Résumé
Clinical applications of cone-beam breast CT(CBBCT) are hindered by relatively higher radiation dose and longer scan time. This study proposes sparse-view CBBCT, i.e. with a small number of projections, to overcome the above bottlenecks. A deep learning method - conditional generative adversarial network constrained by image edges (ECGAN) - is proposed to suppress artifacts on sparse-view CBBCT images reconstructed by filtered backprojection (FBP). The discriminator of the ECGAN is the combination of patchGAN and LSGAN for preserving high frequency information, with a modified U-net as the generator. To further preserve subtle structures and micro calcifications which are particularly important for breast cancer screening and diagnosis, edge images of CBBCT are added to both the generator and the discriminator to guide the learning. The proposed algorithm has been evaluated on 20 clinical raw datasets of CBBCT. ECGAN substantially improves the image qualities of sparse-view CBBCT, with a performance superior to those of total variation (TV) based iterative reconstruction and FBPConvNet based post-processing. On one CBBCT case with the projection number reduced from 300 to 100, ECGAN enhances peak-signal-to-noise ratio (PSNR) and structural similarity (SSIM) on FBP reconstruction from 24.26 and 0.812 to 37.78 and 0.963, respectively. These results indicate that ECGAN successfully reduces radiation dose and scan time of CBBCT by 1/3 with only small image degradations.