Diffusion-Based Feature Denoising and Using NNMF for Robust Brain Tumor Classification
2026-03-13 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a method to classify brain tumors from MRI scans using a combination of mathematical techniques and lightweight deep learning models. They first transform MRI data into simpler, understandable features with Non-Negative Matrix Factorization (NNMF), then use a small convolutional neural network to classify tumors. To make their system more reliable against tricky changes meant to fool it, they add a special step that cleans the features before classification. Their results show good accuracy and strong resistance to intentional attacks that try to confuse the model.
Brain tumor classificationMagnetic Resonance Imaging (MRI)Deep learningNon-Negative Matrix Factorization (NNMF)Convolutional Neural Networks (CNNs)Adversarial perturbationsDiffusion-based purificationAutoAttackRobustnessFeature extraction
Authors
Hiba Adil Al-kharsan, Róbert Rajkó
Abstract
Brain tumor classification from magnetic resonance imaging, which is also known as MRI, plays a sensitive role in computer-assisted diagnosis systems. In recent years, deep learning models have achieved high classification accuracy. However, their sensitivity to adversarial perturbations has become an important reliability concern in medical applications. This study suggests a robust brain tumor classification framework that combines Non-Negative Matrix Factorization (NNMF or NMF), lightweight convolutional neural networks (CNNs), and diffusion-based feature purification. Initially, MRI images are preprocessed and converted into a non-negative data matrix, from which compact and interpretable NNMF feature representations are extracted. Statistical metrics, including AUC, Cohen's d, and p-values, are used to rank and choose the most discriminative components. Then, a lightweight CNN classifier is trained directly on the selected feature groups. To improve adversarial robustness, a diffusion-based feature-space purification module is introduced. A forward noise method followed by a learned denoiser network is used before classification. System performance is estimated using both clean accuracy and robust accuracy under powerful adversarial attacks created by AutoAttack. The experimental results show that the proposed framework achieves competitive classification performance while significantly enhancing robustness against adversarial perturbations.The findings presuppose that combining interpretable NNMF-based representations with a lightweight deep approach and diffusion-based defense technique supplies an effective and reliable solution for medical image classification under adversarial conditions.