Automated Quantitative Assessment of Elastic Fibers in Verhoeff-Van Gieson-Stained Mouse Aorta Histological Images
Lefebvre, A. E. Y. T.-S.; Mullis, M.
Show abstract
The mechanical resilience of the aortic wall hinges on the organisation of its concentric elastic laminae, yet histological evaluation of these fibers remains largely qualitative and observer-dependent. We present a fully automated, stain-aware pipeline that transforms Verhoeff-Van Gieson (VVG) whole-slide images of mouse aortae into reproducible, quantitative maps of elastic-fiber architecture. Leveraging optical-density deconvolution to disentangle elastin from collagen, the workflow couples multi-resolution processing with graph-based skeletonisation to preserve gigapixel detail while scaling efficiently. It returns pixel-level measurements of fiber thickness, tortuosity, lamina count and network complexity, together with validation snapshots for transparent quality control. By eliminating observer bias and delivering high-throughput morphometry, our framework enables powered genotype-phenotype screens in genetically diverse mouse populations and provides objective read-outs for interventions aimed at preserving matrix integrity. The modular codebase is open-source, readily extendable to other elastin-rich tissues or stains, and forms a bridge between qualitative microscopy and biomechanical phenotyping--setting the stage for large-scale, data-driven exploration of vascular structure-function relationships.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- A tool for federated training of segmentation models on whole slide images. 94%
- Independent assessment of a deep learning system for lymph node metastasis detection on the Augmented Reality Microscope 93%
- Deep Learning Based Registration of Serial Whole-slide Histopathology Images in Different Stains 92%
Similar papers in this journal
Similar papers in this journal
- NISNet3D: Three-Dimensional Nuclear Synthesis and Instance Segmentation for Fluorescence Microscopy Images 94%
- Generating synthetic data in digital pathology through diffusion models: a multifaceted approach to evaluation 93%
- OrgaQuant: Intestinal Organoid Localization and Quantification Using Deep Convolutional Neural Networks 93%
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.