Explanation-Driven Deep Learning Model for Prediction of Brain Tumour Status Using MRI Image Data

Abstract

Cancer research has seen explosive development exploring deep learning (DL) techniques for analysing magnetic resonance imaging (MRI) images for predicting brain tumours. We have observed a substantial gap in explanation, interpretability, and high accuracy for DL models. Consequently, we propose an explanation-driven DL model by utilising a convolutional neural network (CNN), local interpretable model-agnostic explanation (LIME), and Shapley additive explanation (SHAP) for the prediction of discrete subtypes of brain tumours (meningioma, glioma, and pituitary) using an MRI image dataset. Unlike previous models, our model used a dual-input CNN approach to prevail over the classification challenge with images of inferior quality in terms of noise and metal artifacts by adding Gaussian noise. Our CNN training results reveal 94.64% accuracy as compared to other state-of-the-art methods. We used SHAP to ensure consistency and local accuracy for interpretation as Shapley values examine all future predictions applying all possible combinations of inputs. In contrast, LIME constructs sparse linear models around each prediction to illustrate how the model operates in the immediate area. Our emphasis for this study is interpretability and high accuracy, which is critical for realising disparities in predictive performance, helpful in developing trust, and essential in integration into clinical practice. The proposed method has a vast clinical application that could potentially be used for mass screening in resource-constraint countries.

Convolutional Neural Network Techniques for Brain Tumor Classification (from 2015 to 2022): Review, Challenges, and Future Perspectives

“…Even though CNNs have demonstrated remarkable performance in brain tumor classification tasks in the majority of the reviewed studies, their level of trustworthiness and transparency must be evaluated in a clinic context. Of the included articles, only two studies, conducted by Artzi et al [ 122 ] and Gaur et al [ 127 ], investigated the Black-Box nature of CNN models for brain tumor classification to ensure that the model is looking in the correct place rather than at noise or unrelated artifacts.…”

“…Gaur et al [ 127 ] proposed a CNN-based model integrated with local interpretable model-agnostic explanation (LIME) and Shapley additive explanation (SHAP) for the classification and explanation of meningioma, glioma, pituitary, and normal images using an MRI dataset of 2870 MR images. For better classification results, Gaussian noise was introduced in the pre-processing step to improve the learning for the CNN, with mean = 0 and a standard deviation of 10 0.5 .…”

Utilization of model-agnostic explainable artificial intelligence frameworks in oncology: a narrative review

“…XAI can also be used to describe how a given imaging voxel contributes to a model’s output. Gaur et al used a deep learning model to identify brain tumor subtypes, with accuracy of 94.64% ( 32 ). To explain how their model made its predictions, they provide examples using the SHAP framework where SHAP values are superimposed on imaging voxels, and in doing so illustrate graphically and intuitively how example images are classified as normal or meningioma, as illustrated in Figure 3 .…”

Detecting COVID-19 infection status from chest X-ray and CT scan via single transfer learning-driven approach

“…DL applications are successfully implemented in the classification of medical images and clinical decision-making tasks Greenspan et al (2016) . The use of machine learning (ML) algorithms and software, or artificial intelligence (AI) Gaur et al (2022) ; Biswas et al (2021) , to replicate human cognition in the analysis, display, and comprehension of complicated medical and health-care data is referred to as AI in healthcare Biswas Milon and Kawsher. (2022) .…”