.png){kind=icon}
.png){kind=icon}
Return
Histolytics: A Panoptic Spatial Analysis Framework for Interpretable Histopathology
.png){kind=icon}
OA
AI
DOI：10.1016/j.csbj.2025.11.022.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Quantifying spatial organization in hematoxylin and eosin (H&E)–stained whole-slide images (WSIs) is essential for uncovering tissue-level patterns relevant to pathology. We present Histolytics, an open-source, scalable Python framework for interpretable, WSI-scale histopathological analysis. Histolytics integrates panoptic segmentation with spatial querying, morphological profiling, and graph-based analytics to enable high-resolution, quantitative characterization of nuclei, tissue compartments, and the extracellular matrix (ECM). Designed to align with diagnostic reasoning, Histolytics supports segmentation with state-of-the-art deep learning models and provides modular tools for extracting biologically grounded features across entire WSIs. By leveraging spatially contextualized measurements at cellular and tissue levels, Histolytics addresses a critical gap in explainable computational pathology, offering an interpretable alternative or complement to black-box predictive models. We validated Histolytics through segmentation benchmarking on cervical and ovarian high-grade serous carcinoma (HGSC) data.
Keywords:
Histopathology
Digital Pathology
cancer
Panoptic Segmentation
Spatial Analysis
Interpretable Features
Software
AI
Deep learning
Machine Learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.1
Papers:
686
Citations:
1.4W