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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Song, Jinsol, Wang, Jiamu, Nguyen, Anh Tien, Byeon, Keunho, Ahn, Sangjeong, Lee, Sung Hak, Kwak, Jin Tae
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915581314203648
author Song, Jinsol
Wang, Jiamu
Nguyen, Anh Tien
Byeon, Keunho
Ahn, Sangjeong
Lee, Sung Hak
Kwak, Jin Tae
author_facet Song, Jinsol
Wang, Jiamu
Nguyen, Anh Tien
Byeon, Keunho
Ahn, Sangjeong
Lee, Sung Hak
Kwak, Jin Tae
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_15256
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Normal and Abnormal Pathology Knowledge-Augmented Vision-Language Model for Anomaly Detection in Pathology Images
Song, Jinsol
Wang, Jiamu
Nguyen, Anh Tien
Byeon, Keunho
Ahn, Sangjeong
Lee, Sung Hak
Kwak, Jin Tae
Computer Vision and Pattern Recognition
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.
title Normal and Abnormal Pathology Knowledge-Augmented Vision-Language Model for Anomaly Detection in Pathology Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.15256