성균관의대 / 천원중, 한영이*
Abstract
PURPOSE:
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.
METHODS:
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 cm2 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.
RESULTS:
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.
CONCLUSIONS:
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.
Author information
Cheon W1, Kim SJ2, Kim K3, Lee M1, Lee J1, Jo K2, Cho S2, Cho H3, Han Y1,4.
1
Department of Health Sciences and Technology, SAIHST, Sungkyunkwan University, Seoul, 06351, Korea.
2
Department of Radiation Oncology, Samsung Medical Center, Seoul, 06351, Korea.
3
Department of Radiation Convergence Engineering, Yonsei University, Wonju, 26493, Korea.
4
Department of Radiation Oncology, School of Medicine, Samsung Medical Center, Sungkyunkwan University, Seoul, 06351, Korea.
편집위원
최근에 인공지능이 적용되지 않는 분야가 없는 것 같은 정도로 많은 분야에 사용되고 있다. 섬광판으로 방사선분포를 측정하는 분야에서도 섬광분포를 방사선분포로 변환하는 과정에 고려해야 할 많은 요소들이 있는데, 이를 인공지능으로 빠르고 쉽게 변환하고자 하는 노력이다. 앞으로는 현상을 논리적으로 이해하고 설명하고자 하는 과학의 개념이 완전히 바뀌지 않을 까 생각해 본다.
2020-01-30 17:33:02