ROIsGAN: A Region Guided Generative Adversarial Framework for Murine Hippocampal Subregion Segmentation

2025-05-15

AI Summary

Existing methods struggle to automatically segment mouse hippocampal subregions (DG, CA1, CA3) in immunohistochemistry (IHC) images, hindering neuroscience and disease mechanism studies. To address this, we introduce ROIsGAN—a region-guided U-Net–GAN hybrid framework—and establish the first four multimodal IHC datasets specifically for hippocampal subregion segmentation. ROIsGAN incorporates a region-aware discriminator and a fused Dice–BCE loss function to jointly model tissue architecture, neural activity, and synaptic plasticity features. On DG/CA1/CA3 segmentation tasks, ROIsGAN achieves 1–10% higher Dice scores and up to 11% improvement in IoU over state-of-the-art models. It demonstrates robust performance under low-contrast and non-standard staining conditions. This work fills a critical technical gap by enabling fully automated, accurate segmentation of hippocampal subregions in IHC images—advancing quantitative neurohistopathology and translational neuroscience research.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

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 {Delta}FosB 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

Problem

• Automated segmentation of hippocampal subregions from IHC images
• Lack of existing methods for precise subregion boundary delineation
• Need for scalable high-precision analysis in neuroscience research

Innovation

• Region-guided U-Net-based GAN for segmentation
• Novel region-guided discriminator loss function
• Comprehensive murine hippocampal IHC datasets