Saved in:
Bibliographic Details
Main Authors: Shin, Yonghan, Kim, SeungKyu, Jeong, Won-Ki
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.14537
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912545569243136
author Shin, Yonghan
Kim, SeungKyu
Jeong, Won-Ki
author_facet Shin, Yonghan
Kim, SeungKyu
Jeong, Won-Ki
contents Whole slide images (WSIs) in computational pathology (CPath) pose a major computational challenge due to their gigapixel scale, often requiring the processing of tens to hundreds of thousands of high-resolution patches per slide. This results in prohibitive encoding costs, with preprocessing and training times extending to days or even weeks-making WSI encoding the most significant bottleneck in real-world deployment. In this work, we propose WISE-FUSE, an adaptive WSI encoding framework that leverages pathology-domain vision-language models and large language models to address this challenge by selectively processing diagnostically relevant regions. WISE-FUSE first computes similarity scores between low-resolution patches and class-specific textual descriptions using a knowledge distillation mechanism that preserves fine-grained diagnostic features. Based on these similarity scores, we select a small subset of informative regions for the target task, which quickly eliminates irrelevant patches at the coarse level. The corresponding high-resolution patches are then selectively encoded and fused with textual embeddings to reinforce diagnostic context. Extensive experiments demonstrate that WISE-FUSE reduces WSI encoding time by over threefold while achieving diagnostic performance comparable to or surpassing that of exhaustive patch processing, offering a scalable and practical solution for CPath.
format Preprint
id arxiv_https___arxiv_org_abs_2508_14537
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WISE-FUSE: Efficient Whole Slide Image Encoding via Coarse-to-Fine Patch Selection with VLM and LLM Knowledge Fusion
Shin, Yonghan
Kim, SeungKyu
Jeong, Won-Ki
Computer Vision and Pattern Recognition
Whole slide images (WSIs) in computational pathology (CPath) pose a major computational challenge due to their gigapixel scale, often requiring the processing of tens to hundreds of thousands of high-resolution patches per slide. This results in prohibitive encoding costs, with preprocessing and training times extending to days or even weeks-making WSI encoding the most significant bottleneck in real-world deployment. In this work, we propose WISE-FUSE, an adaptive WSI encoding framework that leverages pathology-domain vision-language models and large language models to address this challenge by selectively processing diagnostically relevant regions. WISE-FUSE first computes similarity scores between low-resolution patches and class-specific textual descriptions using a knowledge distillation mechanism that preserves fine-grained diagnostic features. Based on these similarity scores, we select a small subset of informative regions for the target task, which quickly eliminates irrelevant patches at the coarse level. The corresponding high-resolution patches are then selectively encoded and fused with textual embeddings to reinforce diagnostic context. Extensive experiments demonstrate that WISE-FUSE reduces WSI encoding time by over threefold while achieving diagnostic performance comparable to or surpassing that of exhaustive patch processing, offering a scalable and practical solution for CPath.
title WISE-FUSE: Efficient Whole Slide Image Encoding via Coarse-to-Fine Patch Selection with VLM and LLM Knowledge Fusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.14537