NCCT-CECT image synthesizers and their application to pulmonary vessel segmentation

• Published in: Computer methods and programs in biomedicine 2023-04, Vol.231, p.107389-107389, Article 107389
• Main Authors: Pang, Haowen, Qi, Shouliang, Wu, Yanan, Wang, Meihuan, Li, Chen, Sun, Yu, Qian, Wei, Tang, Guoyan, Xu, Jiaxuan, Liang, Zhenyu, Chen, Rongchang
• Format: Article
• Language: English
• Subjects: Computed tomography; Generative adversarial network; Image Processing, Computer-Assisted - methods; Medical image synthesis; Pulmonary vessel segmentation; Signal-To-Noise Ratio; Thorax; Tomography, X-Ray Computed - methods
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2023.107389

•Two synthesizers are proposed for the mutual synthesis between NCCT and CECT.•Self-supervised learning and dual-energy CT are used to pretrain the synthesizers.•The synthesizers outperformed state-of-the-art methods.•The proposed synthesizers can help segment pulmonary vessels from NCCT images. Non-contrast CT (NCCT) and contrast-enhanced CT (CECT) are important diagnostic tools with distinct features and applications for chest diseases. We developed two synthesizers for the mutual synthesis of NCCT and CECT and evaluated their applications. Two synthesizers (S1 and S2) were proposed based on a generative adversarial network. S1 generated synthetic CECT (SynCECT) from NCCT and S2 generated synthetic NCCT (SynNCCT) from CECT. A new training procedure for synthesizers was proposed. Initially, the synthesizers were pretrained using self-supervised learning (SSL) and dual-energy CT (DECT) and then fine-tuned using the registered NCCT and CECT images. Pulmonary vessel segmentation from NCCT was used as an example to demonstrate the effectiveness of the synthesizers. Two strategies (ST1 and ST2) were proposed for pulmonary vessel segmentation. In ST1, CECT images were used to train a segmentation model (Model-CECT), NCCT images were converted to SynCECT through S1, and SynCECT was input to Model-CECT for testing. In ST2, CECT data were converted to SynNCCT through S2. SynNCCT and CECT-based annotations were used to train an additional model (Model-NCCT), and NCCT was input to Model-NCCT for testing. Three datasets, D1 (40 paired CTs), D2 (14 NCCTs and 14 CECTs), and D3 (49 paired DECTs), were used to evaluate the synthesizers and strategies. For S1, the mean absolute error (MAE), mean squared error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM) were 14.60± 2.19, 1644± 890, 34.34± 1.91, and 0.94± 0.02, respectively. For S2, they were 12.52± 2.59, 1460± 922, 35.08± 2.35, and 0.95± 0.02, respectively. Our synthesizers outperformed the counterparts of CycleGAN, Pix2Pix, and Pix2PixHD. The results of ablation studies on SSL pretraining, DECT pretraining, and fine-tuning showed that performance worsened (for example, for S1, MAE increased to 16.53± 3.10, 17.98± 3.10, and 20.57± 3.75, respectively). Model-NCCT and Model-CECT achieved dice similarity coefficients (DSC) of 0.77 and 0.86 on D1 and 0.77 and 0.72 on D2, respectively. The proposed synthesizers realized mutual and high-quality synthesis between NCCT and CECT images; the trai