arXiv subjects

Yonghan Shin

Publications and source records attributed to Yonghan Shin.

2 recordsLinked to original sources

arXiv2026

LRMIL: Efficient Low-Resolution Multiple Instance Learning via High-Resolution Knowledge Distillation for Whole Slide Image Classification

Multiple instance learning (MIL) has become a standard paradigm for whole slide image (WSI) analysis in digital pathology, as it enables slide-level prediction without dense annotations. Existing MIL methods typically rely on exhaustive extraction and encoding of high-resolution patches. However, this practice suffers from two critical limitations in real-world clinical settings: it struggles to capture global visual cues at lower magnifications, and incurs substantial computational overhead due to the massive number of high-resolution patches per slide. To address these limitations, we propose an efficient low-resolution multiple instance learning (LRMIL) framework that transfers high-resolution knowledge to low-resolution representations. LRMIL adopts a two-stage distillation strategy. First, patch-level cross-resolution distillation aligns low-resolution patch embeddings with high-resolution representations. Second, slide-level knowledge distillation trains a low-resolution student MIL model under both slide-level supervision and teacher guidance. At inference time, LRMIL operates exclusively on low-resolution patches, substantially reducing data preprocessing and computational cost. Extensive experiments on multiple WSI benchmarks demonstrate that LRMIL consistently outperforms state-of-the-art MIL methods while achieving more efficient inference. These results highlight LRMIL as a practical and scalable solution for WSI analysis in clinical pathology.

cs.CV↗

arXiv2025

LanGuSTE: Language-Guided Coarse-to-Fine Patch Selection for Efficient Whole Slide Image Analysis

Whole slide images (WSIs) in computational pathology pose a major computational challenge due to their gigapixel scale, often requiring tens to hundreds of thousands of high-resolution patches to be processed per slide. In conventional WSI pipelines, exhaustive high-resolution patch processing makes preprocessing far more time-consuming than downstream model training. Existing patch selection methods suffer from a fundamental paradox: all patches must still be extracted and encoded at least during training, and sometimes during both training and inference, before irrelevant ones can be discarded. To address this, we propose LanGuSTE, an efficient patch selection framework that integrates pathology-domain vision-language models (VLMs) and knowledge derived from large language models (LLMs) through two key modules: Cross- Scale Visual Prompt Tuning (CS-VPT) and coarse-to-fine patch selection. CS-VPT aligns low-resolution patches with their spatially corresponding high-resolution patches through contrastive learning, transferring fine-grained diagnostic semantics into low-resolution representations. The patch selection module then leverages VLM representations and LLM-generated pathology-specific descriptions to identify informative regions in a coarse-to-fine manner, encoding only the corresponding high-resolution patches to reduce preprocessing time. Extensive experiments demonstrate that LanGuSTE reduces overall WSI processing time to approximately 3x while achieving diagnostic performance comparable to or better than exhaustive patch processing and recent state-of-the-art patch-selection methods.

cs.CV↗