IVCVApr 12, 2025

PathSeqSAM: Sequential Modeling for Pathology Image Segmentation with SAM2

arXiv:2504.10526v1h-index: 15Has Code
Originality Incremental advance
AI Analysis

This addresses segmentation challenges in pathology imaging, particularly for cases benefiting from cross-slice context, though it appears incremental as it builds on existing SAM2 technology.

The paper tackles the problem of pathology image segmentation by treating 2D slices as sequential video frames using SAM2's memory mechanisms, resulting in improved segmentation quality on the KPI Challenge 2024 dataset for glomeruli segmentation.

Current methods for pathology image segmentation typically treat 2D slices independently, ignoring valuable cross-slice information. We present PathSeqSAM, a novel approach that treats 2D pathology slices as sequential video frames using SAM2's memory mechanisms. Our method introduces a distance-aware attention mechanism that accounts for variable physical distances between slices and employs LoRA for domain adaptation. Evaluated on the KPI Challenge 2024 dataset for glomeruli segmentation, PathSeqSAM demonstrates improved segmentation quality, particularly in challenging cases that benefit from cross-slice context. We have publicly released our code at https://github.com/JackyyyWang/PathSeqSAM.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes