SSMamba: A Self-Supervised Hybrid State Space Model for Pathological Image Classification

2026-04-17

AI Summary

This work addresses three key challenges in region-of-interest (ROI) analysis of histopathological images: cross-magnification domain shift, insufficient modeling of local–global relationships, and inadequate sensitivity to fine-grained diagnostic cues. To tackle these issues, the authors propose SSMamba, a self-supervised hybrid state space model that employs a two-stage learning paradigm—self-supervised pretraining followed by supervised fine-tuning. The approach introduces Mamba-based Masked Image Modeling (MAMIM) to mitigate domain shift, incorporates a Directional Multi-Scale (DMS) module to balance local and global feature representation, and integrates a Local-Perceptive Residual (LPR) module to enhance sensitivity to subtle pathological patterns. Evaluated on 10 ROI and 6 whole-slide image (WSI) public datasets, SSMamba outperforms 11 pathology foundation models and 8 state-of-the-art methods, demonstrating the efficacy and superiority of its task-specific architecture.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Medical and Biological Imaging
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Pathological diagnosis is highly reliant on image analysis, where Regions of Interest (ROIs) serve as the primary basis for diagnostic evidence, while whole-slide image (WSI)-level tasks primarily capture aggregated patterns. To extract these critical morphological features, ROI-level Foundation Models (FMs) based on Vision Transformers (ViTs) and large-scale self-supervised learning (SSL) have been widely adopted. However, three core limitations remain in their application to ROI analysis: (1) cross-magnification domain shift, as fixed-scale pretraining hinders adaptation to diverse clinical settings; (2) inadequate local-global relationship modeling, wherein the ViT backbone of FMs suffers from high computational overhead and imprecise local characterization; (3) insufficient fine-grained sensitivity, as traditional self-attention mechanisms tend to overlook subtle diagnostic cues. To address these challenges, we propose SSMamba, a hybrid SSL framework that enables effective fine-grained feature learning without relying on large external datasets. This framework incorporates three domain-adaptive components: Mamba Masked Image Modeling (MAMIM) for mitigating domain shift, a Directional Multi-scale (DMS) module for balanced local-global modeling, and a Local Perception Residual (LPR) module for enhanced fine-grained sensitivity. Employing a two-stage pipeline, SSL pretraining on target ROI datasets followed by supervised fine-tuning (SFT), SSMamba outperforms 11 state-of-the-art (SOTA) pathological FMs on 10 public ROI datasets and surpasses 8 SOTA methods on 6 public WSI datasets. These results validate the superiority of task-specific architectural designs for pathological image analysis.

Problem

• domain shift
• local-global modeling
• fine-grained sensitivity
• pathological image classification
• self-supervised learning

Innovation

• SSMamba
• State Space Model
• Self-Supervised Learning
• Pathological Image Classification
• Multi-scale Modeling