AI-Enhanced Virtual Biopsies for Brain Tumor Diagnosis in Low Resource Settings

TL;DR

This paper introduces a lightweight, interpretable AI pipeline combining CNN and radiomics features for brain tumor classification in low-resource settings, emphasizing explainability and robustness.

Contribution

It presents a novel fusion approach of deep learning and handcrafted features using MobileNetV2 and RandomForest for accessible brain tumor diagnosis.

Findings

Fusion improves classification accuracy over single methods

System provides explainability via Grad-CAM and feature importance

Robustness tests show sensitivity to low-resolution and noisy images

Abstract

Timely brain tumor diagnosis remains challenging in low-resource clinical environments where expert neuroradiology interpretation, high-end MRI hardware, and invasive biopsy procedures may be limited. Although deep learning has achieved strong performance in brain tumor analysis, real-world adoption is constrained by computational demands, dataset shift across scanners, and limited interpretability. This paper presents a prototype virtual biopsy pipeline for four-class classification of 2D brain MRI images using a lightweight convolutional neural network (CNN) and complementary radiomics-style handcrafted features. A MobileNetV2-based CNN is trained for classification, while an interpretable radiomics branch extracts eight features capturing lesion shape, intensity statistics, and gray-level co-occurrence matrix (GLCM) texture descriptors. A late fusion strategy concatenates CNN embeddings with radiomics features and trains a RandomForest classifier on the fused representation. Explainability is provided via Grad-CAM visualizations and radiomics feature importance analysis. Experiments on a public Kaggle brain tumor MRI dataset show improved validation performance for fusion relative to single-branch baselines, while robustness tests under reduced resolution and additive noise highlight sensitivity relevant to low-resource imaging conditions. The system is framed as decision support and not a substitute for clinical diagnosis or histopathology.