Unsupervised Domain Adaptation for Neuron Membrane Segmentation based on Structural Features
This work addresses the domain gap issue in medical image analysis for neuroinformatics, offering an incremental improvement over existing UDA methods.
The paper tackled the problem of limited generalization in neuron membrane segmentation across different electron microscopy image domains by proposing an unsupervised domain adaptation method with structural feature considerations, achieving improved performance as indicated by extensive experiments on two applications.
AI-enhanced segmentation of neuronal boundaries in electron microscopy (EM) images is crucial for automatic and accurate neuroinformatics studies. To enhance the limited generalization ability of typical deep learning frameworks for medical image analysis, unsupervised domain adaptation (UDA) methods have been applied. In this work, we propose to improve the performance of UDA methods on cross-domain neuron membrane segmentation in EM images. First, we designed a feature weight module considering the structural features during adaptation. Second, we introduced a structural feature-based super-resolution approach to alleviating the domain gap by adjusting the cross-domain image resolutions. Third, we proposed an orthogonal decomposition module to facilitate the extraction of domain-invariant features. Extensive experiments on two domain adaptive membrane segmentation applications have indicated the effectiveness of our method.