Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN

• URL: http://arxiv.org/abs/2008.01910v4
• Date: Mon, 12 Sep 2022 17:04:07 GMT
• Title: Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN
• Authors: Li Sun, Junxiang Chen, Yanwu Xu, Mingming Gong, Ke Yu, Kayhan Batmanghelich
• Abstract summary: We propose a novel end-to-end GAN architecture that can generate high-resolution 3D images. We achieve this goal by using different configurations between training and inference. Experiments on 3D thorax CT and brain MRI demonstrate that our approach outperforms state of the art in image generation.
• Score: 52.851990439671475
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative Adversarial Networks (GAN) have many potential medical imaging applications, including data augmentation, domain adaptation, and model explanation. Due to the limited memory of Graphical Processing Units (GPUs), most current 3D GAN models are trained on low-resolution medical images, these models either cannot scale to high-resolution or are prone to patchy artifacts. In this work, we propose a novel end-to-end GAN architecture that can generate high-resolution 3D images. We achieve this goal by using different configurations between training and inference. During training, we adopt a hierarchical structure that simultaneously generates a low-resolution version of the image and a randomly selected sub-volume of the high-resolution image. The hierarchical design has two advantages: First, the memory demand for training on high-resolution images is amortized among sub-volumes. Furthermore, anchoring the high-resolution sub-volumes to a single low-resolution image ensures anatomical consistency between sub-volumes. During inference, our model can directly generate full high-resolution images. We also incorporate an encoder with a similar hierarchical structure into the model to extract features from the images. Experiments on 3D thorax CT and brain MRI demonstrate that our approach outperforms state of the art in image generation. We also demonstrate clinical applications of the proposed model in data augmentation and clinical-relevant feature extraction.

Related papers

• URCDM: Ultra-Resolution Image Synthesis in Histopathology [4.393805955844748]
  Ultra-Resolution Cascaded Diffusion Models (URCDMs) are capable of synthesising entire histopathology images at high resolutions. We evaluate our method on three separate datasets, consisting of brain, breast and kidney tissue. URCDMs consistently generate outputs across various resolutions that trained evaluators cannot distinguish from real images.
  arXiv  Detail & Related papers  (2024-07-18T08:31:55Z)
• Inter-slice Super-resolution of Magnetic Resonance Images by Pre-training and Self-supervised Fine-tuning [49.197385954021456]
  In clinical practice, 2D magnetic resonance (MR) sequences are widely adopted. While individual 2D slices can be stacked to form a 3D volume, the relatively large slice spacing can pose challenges for visualization and subsequent analysis tasks. To reduce slice spacing, deep-learning-based super-resolution techniques are widely investigated. Most current solutions require a substantial number of paired high-resolution and low-resolution images for supervised training, which are typically unavailable in real-world scenarios.
  arXiv  Detail & Related papers  (2024-06-10T02:20:26Z)
• Memory-efficient High-resolution OCT Volume Synthesis with Cascaded Amortized Latent Diffusion Models [48.87160158792048]
  We introduce a cascaded amortized latent diffusion model (CA-LDM) that can synthesis high-resolution OCT volumes in a memory-efficient way. Experiments on a public high-resolution OCT dataset show that our synthetic data have realistic high-resolution and global features, surpassing the capabilities of existing methods.
  arXiv  Detail & Related papers  (2024-05-26T10:58:22Z)
• ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models [126.35334860896373]
  We investigate the capability of generating images from pre-trained diffusion models at much higher resolutions than the training image sizes. Existing works for higher-resolution generation, such as attention-based and joint-diffusion approaches, cannot well address these issues. We propose a simple yet effective re-dilation that can dynamically adjust the convolutional perception field during inference.
  arXiv  Detail & Related papers  (2023-10-11T17:52:39Z)
• MedSyn: Text-guided Anatomy-aware Synthesis of High-Fidelity 3D CT Images [22.455833806331384]
  This paper introduces an innovative methodology for producing high-quality 3D lung CT images guided by textual information. Current state-of-the-art approaches are limited to low-resolution outputs and underutilize radiology reports' abundant information.
  arXiv  Detail & Related papers  (2023-10-05T14:16:22Z)
• Memory-Efficient 3D Denoising Diffusion Models for Medical Image Processing [0.9424565541639366]
  We present a number of ways to reduce the resource consumption for 3D diffusion models. The main contribution of this paper is the memory-efficient patch-based diffusion model. While the proposed diffusion model can be applied to any image generation tasks, we evaluate the method on the tumor segmentation task of the BraTS 2020 dataset.
  arXiv  Detail & Related papers  (2023-03-27T15:10:19Z)
• SOUP-GAN: Super-Resolution MRI Using Generative Adversarial Networks [9.201328999176402]
  We propose a framework called SOUP-GAN: Super-resolution Optimized Using Perceptual-tuned Generative Adversarial Network (GAN) Our model shows promise as a novel 3D SR technique, providing potential applications in both clinical and research settings.
  arXiv  Detail & Related papers  (2021-06-04T16:59:23Z)
• Modelling the Distribution of 3D Brain MRI using a 2D Slice VAE [66.63629641650572]
  We propose a method to model 3D MR brain volumes distribution by combining a 2D slice VAE with a Gaussian model that captures the relationships between slices. We also introduce a novel evaluation method for generated volumes that quantifies how well their segmentations match those of true brain anatomy.
  arXiv  Detail & Related papers  (2020-07-09T13:23:15Z)
• Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond [62.730497582218284]
  We develop a new deep learning based framework to optimize a diffeomorphic model via multi-scale propagation. We conduct two groups of image registration experiments on 3D volume datasets including image-to-atlas registration on brain MRI data and image-to-image registration on liver CT data.
  arXiv  Detail & Related papers  (2020-04-30T03:23:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.