Noise transfer for unsupervised domain adaptation of retinal OCT images
This addresses domain adaptation for retinal OCT imaging, enabling more accurate machine learning models across devices, but it is incremental as it builds on existing noise-based and domain adaptation techniques.
The paper tackles the problem of domain shift in retinal OCT images from different devices, which reduces model accuracy, by introducing a minimal noise adaptation method (SVDNA) that uses noise structure differences to bridge the domain gap; it demonstrates that SVDNA compares or outperforms state-of-the-art unsupervised domain adaptation methods for semantic segmentation on a public OCT dataset.
Optical coherence tomography (OCT) imaging from different camera devices causes challenging domain shifts and can cause a severe drop in accuracy for machine learning models. In this work, we introduce a minimal noise adaptation method based on a singular value decomposition (SVDNA) to overcome the domain gap between target domains from three different device manufacturers in retinal OCT imaging. Our method utilizes the difference in noise structure to successfully bridge the domain gap between different OCT devices and transfer the style from unlabeled target domain images to source images for which manual annotations are available. We demonstrate how this method, despite its simplicity, compares or even outperforms state-of-the-art unsupervised domain adaptation methods for semantic segmentation on a public OCT dataset. SVDNA can be integrated with just a few lines of code into the augmentation pipeline of any network which is in contrast to many state-of-the-art domain adaptation methods which often need to change the underlying model architecture or train a separate style transfer model. The full code implementation for SVDNA is available at https://github.com/ValentinKoch/SVDNA.