Multi-Scale Texture Loss for CT denoising with GANs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908832442089472 |
|---|---|
| author | Di Feola, Francesco Tronchin, Lorenzo Guarrasi, Valerio Soda, Paolo |
| author_facet | Di Feola, Francesco Tronchin, Lorenzo Guarrasi, Valerio Soda, Paolo |
| contents | Generative Adversarial Networks (GANs) have proved as a powerful framework for denoising applications in medical imaging. However, GAN-based denoising algorithms still suffer from limitations in capturing complex relationships within the images. In this regard, the loss function plays a crucial role in guiding the image generation process, encompassing how much a synthetic image differs from a real image. To grasp highly complex and non-linear textural relationships in the training process, this work presents a novel approach to capture and embed multi-scale texture information into the loss function. Our method introduces a differentiable multi-scale texture representation of the images dynamically aggregated by a self-attention layer, thus exploiting end-to-end gradient-based optimization. We validate our approach by carrying out extensive experiments in the context of low-dose CT denoising, a challenging application that aims to enhance the quality of noisy CT scans. We utilize three publicly available datasets, including one simulated and two real datasets. The results are promising as compared to other well-established loss functions, being also consistent across three different GAN architectures. The code is available at: https://github.com/TrainLaboratory/MultiScaleTextureLoss-MSTLF |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_16640 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-Scale Texture Loss for CT denoising with GANs Di Feola, Francesco Tronchin, Lorenzo Guarrasi, Valerio Soda, Paolo Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Generative Adversarial Networks (GANs) have proved as a powerful framework for denoising applications in medical imaging. However, GAN-based denoising algorithms still suffer from limitations in capturing complex relationships within the images. In this regard, the loss function plays a crucial role in guiding the image generation process, encompassing how much a synthetic image differs from a real image. To grasp highly complex and non-linear textural relationships in the training process, this work presents a novel approach to capture and embed multi-scale texture information into the loss function. Our method introduces a differentiable multi-scale texture representation of the images dynamically aggregated by a self-attention layer, thus exploiting end-to-end gradient-based optimization. We validate our approach by carrying out extensive experiments in the context of low-dose CT denoising, a challenging application that aims to enhance the quality of noisy CT scans. We utilize three publicly available datasets, including one simulated and two real datasets. The results are promising as compared to other well-established loss functions, being also consistent across three different GAN architectures. The code is available at: https://github.com/TrainLaboratory/MultiScaleTextureLoss-MSTLF |
| title | Multi-Scale Texture Loss for CT denoising with GANs |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2403.16640 |