Inpainting Truncated Areas of CT Images Based On Generative Adversarial Networks with Gated Convolution for Radiotherapy
X Kai1,2*, X Qianyi2,3, G Liugang1,2, J Sun1,2, C Qian1,2, N Xinye1,2,3, (1) The Affiliated Changzhou NO.2 People's Hospital of Nanjing Medical University, Changzhou, Jiang Su, CN, (2) Jiangsu Province Engineering Research Center of Medical Physics, Changzhou, Jiangsu, CN,(3) Center for Medical Physics, Nanjing Medical University, Changzhou, Jiangsu, CN
Presentations
PO-GePV-M-327 (Sunday, 7/10/2022) [Eastern Time (GMT-4)]
ePoster Forums
Purpose: This study aimed to inpaint the truncated areas of CT images by using generative adversarial networks with gated convolution (GatedConv) and apply these images to dose calculations in radiotherapy.
Methods: CT images were collected from 100 patients with esophageal cancer under thermoplastic membrane placement, and 85 cases were used for training based on randomly generated circle masks. In the prediction stage, 15 cases of data were used to evaluate the accuracy of the inpainted CT in anatomy and dosimetry based on the mask with truncated volume covering 40% of the arm volume, and they were compared with the inpainted CT synthesized by U-Net, pix2pix, and PConv with partial convolution.
Results: The results showed that GatedConv could directly and effectively inpaint the incomplete CT images in the image domain. For the results of U-Net, pix2pix, PConv, and GatedConv, the mean absolute errors for the truncated tissue were 195.54, 196.20, 190.40, and 158.45 HU, respectively. The mean dose of the planning target volume, heart, and lung in the truncated CT was statistically different (p<0.05) from those of the ground truth CT (CTgt). The differences in dose distribution between the inpainted CT obtained by the four models and CTgt were minimal. The inpainting effect of clinical truncated CT images based on GatedConv showed better stability compared with the other models.
Conclusion: GatedConv can effectively inpaint the truncated areas with high image quality, and it is closer to CTgt in terms of image visualization and dosimetry than other inpainting models.
Funding Support, Disclosures, and Conflict of Interest: This work is supported by Changzhou Sci&Tech Program (No. CJ20210128 and CJ20200099), General Program of Jiangsu Provincial Health Commission (No. M2020006), Changzhou Key Laboratory of Medical Physics (No. CM20193005).
Keywords
CT, Image Processing, Radiation Dosimetry
Taxonomy
IM- CT: Machine learning, computer vision
Contact Email