Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignment
This work addresses the problem of accurate brain tumor subtype classification for medical professionals, offering a zero-shot solution that improves discrimination in digital pathology, though it is incremental as it builds on existing vision-language models.
The paper tackled the challenge of fine-grained brain tumor subtype classification from histopathological images by proposing FG-PAN, a zero-shot framework that aligns refined visual features with LLM-generated descriptions, achieving state-of-the-art performance on public datasets like EBRAINS and TCGA.
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.