An automated deep learning framework for brain tumor classification using MRI imagery.

in Scientific reports by Muhammad Aamir, Ziaur Rahman, Uzair Aslam Bhatti, Waheed Ahmed Abro, Jameel Ahmed Bhutto, Zhonglin He

TLDR

  • The study presents an automated approach for identifying brain lesions in MRI images, achieving high accuracy and improving the diagnostic process.

Abstract

The precise and timely diagnosis of brain tumors is essential for accelerating patient recovery and preserving lives. Brain tumors exhibit a variety of sizes, shapes, and visual characteristics, requiring individualized treatment strategies for each patient. Radiologists require considerable proficiency to manually detect brain malignancies. However, tumor recognition remains inefficient, imprecise, and labor-intensive in manual procedures, underscoring the need for automated methods. This study introduces an effective approach for identifying brain lesions in magnetic resonance imaging (MRI) images, minimizing dependence on manual intervention. The proposed method improves image clarity by combining guided filtering techniques with anisotropic Gaussian side windows (AGSW). A morphological analysis is conducted prior to segmentation to exclude non-tumor regions from the enhanced MRI images. Deep neural networks segment the images, extracting high-quality regions of interest (ROIs) and multiscale features. Identifying salient elements is essential and is accomplished through an attention module that isolates distinctive features while eliminating irrelevant information. An ensemble model is employed to classify brain tumors into different categories. The proposed technique achieves an overall accuracy of 99.94% and 99.67% on the publicly available brain tumor datasets BraTS2020 and Figshare, respectively. Furthermore, it surpasses existing technologies in terms of automation and robustness, thereby enhancing the entire diagnostic process.

Overview

  • The study proposes an automated approach for identifying brain lesions in MRI images, minimizing the need for manual intervention.
  • The method combines guided filtering techniques with anisotropic Gaussian side windows (AGSW) to improve image clarity.
  • A morphological analysis is conducted to exclude non-tumor regions from the enhanced MRI images, followed by segmentation and feature extraction via deep neural networks.

Comparative Analysis & Findings

  • The proposed technique achieves an overall accuracy of 99.94% and 99.67% on the publicly available brain tumor datasets BraTS2020 and Figshare, respectively.
  • The method surpasses existing technologies in terms of automation and robustness, enhancing the diagnostic process.
  • The study demonstrates the effectiveness of combining guided filtering and AGSW techniques with morphological analysis and deep learning-based segmentation and feature extraction.

Implications and Future Directions

  • The proposed method has the potential to revolutionize the diagnosis of brain tumors, reducing dependence on manual intervention and improving diagnostic accuracy.
  • Future research can focus on integrating the proposed technique with other imaging modalities, such as computed tomography and positron emission tomography.
  • The method can be further optimized by incorporating domain adaptation techniques and fine-tuning the model for specific tumor types and imaging protocols.
Read Full Article