Retinal OCT Synthesis with Denoising Diffusion Probabilistic Models for Layer Segmentation

arXiv (Cornell University)

Abstract

Modern biomedical image analysis using deep learning often encounters the challenge of limited annotated data. To overcome this issue, deep generative models can be employed to synthesize realistic biomedical images. In this regard, we propose an image synthesis method that utilizes denoising diffusion probabilistic models (DDPMs) to automatically generate retinal optical coherence tomography (OCT) images. By providing rough layer sketches, the trained DDPMs can generate realistic circumpapillary OCT images. We further find that more accurate pseudo labels can be obtained through knowledge adaptation, which greatly benefits the segmentation task. Through this, we observe a consistent improvement in layer segmentation accuracy, which is validated using various neural networks. Furthermore, we have discovered that a layer segmentation model trained solely with synthesized images can achieve comparable results to a model trained exclusively with real images. These findings demonstrate the promising potential of DDPMs in reducing the need for manual annotations of retinal OCT images.

Authors 8

1. Yuli Wu Aachen Institute of Imaging & Computer Vision

   RWTH Aachen University

   Affiliation as printed

   Institute of Imaging and Computer Vision , RWTH Aachen University , Aachen , Germany

2. Weidong He Aachen Institute of Imaging & Computer Vision

   Tsinghua–Berkeley Shenzhen Institute · RWTH Aachen University · Tsinghua University

   Affiliation as printed

   Bio-manufacturing Engineering Laboratory of Tsinghua SIGS , Tsinghua University , Shenzhen , China

   Institute of Imaging and Computer Vision , RWTH Aachen University , Aachen , Germany

3. Dennis Eschweiler Aachen Institute of Imaging & Computer Vision

   RWTH Aachen University

   Affiliation as printed

   Institute of Imaging and Computer Vision , RWTH Aachen University , Aachen , Germany

4. Ningxin Dou

   ShenZhen People’s Hospital · He Eye Hospital

   Affiliation as printed

   Shenzhen Eye Hospital , Shenzhen , China

5. Zixin Fan

   ShenZhen People’s Hospital · He Eye Hospital

   Affiliation as printed

   Shenzhen Eye Hospital , Shenzhen , China

6. Shengli Mi

   Tsinghua–Berkeley Shenzhen Institute · Tsinghua University

   Affiliation as printed

   Bio-manufacturing Engineering Laboratory of Tsinghua SIGS , Tsinghua University , Shenzhen , China

7. Peter Walter Aachen Department of Ophthalmology

   RWTH Aachen University

   Affiliation as printed

   Department of Ophthalmology , RWTH Aachen University , Aachen , Germany

8. Johannes Stegmaier Aachen Institute of Imaging & Computer Vision

   RWTH Aachen University

   Affiliation as printed

   Institute of Imaging and Computer Vision , RWTH Aachen University , Aachen , Germany