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

Source: [Memory-efficient High-resolution OCT Volume Synthesis with Cascaded Amortized Latent Diffusion Models](<https://www.sota2.com/research/paper/68fa734d1e209131cea5ba6f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-02T05:59:49.089Z

Authors: Kun Huang, Xiao Ma, Yuhan Zhang, Na Su, Songtao Yuan, Yong Liu, Qiang Chen, Huazhu Fu

Published: 2024-05-26T10:58:22.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D OCT Volume Synthesis on OCTA-500 (test)](<https://www.sota2.com/research/sota/3d-oct-volume-synthesis-on-octa-500-test.md>): 3D OCT Volume Synthesis; OCTA-500 (test); Intra-FID: 17.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2405.16516>)

[PDF](<https://arxiv.org/pdf/2405.16516.pdf>)

[Implementation](<https://github.com/nicetomeetu21/CA-LDM>)