural representations of dose data in radiation oncology.
Collapse
|
2
|
Song Y, Hu J, Liu Y, Hu H, Huang Y, Bai S, Yi Z. Dose prediction using a deep neural network for accelerated planning of rectal cancer radiotherapy. Radiother Oncol 2020; 149:111-116. [DOI: 10.1016/j.radonc.2020.05.005] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/02/2020] [Revised: 04/16/2020] [Accepted: 05/05/2020] [Indexed: 10/24/2022]
|
3
|
Ma M, K. Buyyounouski M, Vasudevan V, Xing L, Yang Y. Dose distribution prediction in isodose feature‐preserving voxelization domain using deep convolutional neural network. Med Phys 2019; 46:2978-2987. [DOI: 10.1002/mp.13618] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/22/2019] [Revised: 05/01/2019] [Accepted: 05/02/2019] [Indexed: 01/30/2023] Open
Affiliation(s)
- Ming Ma
- Department of Radiation Oncology Stanford University 875 Blake Wilbur Drive Stanford CA 94305‐5847USA
| | - Mark K. Buyyounouski
- Department of Radiation Oncology Stanford University 875 Blake Wilbur Drive Stanford CA 94305‐5847USA
| | - Varun Vasudevan
- Department of Radiation Oncology Stanford University 875 Blake Wilbur Drive Stanford CA 94305‐5847USA
| | - Lei Xing
- Department of Radiation Oncology Stanford University 875 Blake Wilbur Drive Stanford CA 94305‐5847USA
| | - Yong Yang
- Department of Radiation Oncology Stanford University 875 Blake Wilbur Drive Stanford CA 94305‐5847USA
| |
Collapse
|