GeNSeg-Net: A General Segmentation Framework for Any Nucleus in Immunohistochemistry Images

Siyuan Xu, Guannan Li, Haofei Song, Jiansheng Wang, Yan Wang, Qingli Li

Abstract: Immunohistochemistry (IHC) plays a crucial role in understanding disease mechanisms, diagnosing pathology and guiding treatment decisions. The precise analysis heavily depends on accurate nucleus segmentation. However, segmentation is challenging due to significant inter- and intra-nucleus variability in morphology and distribution, stemming from inherent characteristics, imaging techniques, tissue differences and other factors. While current deep learning-based methods have shown promising results, their generalization performance is limited, inevitably requiring specific training data. To address the problem, we propose a novel General framework for Nucleus Segmentation in IHC images (GeNSeg-Net). GeNSeg-Net effectively segments nuclei across diverse tissue types and imaging techniques with high variability using a small subset for training. It comprises an enhancement model and a segmentation model. Initially, all nuclei are enhanced to a uniform morphology with distinct features by the enhancement model through generation. The subsequent segmentation task is thereby simplified, leading to higher accuracy. We design a lightweight generator and discriminator to improve both enhancement quality and computational efficiency. Extensive experiments demonstrate the effectiveness of each component within GeNSeg-Net. Compared to existing methods, GeNSeg-Net achieves state-of-the-art (SOTA) segmentation accuracy and generalization performance on both private and public datasets, while maintaining highly competitive processing speed. Code will be available for research and clinical purposes.

Primary Subject Area: [Content] Media Interpretation

Secondary Subject Area: [Generation] Generative Multimedia

Relevance To Conference: Our work involves analyzing visual information in the multimedia domain. To be specific, we focus on the processing of pathological images. The paper introduces a novel nucleus segmentation method for any nucleus in immunohistochemistry images, offering innovative insights and methods for interpreting and exploring multimedia image content. Our study showcases the value and potential of generative networks in the processing of pathological images.

Submission Number: 431