Rethinking Data Augmentation for Single-Source Domain Generalization in OCT Image Segmentation

Domain shifts between samples acquired with different instruments are one of the major challenges in accurate segmentation of Optical Coherence Tomography (OCT) images. Given that OCT images may be acquired with different devices in different clinical centers, this study presents astyle and structure data augmentation (SSDA) method to improve the adaptability of segmentation models. Inspired by our initial analysis of OCT domain differences, we propose an innovative hypothesis that domain shifts are primarily due to differences in image style and anatomical structure, which further guides the design of our method. By designing a modality-specific NURBS curve for style enhancement and implementing global and local elastic deformation fields, SSDA addresses both stylistic and structural variations in OCT data. Global deformations simulate changes in retinal curvature, while local deformations model layer-specific changes observed in OCT images. We validate our hypothesis through a comprehensive evaluation conducted on five OCT data domains, each differing in device type and imaging conditions. We train models on each of these domains for single-domain generalisation experiments and evaluate performance on the remaining unseen domains. The results show that SSDA outperforms existing methods when segmenting OCT images from different sources with different requirements for retinal layer segmentation. Specifically, across five different source domain generalisation experiments, SSDA achieves approximately 1. 6% higher Dice and 2. 6% improved MIOU, underscoring its superior segmentation accuracy and robust generalisation across all evaluated unseen domains.

Authors

• Jiayi Lu
• Shaodong Ma
• Yonghuai Liu
• Yuhui Ma
• Lei Mou
• Yang Jiang
• Yitian Zhao Cixi Institute of Biomedical Engineering, Ningbo Institute of Industrial Technology, Chinese Academy of Sciences

Keywords

• Retina
• Image segmentation
• Imaging
• Training
• Data augmentation
• Deformation
• Noise
• Image resolution
• Bioinformatics
• Performance evaluation
• Optical Coherence Tomography Images
• Domain Generalization
• Single-source Domain Generalization
• Local Changes
• Domain Shift
• Retinal Layer
• Segmentation Accuracy
• Elastic Deformation
• Change Curve
• Imaging Conditions
• Local Deformation
• Source Domain
• Differences In Styles
• Variety Of Styles
• Deformation Field
• Data Augmentation Methods
• Layer Segmentation
• Style Image
• Mean Intersection Over Union
• Unknown Domain
• Optical Coherence Tomography B-scans
• Retinal Structure
• Diabetic Macular Edema
• Target Domain
• Variation Curve
• Age-related Macular Degeneration
• Imaging Device
• Dice Score
• Retinal Structural Changes
• OCT layer segmentation
• domain shifts
• Tomography, Optical Coherence
• Humans
• Algorithms
• Image Processing, Computer-Assisted