Translator Disclaimer
1 March 2019 Image quality improvement in cone-beam CT using deep learning
Author Affiliations +
We propose a learning method to generate corrected CBCT (CCBCT) images with the goal of improving the image quality and clinical utility of on-board CBCT. The proposed method integrated a residual block concept into a cyclegenerative adversarial network (cycle-GAN) framework, which is named as Res-cycle GAN in this study. Compared with a GAN, a cycle-GAN includes an inverse transformation from CBCT to CT images, which could further constrain the learning model. A fully convolution neural network (FCN) with residual block is used in generator to enable end-toend transformation. A FCN is used in discriminator to discriminate from planning CT (ground truth) and correction CBCT (CCBCT) generated by the generator. This proposed algorithm was evaluated using 12 sets of patient data with CBCT and CT images. The mean absolute error (MAE), peak signal-to-noise ratio (PSNR), normalized cross correlation (NCC) indexes and spatial non-uniformity (SNU) in the selected regions of interests (ROIs) were used to quantify the correction accuracy of the proposed algorithm. Overall, the MAE, PSNR, NCC and SNU were 20.8±3.4 HU, 32. 8±1.5 dB, 0.986±0.004 and 1.7±3.6%. We have developed a novel deep learning-based method to generate CCBCT with a high image quality. The proposed method increases on-board CBCT image quality, making it comparable to that of the planning CT. With further evaluation and clinical implementation, this method could lead to quantitative adaptive radiotherapy.
Conference Presentation
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yang Lei, Tonghe Wang, Joseph Harms, Ghazal Shafai-Erfani, Xue Dong, Jun Zhou, Pretesh Patel, Xiangyang Tang, Tian Liu, Walter J. Curran, Kristin Higgins, and Xiaofeng Yang "Image quality improvement in cone-beam CT using deep learning", Proc. SPIE 10948, Medical Imaging 2019: Physics of Medical Imaging, 1094827 (1 March 2019);

Back to Top