David C Hansen1, Guillaume Landry2, Florian Kamp3, Minglun Li3, Claus Belka3,4, Katia Parodi2, Christopher Kurz2,3. 1. Department of Medical Physics, Aarhus University Hospital, Aarhus, 8200, Denmark. 2. Department of Medical Physics, Faculty of Physics, Ludwig-Maximilians-Universität München (LMU Munich), Garching bei München, 85748, Germany. 3. Department of Radiation Oncology, University Hospital, LMU Munich, Munich, 81377, Germany. 4. German Cancer Consortium (DKTK), Munich, Germany.
Abstract
PURPOSE: To demonstrate a proof-of-concept for fast cone-beam CT (CBCT) intensity correction in projection space by the use of deep learning. METHODS: The CBCT scans and corresponding projections were acquired from 30 prostate cancer patients. Reference shading correction was performed using a validated method (CBCT cor ), which estimates scatter and other low-frequency deviations in the measured CBCT projections on the basis of a prior CT image obtained from warping the planning CT to the CBCT. A convolutional neural network (ScatterNet) was designed, consisting of an attenuation conversion stage followed by a shading correction stage using a UNet-like architecture. The combined network was trained in 2D, utilizing pairs of measured and corrected projections of the reference method, in order to perform shading correction in projection space before reconstruction. The number of patients used for training, testing, and evaluation was 15, 7, and 8, respectively. The reconstructed CBCT ScatterNet was compared to CBCT cor in terms of mean and absolute errors (ME and MAE) for the eight evaluation patients (not included in the network training). Volumetric modulated arc photon therapy (VMAT) and intensity-modulated proton therapy (IMPT) plans were generated on CBCT cor . Dose was recalculated on CBCT ScatterNet to evaluate its dosimetric accuracy. Single-field uniform dose proton plans were utilized for proton range comparison of CBCT ScatterNet and CBCT cor . RESULTS: The CBCT ScatterNet showed no cupping artifacts and a considerably smaller MAE and ME with respect to CBCT cor than the uncorrected CBCT (on average 144 Hounsfield units (HU) vs 46 HU for MAE and 138 HU vs -3 HU for ME). The pass-rates using a 2% dose-difference criterion at 50% dose cut-off, were close to 100% for the VMAT plans of all patients when comparing CBCT ScatterNet to CBCT cor . For IMPT plans pass-rates were clearly lower, ranging from 15% to 81%. Proton range differences of up to 5 mm occurred. CONCLUSIONS: Using a deep convolutional neural network for CBCT intensity correction was shown to be feasible in the pelvic region for the first time. Dose calculation accuracy on CBCT ScatterNet was high for VMAT, but unsatisfactory for IMPT. With respect to the reference technique (CBCT cor ), the neural network enabled a considerable increase in speed for intensity correction and might eventually allow for on-the-fly shading correction during CBCT acquisition.
PURPOSE: To demonstrate a proof-of-concept for fast cone-beam CT (CBCT) intensity correction in projection space by the use of deep learning. METHODS: The CBCT scans and corresponding projections were acquired from 30 prostate cancerpatients. Reference shading correction was performed using a validated method (CBCT cor ), which estimates scatter and other low-frequency deviations in the measured CBCT projections on the basis of a prior CT image obtained from warping the planning CT to the CBCT. A convolutional neural network (ScatterNet) was designed, consisting of an attenuation conversion stage followed by a shading correction stage using a UNet-like architecture. The combined network was trained in 2D, utilizing pairs of measured and corrected projections of the reference method, in order to perform shading correction in projection space before reconstruction. The number of patients used for training, testing, and evaluation was 15, 7, and 8, respectively. The reconstructed CBCT ScatterNet was compared to CBCT cor in terms of mean and absolute errors (ME and MAE) for the eight evaluation patients (not included in the network training). Volumetric modulated arc photon therapy (VMAT) and intensity-modulated proton therapy (IMPT) plans were generated on CBCT cor . Dose was recalculated on CBCT ScatterNet to evaluate its dosimetric accuracy. Single-field uniform dose proton plans were utilized for proton range comparison of CBCT ScatterNet and CBCT cor . RESULTS: The CBCT ScatterNet showed no cupping artifacts and a considerably smaller MAE and ME with respect to CBCT cor than the uncorrected CBCT (on average 144 Hounsfield units (HU) vs 46 HU for MAE and 138 HU vs -3 HU for ME). The pass-rates using a 2% dose-difference criterion at 50% dose cut-off, were close to 100% for the VMAT plans of all patients when comparing CBCT ScatterNet to CBCT cor . For IMPT plans pass-rates were clearly lower, ranging from 15% to 81%. Proton range differences of up to 5 mm occurred. CONCLUSIONS: Using a deep convolutional neural network for CBCT intensity correction was shown to be feasible in the pelvic region for the first time. Dose calculation accuracy on CBCT ScatterNet was high for VMAT, but unsatisfactory for IMPT. With respect to the reference technique (CBCT cor ), the neural network enabled a considerable increase in speed for intensity correction and might eventually allow for on-the-fly shading correction during CBCT acquisition.
Authors: Joseph Harms; Yang Lei; Tonghe Wang; Rongxiao Zhang; Jun Zhou; Xiangyang Tang; Walter J Curran; Tian Liu; Xiaofeng Yang Journal: Med Phys Date: 2019-07-17 Impact factor: 4.071
Authors: Yang Zhang; Ning Yue; Min-Ying Su; Bo Liu; Yi Ding; Yongkang Zhou; Hao Wang; Yu Kuang; Ke Nie Journal: Med Phys Date: 2021-05-14 Impact factor: 4.071
Authors: Nimu Yuan; Brandon Dyer; Shyam Rao; Quan Chen; Stanley Benedict; Lu Shang; Yan Kang; Jinyi Qi; Yi Rong Journal: Phys Med Biol Date: 2020-01-27 Impact factor: 3.609