Normal and Abnormal Pathology Knowledge-Augmented Vision-Language Model for Anomaly Detection in Pathology Images

2025-08-21

AI Summary

Addressing the challenge of rare anomaly detection in histopathological images—particularly under conditions of scarce anomalous samples or absent annotations—existing industrial methods struggle to balance computational efficiency, tissue structural diversity, and result interpretability. This paper proposes Ano-NAViLa, a vision-language collaborative model that integrates both normal and abnormal pathological priors. It enables end-to-end anomaly localization via text-guided visual feature enhancement and a lightweight MLP adapter. Our key innovation lies in embedding structured medical knowledge into the multimodal alignment process and establishing explicit image-text associations to ensure clinical interpretability. Evaluated on a cross-organ lymph node dataset, Ano-NAViLa achieves state-of-the-art performance on both anomaly classification and pixel-level localization tasks, significantly outperforming leading unsupervised and weakly supervised approaches.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• 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
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Anomaly detection in computational pathology aims to identify rare and scarce anomalies where disease-related data are often limited or missing. Existing anomaly detection methods, primarily designed for industrial settings, face limitations in pathology due to computational constraints, diverse tissue structures, and lack of interpretability. To address these challenges, we propose Ano-NAViLa, a Normal and Abnormal pathology knowledge-augmented Vision-Language model for Anomaly detection in pathology images. Ano-NAViLa is built on a pre-trained vision-language model with a lightweight trainable MLP. By incorporating both normal and abnormal pathology knowledge, Ano-NAViLa enhances accuracy and robustness to variability in pathology images and provides interpretability through image-text associations. Evaluated on two lymph node datasets from different organs, Ano-NAViLa achieves the state-of-the-art performance in anomaly detection and localization, outperforming competing models.

Problem

• Detecting rare anomalies in pathology images with limited disease data
• Overcoming computational constraints and lack of interpretability in pathology
• Improving accuracy and robustness for diverse tissue structure variability

Innovation

• Vision-language model with pathology knowledge augmentation
• Lightweight trainable MLP on pre-trained foundation
• Image-text associations for interpretable anomaly detection