SSMamba model enhances pathological image classification with hybrid self-supervised learning

Researchers have developed SSMamba, a novel self-supervised hybrid state space model designed for pathological image classification. This framework addresses limitations in current models, such as domain shift across magnifications, inadequate local-global relationship modeling, and insufficient fine-grained sensitivity. SSMamba integrates Mamba Masked Image Modeling, a Directional Multi-scale module, and a Local Perception Residual module to improve feature learning without extensive external datasets. The model demonstrated superior performance compared to eleven state-of-the-art pathological foundation models on ten public ROI datasets and eight methods on six public WSI datasets. AI

影响 Introduces a new architecture for medical image analysis, potentially improving diagnostic accuracy and efficiency in pathology.

排序理由 This is a research paper detailing a new model architecture for a specific domain. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

• Mamba
• SSMamba
• Vision Transformers

• 论文
• 其他

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →