Meningioma Analysis and Diagnosis using Limited Labeled Samples

2026-02-11

AI Summary

Accurate grading of meningiomas is critical for treatment planning and prognosis, yet existing methods often suffer from limited performance under scarce annotated data. To address this challenge, this work proposes a deep learning architecture that adaptively fuses spatial and frequency-domain features. Specifically, discrete wavelet transform is employed to extract multi-band frequency information, and a content-aware dynamic weighting mechanism is introduced to adaptively modulate the contribution of each frequency band and spatial features during fusion. This design enhances the model’s generalization capability in low-data regimes. Extensive experiments on three datasets—including a newly released meningioma MRI dataset—demonstrate that the proposed method significantly outperforms current state-of-the-art approaches, achieving notably higher grading accuracy.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Other Foundations of Computer Vision
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Web Mining and Content Analysis: Machine learning and data science for the Web
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

The biological behavior and treatment response of meningiomas depend on their grade, making an accurate diagnosis essential for treatment planning and prognosis assessment. We observed that the weighted fusion of spatial-frequency domain features significantly influences meningioma classification performance. Notably, the contribution of specific frequency bands obtained by discrete wavelet transform varies considerably across different images. A feature fusion architecture with adaptive weights of different frequency band information and spatial domain information is proposed for few-shot meningioma learning. To verify the effectiveness of the proposed method, a new MRI dataset of meningiomas is introduced. The experimental results demonstrate the superiority of the proposed method compared with existing state-of-the-art methods in three datasets. The code will be available at: https://github.com/ICL-SUST/AMSF-Net

Problem

• meningioma
• few-shot learning
• diagnosis
• MRI
• limited labeled samples

Innovation

• adaptive feature fusion
• few-shot learning
• spatial-frequency domain
• discrete wavelet transform
• meningioma classification