Feasibility of two-dimensional dose distribution deconvolution using convolution neural networks

• Published in: Medical physics (Lancaster) Vol. 46; no. 12; p. 5833
• Main Authors: Cheon, Wonjoong, Kim, Sung Jin, Kim, Kyuseok, Lee, Moonhee, Lee, Jinhyeop, Jo, Kwanghyun, Cho, Sungkoo, Cho, Hyosung, Han, Youngyih
• Format: Journal Article
• Language: English
• Published: United States 01.12.2019
• Subjects: Feasibility Studies; Humans; Neural Networks, Computer; Radiation Dosage; Radiometry; Radiotherapy Dosage; Radiotherapy Planning, Computer-Assisted - methods; Radiotherapy, Intensity-Modulated; scintillation detector; deconvolution; convolution neural network
• ISSN: 2473-4209
• DOI: 10.1002/mp.13869

The purpose of this study was to investigate the feasibility of two-dimensional (2D) dose distribution deconvolution using convolutional neural networks (CNNs) instead of an analytical approach for an in-house scintillation detector that has a detector-interface artifact in the penumbra region. Datasets of 2D dose distributions were acquired from a medical linear accelerator of Novalis Tx. The datasets comprise two different sizes of square radiation fields and 13 clinical intensity-modulated radiation treatment (IMRT) plans. These datasets were divided into two datasets (training and test) to train and validate the developed network, called PenumbraNet, which is a shallow linear CNN. The PenumbraNet was trained to transform the measured dose distribution [M(x, y)] to calculated distribution [D(x, y)] by the treatment planning system. After training of the PenumbraNet was completed, the performance was evaluated using test data, which were 10 × 10 cm open field and ten clinical IMRT cases. The corrected dose distribution [C(x, y)] was evaluated against D(x, y) with 2%/2 mm and 3%/3 mm criteria of the gamma index for each field. The M(x, y) and deconvolved dose distribution with the analytically obtained kernel using Wiener filtering [A(x, y)] were also evaluated for comparison. In addition, we compared the performance of the shallow depth of linear PenumbraNet with that of nonlinear PenumbraNet and a deep nonlinear PenumbraNet within the same training epoch. The mean gamma passing rates were 84.77% and 95.81% with 3%/3 mm gamma criteria for A(x, y) and C(x, y) of the PenumbraNet, respectively. The mean gamma pass rates of nonlinear PenumbraNet and the deep depth of nonlinear PenumbraNet were 96.62%, 93.42% with 3%/3 mm gamma criteria, respectively. We demonstrated the feasibility of the PenumbraNets for 2D dose distribution deconvolution. The nonlinear PenumbraNet which has the best performance improved the gamma passing rate by 11.85% from the M(x, y) at 3%/3 mm gamma criteria.