Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

From Images to Insights: Transforming Brain Cancer Diagnosis with Explainable AI

Md. Arafat Alam Khandaker, Ziyan Shirin Raha, Salehin Bin Iqbal, M. F. Mridha, Jungpil Shin

TL;DR

Brain cancer diagnosis remains challenging due to intraclass variability and limited expertise in some regions. The authors evaluate nine CNN architectures on the Bangladesh Brain Cancer MRI Dataset (6,056 images across Brain Glioma, Brain Meningioma, and Brain Tumor) and enhance interpretability with four XAI methods (GradCAM, GradCAM++, ScoreCAM, LayerCAM). DenseNet169 delivers the best performance (accuracy 0.9983; F1 0.9983; Jaccard 0.9967), with XAI visualizations highlighting diagnostically relevant regions to improve transparency. The work demonstrates high-accuracy, explainable brain tumor classification on a real-world dataset, offering potential support for radiologists and faster, more trusted early diagnoses.

Abstract

Brain cancer represents a major challenge in medical diagnostics, requisite precise and timely detection for effective treatment. Diagnosis initially relies on the proficiency of radiologists, which can cause difficulties and threats when the expertise is sparse. Despite the use of imaging resources, brain cancer remains often difficult, time-consuming, and vulnerable to intraclass variability. This study conveys the Bangladesh Brain Cancer MRI Dataset, containing 6,056 MRI images organized into three categories: Brain Tumor, Brain Glioma, and Brain Menin. The dataset was collected from several hospitals in Bangladesh, providing a diverse and realistic sample for research. We implemented advanced deep learning models, and DenseNet169 achieved exceptional results, with accuracy, precision, recall, and F1-Score all reaching 0.9983. In addition, Explainable AI (XAI) methods including GradCAM, GradCAM++, ScoreCAM, and LayerCAM were employed to provide visual representations of the decision-making processes of the models. In the context of brain cancer, these techniques highlight DenseNet169's potential to enhance diagnostic accuracy while simultaneously offering transparency, facilitating early diagnosis and better patient outcomes.

From Images to Insights: Transforming Brain Cancer Diagnosis with Explainable AI

TL;DR

Brain cancer diagnosis remains challenging due to intraclass variability and limited expertise in some regions. The authors evaluate nine CNN architectures on the Bangladesh Brain Cancer MRI Dataset (6,056 images across Brain Glioma, Brain Meningioma, and Brain Tumor) and enhance interpretability with four XAI methods (GradCAM, GradCAM++, ScoreCAM, LayerCAM). DenseNet169 delivers the best performance (accuracy 0.9983; F1 0.9983; Jaccard 0.9967), with XAI visualizations highlighting diagnostically relevant regions to improve transparency. The work demonstrates high-accuracy, explainable brain tumor classification on a real-world dataset, offering potential support for radiologists and faster, more trusted early diagnoses.

Abstract

Brain cancer represents a major challenge in medical diagnostics, requisite precise and timely detection for effective treatment. Diagnosis initially relies on the proficiency of radiologists, which can cause difficulties and threats when the expertise is sparse. Despite the use of imaging resources, brain cancer remains often difficult, time-consuming, and vulnerable to intraclass variability. This study conveys the Bangladesh Brain Cancer MRI Dataset, containing 6,056 MRI images organized into three categories: Brain Tumor, Brain Glioma, and Brain Menin. The dataset was collected from several hospitals in Bangladesh, providing a diverse and realistic sample for research. We implemented advanced deep learning models, and DenseNet169 achieved exceptional results, with accuracy, precision, recall, and F1-Score all reaching 0.9983. In addition, Explainable AI (XAI) methods including GradCAM, GradCAM++, ScoreCAM, and LayerCAM were employed to provide visual representations of the decision-making processes of the models. In the context of brain cancer, these techniques highlight DenseNet169's potential to enhance diagnostic accuracy while simultaneously offering transparency, facilitating early diagnosis and better patient outcomes.
Paper Structure (17 sections, 5 figures, 2 tables)

This paper contains 17 sections, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Brain Tumor Classification without using XAI Techniques
  4. Brain Tumor Classification using XAI Techniques
  5. BackGround Study
  6. Convolutional Neural Networks (CNNs)
  7. Explainable Artificial Intelligence (XAI) techniques
  8. Evaluation Metrics
  9. Methodology
  10. Dataset
  11. Proposed Methodology
  12. Result Analysis
  13. Experimental setup
  14. Evaluation
  15. Model Interpretation using XAI
  16. ...and 2 more sections

Figures (5)

  • Figure 1: Dataset Representation
  • Figure 2: Methodological Framework for Brain Cancer Classification
  • Figure 3: Performance Analysis Graph of the Proposed Models
  • Figure 4: Confusion Matrix of the Proposed Models
  • Figure 5: Explanation of the Model's Decision Making