Dose image prediction for range and width verifications from carbon ion‐induced secondary electron bremsstrahlung x‐rays using deep learning workflow

Abstract

Purpose Imaging of the secondary electron bremsstrahlung (SEB) x rays emitted during particle‐ion irradiation is a promising method for beam range estimation. However, the SEB x‐ray images are not directly correlated to the dose images. In addition, limited spatial resolution of the x‐ray camera and low‐count situation may impede correctly estimating the beam range and width in SEB x‐ray images. To overcome these limitations of the SEB x‐ray images measured by the x‐ray camera, a deep learning (DL) approach was proposed in this work to predict the dose images for estimating the range and width of the carbon ion beam on the measured SEB x‐ray images. Methods To prepare enough data for the DL training efficiently, 10,000 simulated SEB x‐ray and dose image pairs were generated by our in‐house developed model function for different carbon ion beam energies and doses. The proposed DL neural network consists of two U‐nets for SEB x ray to dose image conversion and super resolution. After the network being trained with these simulated x‐ray and dose image pairs, the dose images were predicted from simulated and measured SEB x‐ray testing images for performance evaluation. Results For the 500 simulated testing images, the average mean squared error (MSE) was 2.5 × 10−5 and average structural similarity index (SSIM) was 0.997 while the error of both beam range and width was within 1 mm FWHM. For the three measured SEB x‐ray images, the MSE was no worse than 5.5 × 10−3 and SSIM was no worse than 0.980 while the error of the beam range and width was 2 mm and 5 mm FWHM, respectively. Conclusions We have demonstrated the advantages of predicting dose images from not only simulated data but also measured data using our deep learning approach.

Technical note: Correcting angular dependencies using non‐polarized components of Cherenkov light in water during high‐energy X‐ray irradiation

“…In addition, a deep learning approach may be able to reduce the noise in the images without blurring the images. [17][18] Triggering and gating to the pulses from the LINAC during imaging would also improve the signal to noise ratio (SNR) of the images. [20][21] Among other methods to reduce the angular dependency of the Cherenkov light in high-energy X-rays, 2,8,19 adding fluorescent dyes to the water is a useful approach.…”

Patch-Based U-Net Model for Isotropic Quantitative Differential Phase Contrast Imaging

“…The U-net model has been often utilized in image transformation as an alternative method for inverse problems [25][26][27]. U-net has already been considered as one of the most useful architectures for biomedical imaging [28].…”

Deep learning-based in vivo dose verification from proton-induced secondary-electron-bremsstrahlung images with various count level

“…To overcome these limitations of the SEB imaging, we have applied a deep learning (DL) approach to the dose distribution prediction from the measured SEB images for carbon-ions in the previous study [23]. The predicted images by the DL approach showed a good agreement with dose distributions of carbon-ions [23].…”

“…To overcome these limitations of the SEB imaging, we have applied a deep learning (DL) approach to the dose distribution prediction from the measured SEB images for carbon-ions in the previous study [23]. The predicted images by the DL approach showed a good agreement with dose distributions of carbon-ions [23]. However, the DL approach was applied for only SEB images of carbon-ions and it was not clear whether this approach can be applied to SEB images of protons.…”