Virtual Biopsy for Intracranial Tumors Diagnosis on MRI

2026-02-25

AI Summary

This study addresses the challenges of deep intracranial tumor biopsy—including procedural difficulty, high sampling bias, scarcity of MRI-pathology paired data, and the difficulty of localizing small lesions—by introducing ICT-MRI, the first publicly available biopsy-validated intracranial tumor MRI dataset. The authors propose a non-invasive virtual biopsy framework that integrates standardized MRI preprocessing, a weakly supervised coarse-to-fine localization module (Tumor-Localizer) based on vision-language models, and an adaptive diagnostic model (Adaptive-Diagnoser) incorporating a masked channel attention mechanism. This architecture effectively fuses local discriminative features with global contextual information. Evaluated on four classes of intracranial tumor pathology prediction, the framework achieves over 90% accuracy, surpassing existing baselines by more than 20%, thereby significantly advancing non-invasive precision diagnosis.

Technology Category

• Computer Vision: Medical and Biological Imaging
• Machine Learning: Multi-instance/Multi-view Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Deep intracranial tumors situated in eloquent brain regions controlling vital functions present critical diagnostic challenges. Clinical practice has shifted toward stereotactic biopsy for pathological confirmation before treatment. Yet biopsy carries inherent risks of hemorrhage and neurological deficits and struggles with sampling bias due to tumor spatial heterogeneity, because pathological changes are typically region-selective rather than tumor-wide. Therefore, advancing non-invasive MRI-based pathology prediction is essential for holistic tumor assessment and modern clinical decision-making. The primary challenge lies in data scarcity: low tumor incidence requires long collection cycles, and annotation demands biopsy-verified pathology from neurosurgical experts. Additionally, tiny lesion volumes lacking segmentation masks cause critical features to be overwhelmed by background noise. To address these challenges, we construct the ICT-MRI dataset - the first public biopsy-verified benchmark with 249 cases across four categories. We propose a Virtual Biopsy framework comprising: MRI-Processor for standardization; Tumor-Localizer employing vision-language models for coarse-to-fine localization via weak supervision; and Adaptive-Diagnoser with a Masked Channel Attention mechanism fusing local discriminative features with global contexts. Experiments demonstrate over 90% accuracy, outperforming baselines by more than 20%.

Problem

• intracranial tumors
• virtual biopsy
• MRI
• data scarcity
• sampling bias

Innovation

• Virtual Biopsy
• Vision-Language Model
• Masked Channel Attention
• Weakly Supervised Localization
• ICT-MRI Dataset