Saved in:
Bibliographic Details
Main Authors: Zhang, Shengxuming, Li, Weihan, Gao, Tianhong, Hu, Jiacong, Luo, Haoming, Zhang, Xiuming, Zhang, Jing, Song, Mingli, Feng, Zunlei
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.09521
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915289349750784
author Zhang, Shengxuming
Li, Weihan
Gao, Tianhong
Hu, Jiacong
Luo, Haoming
Zhang, Xiuming
Zhang, Jing
Song, Mingli
Feng, Zunlei
author_facet Zhang, Shengxuming
Li, Weihan
Gao, Tianhong
Hu, Jiacong
Luo, Haoming
Zhang, Xiuming
Zhang, Jing
Song, Mingli
Feng, Zunlei
contents Pathological diagnosis is vital for determining disease characteristics, guiding treatment, and assessing prognosis, relying heavily on detailed, multi-scale analysis of high-resolution whole slide images (WSI). However, existing large vision-language models (LVLMs) are limited by input resolution constraints, hindering their efficiency and accuracy in pathology image analysis. To overcome these issues, we propose two innovative strategies: the mixed task-guided feature enhancement, which directs feature extraction toward lesion-related details across scales, and the prompt-guided detail feature completion, which integrates coarse- and fine-grained features from WSI based on specific prompts without compromising inference speed. Leveraging a comprehensive dataset of 490K samples from diverse pathology tasks, we trained the pathology-specialized LVLM, OmniPath. Extensive experiments demonstrate that this model significantly outperforms existing methods in diagnostic accuracy and efficiency, providing an interactive, clinically aligned approach for auxiliary diagnosis in a wide range of pathology applications.
format Preprint
id arxiv_https___arxiv_org_abs_2412_09521
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient and Comprehensive Feature Extraction in Large Vision-Language Model for Pathology Analysis
Zhang, Shengxuming
Li, Weihan
Gao, Tianhong
Hu, Jiacong
Luo, Haoming
Zhang, Xiuming
Zhang, Jing
Song, Mingli
Feng, Zunlei
Computer Vision and Pattern Recognition
Artificial Intelligence
Pathological diagnosis is vital for determining disease characteristics, guiding treatment, and assessing prognosis, relying heavily on detailed, multi-scale analysis of high-resolution whole slide images (WSI). However, existing large vision-language models (LVLMs) are limited by input resolution constraints, hindering their efficiency and accuracy in pathology image analysis. To overcome these issues, we propose two innovative strategies: the mixed task-guided feature enhancement, which directs feature extraction toward lesion-related details across scales, and the prompt-guided detail feature completion, which integrates coarse- and fine-grained features from WSI based on specific prompts without compromising inference speed. Leveraging a comprehensive dataset of 490K samples from diverse pathology tasks, we trained the pathology-specialized LVLM, OmniPath. Extensive experiments demonstrate that this model significantly outperforms existing methods in diagnostic accuracy and efficiency, providing an interactive, clinically aligned approach for auxiliary diagnosis in a wide range of pathology applications.
title Efficient and Comprehensive Feature Extraction in Large Vision-Language Model for Pathology Analysis
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2412.09521