Image translation of Ultrasound to Pseudo Anatomical Display by CycleGAN
Lilach Barkat, Moti Freiman, Haim Azhari

TL;DR
This paper demonstrates that CycleGAN can translate ultrasound images into pseudo anatomical displays, improving lesion visualization and aiding diagnosis without paired training data.
Contribution
The study introduces a novel application of CycleGAN for ultrasound image translation into anatomical-like images, enhancing interpretability and diagnostic potential.
Findings
Generated images show clearer lesion borders and higher contrast.
Quantitative metrics indicate high preservation of anatomical features.
Improved lesion segmentation accuracy demonstrated.
Abstract
Ultrasound is the second most used modality in medical imaging. It is cost effective, hazardless, portable and implemented routinely in numerous clinical procedures. Nonetheless, image quality is characterized by granulated appearance, poor SNR and speckle noise. Specific for malignant tumors, the margins are blurred and indistinct. Thus, there is a great need for improving ultrasound image quality. We hypothesize that this can be achieved, using neural networks, by translation into a more realistic display which mimics an anatomical cut through the tissue. In order to achieve this goal, the preferable approach would be to use a set of paired images. However, this is practically impossible in our case. Therefore, Cycle Generative Adversarial Network (CycleGAN) was used, in order to learn each domain properties separately and enforce cross domain cycle consistency. The two datasets which…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAI in cancer detection · Radiomics and Machine Learning in Medical Imaging · Advanced Image Processing Techniques
Methods*Communicated@Fast*How Do I Communicate to Expedia? · Instance Normalization · Convolution · HuMan(Expedia)||How do I get a human at Expedia? · Tanh Activation · PatchGAN · Sigmoid Activation · Cycle Consistency Loss · GAN Least Squares Loss · Batch Normalization
