Conditioning 3D Diffusion Models with 2D Images: Towards Standardized OCT Volumes through En Face-Informed Super-Resolution

TL;DR

This paper introduces a method to standardize OCT volumes by conditioning 3D diffusion models with 2D en face SLO images, improving structural coherence and reducing hallucinations in generated volumes.

Contribution

The study presents a novel approach to enhance OCT volume standardization using 2D SLO data with 3D diffusion models, outperforming traditional interpolation methods.

Findings

Outperforms tricubic interpolation in perceptual metrics

Improves structural coherence in OCT volumes

Reduces hallucinations in generated images

Abstract

High anisotropy in volumetric medical images can lead to the inconsistent quantification of anatomical and pathological structures. Particularly in optical coherence tomography (OCT), slice spacing can substantially vary across and within datasets, studies, and clinical practices. We propose to standardize OCT volumes to less anisotropic volumes by conditioning 3D diffusion models with en face scanning laser ophthalmoscopy (SLO) imaging data, a 2D modality already commonly available in clinical practice. We trained and evaluated on data from the multicenter and multimodal MACUSTAR study. While upsampling the number of slices by a factor of 8, our method outperforms tricubic interpolation and diffusion models without en face conditioning in terms of perceptual similarity metrics. Qualitative results demonstrate improved coherence and structural similarity. Our approach allows for better informed generative decisions, potentially reducing hallucinations. We hope this work will provide the next step towards standardized high-quality volumetric imaging, enabling more consistent quantifications.