Interpretable machine learning for brain tumour analysis using MRI and whole slide images

Tumour-Analyser is a web application that classifies brain tumour into three classes, namely, lower-grade astrocytoma (A), oligodendroglioma (O), glioblastoma & diffuse astrocytic glioma (G). We use magnetic resonance imaging (MRI) sequence and whole slide (WSI) are classified using DenseNet ResNet, respectively. The tool interprets the decision-making process of each classification model. provides viable solution to less human understandability existing models due inherent black-box nature deep learning transparency, by applying interpretability.