提出ROIsGAN模型，实现小鼠海马亚区高精度自动分割。
ROIsGAN: A Region Guided Generative Adversarial Framework for Murine Hippocampal Subregion Segmentation
- 基于区域引导的生成对抗网络，结合Dice与交叉熵损失提升边界精度。
- 在三种亚区上平均提升1-10%的Dice分数，挑战性染色下最高增11% IoU。
- 开源数据集与代码，适合神经科学组织图像分析研究者使用。
海马体是参与记忆处理及多种神经退行性和精神疾病的关键脑结构，包含齿状回（DG）、CA1和CA3三个重要亚区。从组织学切片图像中精确分割这些亚区对理解疾病机制、发育动态和治疗干预至关重要。然而，现有方法尚未解决从组织切片图像（尤其是免疫组化，IHC）中自动化分割海马亚区的问题。为此，我们构建了四套完整的啮齿类海马组织学IHC数据集，涵盖cFos、NeuN以及结合ΔFosB或GAD67的多重染色，捕捉结构、神经元活动和可塑性相关信息。同时，提出ROIsGAN——一种面向海马亚区分割的区域引导式U-Net生成对抗网络。通过对抗学习，利用融合Dice与二值交叉熵的区域引导判别器损失，增强边界划分与结构细节优化。在DG、CA1、CA3三个亚区上的评估显示，该模型持续优于传统分割方法，Dice分数提升1-10%，交并比（IoU）最高提升11%，尤其在困难染色条件下表现突出。本工作建立了海马自动分割的基础数据集与方法，支持神经科学研究中组织图像的可扩展高精度分析。所有生成数据集、模型及源代码已公开：https://github.com/MehediAzim/ROIsGAN
原文摘要 · Abstract (English)
The hippocampus, a critical brain structure involved in memory processing and various neurodegenerative and psychiatric disorders, comprises three key subregions: the dentate gyrus (DG), Cornu Ammonis 1 (CA1), and Cornu Ammonis 3 (CA3). Accurate segmentation of these subregions from histological tissue images is essential for advancing our understanding of disease mechanisms, developmental dynamics, and therapeutic interventions. However, no existing methods address the automated segmentation of hippocampal subregions from tissue images, particularly from immunohistochemistry (IHC) images. To bridge this gap, we introduce a novel set of four comprehensive murine hippocampal IHC datasets featuring distinct staining modalities: cFos, NeuN, and multiplexed stains combining cFos, NeuN, and either ΔFosB or GAD67, capturing structural, neuronal activity, and plasticity associated information. Additionally, we propose ROIsGAN, a region-guided U-Net-based generative adversarial network tailored for hippocampal subregion segmentation. By leveraging adversarial learning, ROIsGAN enhances boundary delineation and structural detail refinement through a novel region-guided discriminator loss combining Dice and binary cross-entropy loss. Evaluated across DG, CA1, and CA3 subregions, ROIsGAN consistently outperforms conventional segmentation models, achieving performance gains ranging from 1-10% in Dice score and up to 11% in Intersection over Union (IoU), particularly under challenging staining conditions. Our work establishes foundational datasets and methods for automated hippocampal segmentation, enabling scalable, high-precision analysis of tissue images in neuroscience research. Our generated datasets, proposed model as a standalone tool, and its corresponding source code are publicly available at: https://github.com/MehediAzim/ROIsGAN
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。