NeuroNet19: an explainable deep neural network model for the classification of brain tumors using magnetic resonance imaging data

Abstract

Brain tumors (BTs) are one of the deadliest diseases that can significantly shorten a person’s life. In recent years, deep learning has become increasingly popular for detecting and classifying BTs. In this paper, we propose a deep neural network architecture called NeuroNet19. It utilizes VGG19 as its backbone and incorporates a novel module named the Inverted Pyramid Pooling Module (iPPM). The iPPM captures multi-scale feature maps, ensuring the extraction of both local and global image contexts. This enhances the feature maps produced by the backbone, regardless of the spatial positioning or size of the tumors. To ensure the model’s transparency and accountability, we employ Explainable AI. Specifically, we use Local Interpretable Model-Agnostic Explanations (LIME), which highlights the features or areas focused on while predicting individual images. NeuroNet19 is trained on four classes of BTs: glioma, meningioma, no tumor, and pituitary tumors. It is tested on a public dataset containing 7023 images. Our research demonstrates that NeuroNet19 achieves the highest accuracy at 99.3%, with precision, recall, and F1 scores at 99.2% and a Cohen Kappa coefficient (CKC) of 99%.

Brain Tumor Recognition Using Artificial Intelligence Neural-Networks (BRAIN): A Cost-Effective Clean-Energy Platform

“…Deep learning models are seldom analyzed to understand which features are most important, making it challenging to understand the underlying decision-making process. Interpretability is crucial in the medical domain, where clinicians need to justify and explain the reasoning behind diagnostic results [76]. Addressing this limitation and improving the interpretability of our models are areas of ongoing research.…”

“…Developing techniques to enhance the explainability of deep learning models will increase their acceptance and trust in clinical practice. Interrogating the explainability of models can allow clinicians to understand the steps and features that most greatly influence classification tasks [76]. Additionally, exploring transfer learning and domain adaptation methods can improve the generalizability of models, enabling them to perform well with new clinical data.…”

XAI-based Clinical Decision Support System: A Systematic Review

“…Another framework for brain tumor diagnosis, NeuroNet19, combines a 19-layer VGG19 that detects complex hierarchical features in images with an inverted pyramid pooling module (iPPM) model, which refines these features, leveraging post-interpretability [100]. Methodology-based techniques are categorized into Backpropagation-based and Perturbation-based [67], among which Backpropagation-based GradCAM was proposed to describe CNN models with good performance [101].…”