L0 norm improves brain CT to MR image synthesis accuracy
L0-Norm-Based CycleGAN for Unpaired Brain CT-to-MR Synthesis
Computer Vision and Pattern Recognition
Summary
Brain CT and MR images show different details but are not always both available for a patient. The authors improved a computer method that transforms CT images into MR images without paired scans using a special math trick called the L0 norm. This trick helps the method pay more attention to small differences and less to big errors, making the generated MR images closer to real ones. Their approach showed better accuracy compared to the usual method in tests with brain images.
What this means in practice
- •For medical image processing teams: Generate more accurate MR-like images from unpaired CT scans for improved brain analysis when MR imaging is unavailable.
- •For clinical software developers: Incorporate refined image translation techniques to enhance diagnostic tools that aid radiologists with complementary imaging modalities.
Authors
Yunxiao Zhang, Shouqiang Du, Zexian Xu, Chuanlong Xu
Abstract
Computed tomography (CT) and magnetic resonance (MR) imaging provide complementary information for the brain, but acquiring both modalities is not always possible. The cycle-consistent adversarial network (CycleGAN) enables unpaired CT-to-MR synthesis, but because the standard L1-norm cycle?consistency penalty grows linearly with the residual magnitude, the network tends to focus on large residuals. This paper introduces an L0-norm-based cycle?consistency term, in which the L0-norm is approximated by a smooth and bounded function. This approximation not only increases sensitivity to small residuals but also effectively suppresses the influence of large residuals. The proposed model and an otherwise identical L1-norm baseline were trained on 102 images and evaluated on 9 test images. The proposed model achieves a lower mean squared error (0.02746 versus 0.03464, a 20.7% reduction), a higher mean peak signal-to-noise ratio (15.80 versus 14.77 dB), and a higher mean structural similarity index (0.5689 versus 0.5407). It also has a lower maximum MSE and higher minimum PSNR and SSIM than the baseline. These results indicate that modifying the cycle-consistency penalty can improve reconstruction accuracy on this dataset.