Pathology-Informed Latent Diffusion Model for Anomaly Detection in Lymph Node Metastasis

2025-08-21

AI Summary

Unsupervised anomaly detection for lymph node metastasis in digital pathology is hindered by severe scarcity of annotated data, rendering conventional supervised methods inapplicable. Method: We propose Patho-LDM, a pathology-knowledge-integrated latent diffusion model. It leverages vision-language models to extract semantic prompts (e.g., “follicle”, “germinal center”) from normal tissue descriptions and employs keyword-guided cross-modal attention in the latent space to constrain the diffusion process, enabling precise modeling of normal tissue distributions. Training requires only normal-tissue images and brief pathological text—no abnormal samples or extensive annotations. Contribution/Results: Patho-LDM achieves state-of-the-art performance on a local gastric cancer lymph node dataset and demonstrates strong cross-organ generalization on a public breast cancer dataset. It significantly improves accuracy and robustness of unsupervised anomaly detection in digital pathology.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Diffusion Models for Vision
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Anomaly detection is an emerging approach in digital pathology for its ability to efficiently and effectively utilize data for disease diagnosis. While supervised learning approaches deliver high accuracy, they rely on extensively annotated datasets, suffering from data scarcity in digital pathology. Unsupervised anomaly detection, however, offers a viable alternative by identifying deviations from normal tissue distributions without requiring exhaustive annotations. Recently, denoising diffusion probabilistic models have gained popularity in unsupervised anomaly detection, achieving promising performance in both natural and medical imaging datasets. Building on this, we incorporate a vision-language model with a diffusion model for unsupervised anomaly detection in digital pathology, utilizing histopathology prompts during reconstruction. Our approach employs a set of pathology-related keywords associated with normal tissues to guide the reconstruction process, facilitating the differentiation between normal and abnormal tissues. To evaluate the effectiveness of the proposed method, we conduct experiments on a gastric lymph node dataset from a local hospital and assess its generalization ability under domain shift using a public breast lymph node dataset. The experimental results highlight the potential of the proposed method for unsupervised anomaly detection across various organs in digital pathology. Code: https://github.com/QuIIL/AnoPILaD.

Problem

• Detecting lymph node metastasis anomalies unsupervised
• Overcoming data scarcity in digital pathology
• Differentiating normal and abnormal tissues using diffusion models

Innovation

• Latent diffusion model with pathology prompts
• Vision-language guidance for reconstruction
• Unsupervised anomaly detection using histopathology keywords