# Multi-scale fully convolutional neural networks for histopathology image segmentation: from nuclear aberrations to the global tissue architecture

arXiv: https://arxiv.org/abs/1909.10726 · HTML: https://mlsanity.com/paper/1909.10726/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Sep 2019.

## Built on by (most cited first, 20 of 20)

- [OCELOT: Overlapped Cell on Tissue Dataset for Histopathology](https://mlsanity.com/paper/2303.13110/) (2023)
- [Nuclei Segmentation with Point Annotations from Pathology Images via Self-Supervised Learning and Co-Training](https://mlsanity.com/paper/2202.08195/) (2022)
- [DPA-P2PNet: Deformable Proposal-aware P2PNet for Accurate Point-based Cell Detection](https://mlsanity.com/paper/2303.02602/) (2023)
- [Cross-attention Spatio-temporal Context Transformer for Semantic Segmentation of Historical Maps](https://mlsanity.com/paper/2310.12616/) (2023)
- [A State-of-the-art Survey of Artificial Neural Networks for Whole-slide Image Analysis:from Popular Convolutional Neural Networks to Potential Visual Transformers](https://mlsanity.com/paper/2104.06243/) (2021)
- [A Dual-branch Self-supervised Representation Learning Framework for Tumour Segmentation in Whole Slide Images](https://mlsanity.com/paper/2303.11019/) (2023)
- [Towards Effective and Efficient Context-aware Nucleus Detection in Histopathology Whole Slide Images](https://mlsanity.com/paper/2503.05678/) (2025)
- [Valuing Vicinity: Memory attention framework for context-based semantic segmentation in histopathology](https://mlsanity.com/paper/2210.11822/) (2022)
- [Category Prompt Mamba Network for Nuclei Segmentation and Classification](https://mlsanity.com/paper/2503.10422/) (2025)
- [Hybrid guiding: A multi-resolution refinement approach for semantic segmentation of gigapixel histopathological images](https://mlsanity.com/paper/2112.03455/) (2021)
- [Structure-aware scale-adaptive networks for cancer segmentation in whole-slide images](https://mlsanity.com/paper/2109.12617/) (2021)
- [A Hierarchical Transformer Encoder to Improve Entire Neoplasm Segmentation on Whole Slide Image of Hepatocellular Carcinoma](https://mlsanity.com/paper/2307.05800/) (2023)
- [Multi-Scale Semantic Segmentation with Modified MBConv Blocks](https://mlsanity.com/paper/2402.04618/) (2024)
- [Towards Efficient Information Fusion: Concentric Dual Fusion Attention Based Multiple Instance Learning for Whole Slide Images](https://mlsanity.com/paper/2403.14346/) (2024)
- [Joint Modelling Histology and Molecular Markers for Cancer Classification](https://mlsanity.com/paper/2502.07979/) (2025)
- [GNCAF: A GNN-based Neighboring Context Aggregation Framework for Tertiary Lymphoid Structures Semantic Segmentation in WSI](https://mlsanity.com/paper/2505.08430/) (2025)
- [Efficient Pyramidal Analysis of Gigapixel Images on a Decentralized Modest Computer Cluster](https://mlsanity.com/paper/2509.02440/) (2025)
- [Generalisation of automatic tumour segmentation in histopathological whole-slide images across multiple cancer types](https://mlsanity.com/paper/2510.11182/) (2025)
- [Adapting Vision Transformers to Ultra-High Resolution Semantic Segmentation with Relay Tokens](https://mlsanity.com/paper/2601.05927/) (2026)
- [PathPilot: An Adaptive Question-Conditioned Multi-Magnification Navigation Agent for Whole-Slide Image Analysis](https://mlsanity.com/paper/2610.16734/) (2026)

## Abstract (arXiv)

Histopathologic diagnosis relies on simultaneous integration of information from a broad range of scales, ranging from nuclear aberrations (≈ O(0.1μ m)) through cellular structures (≈ O(10μ m)) to the global tissue architecture (gtrapprox O(1mm)). To explicitly mimic how human pathologists combine multi-scale information, we introduce a family of multi-encoder FCNs with deep fusion. We present a simple block for merging model paths with differing spatial scales in a spatial relationship-preserving fashion, which can readily be included in standard encoder-decoder networks. Additionally, a context classification gate block is proposed as an alternative for the incorporation of global context. Our experiments were performed on three publicly available whole-slide images of recent challenges (PAIP 2019, BACH 2020, CAMELYON 2016). The multi-scale architectures consistently outperformed the baseline single-scale U-Nets by a large margin. They benefit from local as well as global context and particularly a combination of both. If feature maps from different scales are fused, doing so in a manner preserving spatial relationships was found to be beneficial. Deep guidance by a context classification loss appeared to improve model training at low computational costs. All multi-scale models had a reduced GPU memory footprint compared to ensembles of individual U-Nets trained on different image scales. Additional path fusions were shown to be possible at low computational cost, opening up possibilities for further, systematic and task-specific architecture optimization. The findings demonstrate the potential of the presented family of human-inspired, end-to-end trainable, multi-scale multi-encoder FCNs to improve deep histopathologic diagnosis by extensive integration of largely different spatial scales.