English

Memory-efficient High-resolution OCT Volume Synthesis with Cascaded Amortized Latent Diffusion Models

Image and Video Processing 2024-05-28 v1 Computer Vision and Pattern Recognition

Abstract

Optical coherence tomography (OCT) image analysis plays an important role in the field of ophthalmology. Current successful analysis models rely on available large datasets, which can be challenging to be obtained for certain tasks. The use of deep generative models to create realistic data emerges as a promising approach. However, due to limitations in hardware resources, it is still difficulty to synthesize high-resolution OCT volumes. In this paper, we introduce a cascaded amortized latent diffusion model (CA-LDM) that can synthesis high-resolution OCT volumes in a memory-efficient way. First, we propose non-holistic autoencoders to efficiently build a bidirectional mapping between high-resolution volume space and low-resolution latent space. In tandem with autoencoders, we propose cascaded diffusion processes to synthesize high-resolution OCT volumes with a global-to-local refinement process, amortizing the memory and computational demands. 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. Moreover, performance gains on two down-stream fine-grained segmentation tasks demonstrate the benefit of the proposed method in training deep learning models for medical imaging tasks. The code is public available at: https://github.com/nicetomeetu21/CA-LDM.

Keywords

Cite

@article{arxiv.2405.16516,
  title  = {Memory-efficient High-resolution OCT Volume Synthesis with Cascaded Amortized Latent Diffusion Models},
  author = {Kun Huang and Xiao Ma and Yuhan Zhang and Na Su and Songtao Yuan and Yong Liu and Qiang Chen and Huazhu Fu},
  journal= {arXiv preprint arXiv:2405.16516},
  year   = {2024}
}

Comments

Provisionally accepted for medical image computing and computer-assisted intervention (MICCAI) 2024

R2 v1 2026-06-28T16:40:44.178Z