mlsanityData to 7 Oct 2026

Constrained CycleGAN for Effective Generation of Ultrasound Sector Images of Improved Spatial Resolution

arXiv 2309.00995 ↗First posted 2 Sep 2023eess.IV cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Objective. A phased or a curvilinear array produces ultrasound (US) images with a sector field of view (FOV), which inherently exhibits spatially-varying image resolution with inferior quality in the far zone and towards the two sides azimuthally. Sector US images with improved spatial resolutions are favorable for accurate quantitative analysis of large and dynamic organs, such as the heart. Therefore, this study aims to translate US images with spatially-varying resolution to ones with less spatially-varying resolution. CycleGAN has been a prominent choice for unpaired medical image translation; however, it neither guarantees structural consistency nor preserves backscattering patterns between input and generated images for unpaired US images. Approach. To circumvent this limitation, we propose a constrained CycleGAN (CCycleGAN), which directly performs US image generation with unpaired images acquired by different ultrasound array probes. In addition to conventional adversarial and cycle-consistency losses of CycleGAN, CCycleGAN introduces an identical loss and a correlation coefficient loss based on intrinsic US backscattered signal properties to constrain structural consistency and backscattering patterns, respectively. Instead of post-processed B-mode images, CCycleGAN uses envelope data directly obtained from beamformed radio-frequency signals without any other non-linear postprocessing. Main Results. In vitro phantom results demonstrate that CCycleGAN successfully generates images with improved spatial resolution as well as higher peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) compared with benchmarks. Significance. CCycleGAN-generated US images of the in vivo human beating heart further facilitate higher quality heart wall motion estimation than benchmarks-generated ones, particularly in deep regions.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 76 references that are in the map. First posted on arXiv 2 Sep 2023.

Builds on

17 of 76 references.

References · 17

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  6. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  7. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  8. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  9. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  10. 2018Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networkscited by 133
  11. 2018Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-Consistency Generative Adversarial Networkcited by 97
  12. 2017Deep MR to CT Synthesis using Unpaired Datacited by 86
5 more
  1. 2017Perceptual Adversarial Networks for Image-to-Image Transformationcited by 42
  2. 2018Unpaired Brain MR-to-CT Synthesis using a Structure-Constrained CycleGANcited by 31
  3. 2018Cycle Consistent Adversarial Denoising Network for Multiphase Coronary CT Angiographycited by 23
  4. 2017Simulating Patho-realistic Ultrasound Images using Deep Generative Networks with Adversarial Learningcited by 13
  5. 2020Perception Consistency Ultrasound Image Super-resolution via Self-supervised CycleGANcited by 6

Built on by

Not cited yet.