Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignment

TL;DR

This paper introduces FG-PAN, a zero-shot framework that improves brain tumor subtype classification from histopathological images by aligning refined visual features with pathology-aware text descriptions, achieving state-of-the-art results.

Contribution

The paper presents a novel fine-grained patch alignment network that enhances zero-shot classification by combining spatially refined visual features with large language model-generated semantic prototypes.

Findings

Achieves state-of-the-art zero-shot classification accuracy on pathology datasets.

Effectively captures subtle morphological differences in tumor subtypes.

Demonstrates robust generalization across multiple datasets.

Abstract

The fine-grained classification of brain tumor subtypes from histopathological whole slide images is highly challenging due to subtle morphological variations and the scarcity of annotated data. Although vision-language models have enabled promising zero-shot classification, their ability to capture fine-grained pathological features remains limited, resulting in suboptimal subtype discrimination. To address these challenges, we propose the Fine-Grained Patch Alignment Network (FG-PAN), a novel zero-shot framework tailored for digital pathology. FG-PAN consists of two key modules: (1) a local feature refinement module that enhances patch-level visual features by modeling spatial relationships among representative patches, and (2) a fine-grained text description generation module that leverages large language models to produce pathology-aware, class-specific semantic prototypes. By aligning refined visual features with LLM-generated fine-grained descriptions, FG-PAN effectively increases class separability in both visual and semantic spaces. Extensive experiments on multiple public pathology datasets, including EBRAINS and TCGA, demonstrate that FG-PAN achieves state-of-the-art performance and robust generalization in zero-shot brain tumor subtype classification.