Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.03749 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911483868217344 |
|---|---|
| author | Wu, Yunheng Huang, Wenqi Wang, Liangyi Oda, Masahiro Hayashi, Yuichiro Rueckert, Daniel Mori, Kensaku |
| author_facet | Wu, Yunheng Huang, Wenqi Wang, Liangyi Oda, Masahiro Hayashi, Yuichiro Rueckert, Daniel Mori, Kensaku |
| contents | Whole-slide images (WSIs) are fundamental for computational pathology, where accurate lesion segmentation is critical for clinical decision making. Existing methods partition WSIs into discrete patches, disrupting spatial continuity and treating multi-resolution views as independent samples, which leads to spatially fragmented segmentation and reduced robustness to resolution variations. To address the issues, we propose WSI-INR, a novel patch-free framework based on Implicit Neural Representations (INRs). WSI-INR models the WSI as a continuous implicit function mapping spatial coordinates directly to tissue semantics features, outputting segmentation results while preserving intrinsic spatial information across the entire slide. In the WSI-INR, we incorporate multi-resolution hash grid encoding to regard different resolution levels as varying sampling densities of the same continuous tissue, achieving a consistent feature representation across resolutions. In addition, by jointly training a shared INR decoder, WSI-INR can capture general priors across different cases. Experimental results showed that WSI-INR maintains robust segmentation performance across resolutions; at Base/4, our resolution-specific optimization improves Dice score by +26.11%, while U-Net and TransUNet decrease by 54.28% and 36.18%, respectively. Crucially, this work enables INRs to segment highly heterogeneous pathological lesions beyond structurally consistent anatomical tissues, offering a fresh perspective for pathological analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03749 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | WSI-INR: Implicit Neural Representations for Lesion Segmentation in Whole-Slide Images Wu, Yunheng Huang, Wenqi Wang, Liangyi Oda, Masahiro Hayashi, Yuichiro Rueckert, Daniel Mori, Kensaku Computer Vision and Pattern Recognition Whole-slide images (WSIs) are fundamental for computational pathology, where accurate lesion segmentation is critical for clinical decision making. Existing methods partition WSIs into discrete patches, disrupting spatial continuity and treating multi-resolution views as independent samples, which leads to spatially fragmented segmentation and reduced robustness to resolution variations. To address the issues, we propose WSI-INR, a novel patch-free framework based on Implicit Neural Representations (INRs). WSI-INR models the WSI as a continuous implicit function mapping spatial coordinates directly to tissue semantics features, outputting segmentation results while preserving intrinsic spatial information across the entire slide. In the WSI-INR, we incorporate multi-resolution hash grid encoding to regard different resolution levels as varying sampling densities of the same continuous tissue, achieving a consistent feature representation across resolutions. In addition, by jointly training a shared INR decoder, WSI-INR can capture general priors across different cases. Experimental results showed that WSI-INR maintains robust segmentation performance across resolutions; at Base/4, our resolution-specific optimization improves Dice score by +26.11%, while U-Net and TransUNet decrease by 54.28% and 36.18%, respectively. Crucially, this work enables INRs to segment highly heterogeneous pathological lesions beyond structurally consistent anatomical tissues, offering a fresh perspective for pathological analysis. |
| title | WSI-INR: Implicit Neural Representations for Lesion Segmentation in Whole-Slide Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.03749 |