Heatmap Guided Query Transformers for Robust Astrocyte Detection across Immunostains and Resolutions

2025/09/03 by Xiaolu Zhang, Zhang, Xizhe, Zhu, Jiayang
Biochemistry, Genetics and Molecular Biology · Computer Science · #Artificial Intelligence (cs.AI) #Cell Image Analysis Techniques #Computer Vision and Pattern Recognition (cs.CV) #Digital Imaging for Blood Diseases #FOS: Computer and information sciences #Single-cell and spatial transcriptomics

paper · pdf · doi:10.48550/arxiv.2509.03323

openalex publication_date 2025/09/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Astrocytes are critical glial cells whose altered morphology and density are hallmarks of many neurological disorders. However, their intricate branching and stain dependent variability make automated detection of histological images a highly challenging task. To address these challenges, we propose a hybrid CNN Transformer detector that combines local feature extraction with global contextual reasoning. A heatmap guided query mechanism generates spatially grounded anchors for small and faint astrocytes, while a lightweight Transformer module improves discrimination in dense clusters. Evaluated on ALDH1L1 and GFAP stained astrocyte datasets, the model consistently outperformed Faster R-CNN, YOLOv11 and DETR, achieving higher sensitivity with fewer false positives, as confirmed by FROC analysis. These results highlight the potential of hybrid CNN Transformer architectures for robust astrocyte detection and provide a foundation for advanced computational pathology tools.

Citations

• RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervision
• DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR
• Reactive astrocyte nomenclature, definitions, and future directions
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Deformable DETR: Deformable Transformers for End-to-End Object Detection
• End-to-End Object Detection with Transformers
• Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
• Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
• CenterNet: Keypoint Triplets for Object Detection
• Generalized Intersection over Union: A Metric and A Loss for Bounding\n Box Regression
• Attention Is All You Need
• Soft-NMS -- Improving Object Detection With One Line of Code
• Feature Pyramid Networks for Object Detection
• Deep Residual Learning for Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal\n Networks
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Astrocytes: biology and pathology
• Molecular dissection of reactive astrogliosis and glial scar formation

Related

• FDNet: Frequency Domain Denoising Network For Cell Segmentation in Astrocytes Derived From Induced Pluripotent Stem Cells
• CE-RS-SBCIT A Novel Channel Enhanced Hybrid CNN Transformer with Residual, Spatial, and Boundary-Aware Learning for Brain Tumor MRI Analysis
• Delving Deeper Into Astromorphic Transformers
• Comprehensive benchmarking of deep learning approaches for automated astrocyte segmentation in traumatic brain injury
• How GNNs Facilitate CNNs in Mining Geometric Information from Large-Scale Medical Images