Saved in:
Bibliographic Details
Main Authors: Pekár, Matěj, Musil, Vít, Nenutil, Rudolf, Holub, Petr, Brázdil, Tomáš
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.03163
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911357013590016
author Pekár, Matěj
Musil, Vít
Nenutil, Rudolf
Holub, Petr
Brázdil, Tomáš
author_facet Pekár, Matěj
Musil, Vít
Nenutil, Rudolf
Holub, Petr
Brázdil, Tomáš
contents Precise and scalable instance segmentation of cell nuclei is essential for computational pathology, yet gigapixel Whole-Slide Images pose major computational challenges. Existing approaches rely on patch-based processing and costly post-processing for instance separation, sacrificing context and efficiency. We introduce LSP-DETR (Local Star Polygon DEtection TRansformer), a fully end-to-end framework that uses a lightweight transformer with linear complexity to process substantially larger images without additional computational cost. Nuclei are represented as star-convex polygons, and a novel radial distance loss function allows the segmentation of overlapping nuclei to emerge naturally, without requiring explicit overlap annotations or handcrafted post-processing. Evaluations on PanNuke and MoNuSeg show strong generalization across tissues and state-of-the-art efficiency, with LSP-DETR being over five times faster than the next-fastest leading method. Code and models are available at https://github.com/RationAI/lsp-detr.
format Preprint
id arxiv_https___arxiv_org_abs_2601_03163
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LSP-DETR: Efficient and Scalable Nuclei Segmentation in Whole Slide Images
Pekár, Matěj
Musil, Vít
Nenutil, Rudolf
Holub, Petr
Brázdil, Tomáš
Computer Vision and Pattern Recognition
Precise and scalable instance segmentation of cell nuclei is essential for computational pathology, yet gigapixel Whole-Slide Images pose major computational challenges. Existing approaches rely on patch-based processing and costly post-processing for instance separation, sacrificing context and efficiency. We introduce LSP-DETR (Local Star Polygon DEtection TRansformer), a fully end-to-end framework that uses a lightweight transformer with linear complexity to process substantially larger images without additional computational cost. Nuclei are represented as star-convex polygons, and a novel radial distance loss function allows the segmentation of overlapping nuclei to emerge naturally, without requiring explicit overlap annotations or handcrafted post-processing. Evaluations on PanNuke and MoNuSeg show strong generalization across tissues and state-of-the-art efficiency, with LSP-DETR being over five times faster than the next-fastest leading method. Code and models are available at https://github.com/RationAI/lsp-detr.
title LSP-DETR: Efficient and Scalable Nuclei Segmentation in Whole Slide Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.03163