Explainable artificial intelligence with UNet based segmentation and Bayesian machine learning for classification of brain tumors using MRI images.

in Scientific reports by K Lakshmi, Sibi Amaran, G Subbulakshmi, S Padmini, Gyanenedra Prasad Joshi, Woong Cho

TLDR

  • The XAISS-BMLBT technique, a new explainable AI approach, achieves an accuracy of 97.75% in detecting brain tumors in MRI images, outperforming existing models.

Abstract

Detecting brain tumours (BT) early improves treatment possibilities and increases patient survival rates. Magnetic resonance imaging (MRI) scanning offers more comprehensive information, such as better contrast and clarity, than any alternative scanning process. Manually separating BTs from several MRI images gathered in medical practice for cancer analysis is challenging and time-consuming. Tumours and MRI scans of the brain are exposed utilizing methods and machine learning technologies, simplifying the process for doctors. MRI images can sometimes appear normal even when a patient has a tumour or malignancy. Deep learning approaches have recently depended on deep convolutional neural networks to analyze medical images with promising outcomes. It supports saving lives faster and rectifying some medical errors. With this motivation, this article presents a new explainable artificial intelligence with semantic segmentation and Bayesian machine learning for brain tumors (XAISS-BMLBT) technique. The presented XAISS-BMLBT technique mainly concentrates on the semantic segmentation and classification of BT in MRI images. The presented XAISS-BMLBT approach initially involves bilateral filtering-based image pre-processing to eliminate the noise. Next, the XAISS-BMLBT technique performs the MEDU-Net+ segmentation process to define the impacted brain regions. For the feature extraction process, the ResNet50 model is utilized. Furthermore, the Bayesian regularized artificial neural network (BRANN) model is used to identify the presence of BTs. Finally, an improved radial movement optimization model is employed for the hyperparameter tuning of the BRANN technique. To highlight the improved performance of the XAISS-BMLBT technique, a series of simulations were accomplished by utilizing a benchmark database. The experimental validation of the XAISS-BMLBT technique portrayed a superior accuracy value of 97.75% over existing models.

Overview

  • The study focuses on developing a new explainable artificial intelligence (XAI) technique, XAISS-BMLBT, to detect brain tumors in MRI images.
  • The technique utilizes bilateral filtering-based image pre-processing, MEDU-Net+ segmentation, ResNet50 for feature extraction, and Bayesian regularized artificial neural network (BRANN) for classification.
  • The primary objective of the study is to improve the accuracy of brain tumor detection and classification using MRI images.

Comparative Analysis & Findings

  • The XAISS-BMLBT technique achieved an accuracy of 97.75% in detecting brain tumors, outperforming existing models.
  • The experimental validation of the XAISS-BMLBT technique demonstrated its ability to effectively identify the presence of brain tumors in MRI images.
  • The technique's performance was evaluated using a benchmark database, showcasing its potential for clinical applications.

Implications and Future Directions

  • The XAISS-BMLBT technique has the potential to improve the detection and diagnosis of brain tumors, ultimately leading to better treatment outcomes and patient survival rates.
  • Future studies can focus on incorporating additional features, such as patient-specific characteristics, to further improve the accuracy of the technique.
  • The development of explainable AI techniques like XAISS-BMLBT can help address concerns about AI decision-making and increase confidence in the use of AI in medical diagnosis.
Read Full Article