The Normal Lyceum of Helsinki, upper secondary school, Research Program in Systems Oncology, Research Programs Unit, Faculty of Medicine, Medicum, Clinicum, Department of Obstetrics and Gynecology, HUS Gynecology and Obstetrics, HUS Radiology and Pathology, Department of Pathology, HUS Diagnostic Center, Sampsa Hautaniemi / Principal Investigator, Bioinformatics, Department of Biochemistry and Developmental Biology
Publisher Information:
Chalmers University of Technology
Publication Year:
2025
Collection:
Helsingfors Universitet: HELDA – Helsingin yliopiston digitaalinen arkisto
We acknowledge CSC-IT Center for Science, Finland, for computational resources, Kari Lavikka for his invaluable assistance in the creation and refinement of the figures presented in this manuscript. This work utilized High-Grade Serous Carcinoma data, which originated from the DECIDER cohort (Multi-layer Data to Improve Diagnosis, Predict Therapy Resistance and Suggest Targeted Therapies in HGSOC; ClinicalTrials.gov identifier: NCT04846933) that has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 965193 . We also acknowledge the support from Finnish Medical Foundation (recipient I.K) and O.L acknowledges Finnish Society for Colposcopy r.y for a personal research grant. Additionally, we acknowledge Helsinki and Auria Biobanks for scanning the whole-slide data used in this work. We acknowledge CSC-IT Center for Science, Finland, for computational resources, Kari Lavikka for his invaluable assistance in the creation and refinement of the figures presented in this manuscript. This work utilized High-Grade Serous Carcinoma data, which originated from the DECIDER cohort (Multi-layer Data to Improve Diagnosis, Predict Therapy Resistance and Suggest Targeted Therapies in HGSOC; ClinicalTrials.gov identifier: NCT04846933) that has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 965193. We also acknowledge the support from Finnish Medical Foundation (recipient I.K) and O.L acknowledges Finnish Society for Colposcopy r.y for a personal research grant. Additionally, we acknowledge Helsinki and Auria Biobanks for scanning the whole-slide data used in this work.; https://hdl.handle.net/10138/609060; 105021876750; 001622413200001
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 data. ; Peer reviewed
