Explainable Artificial Intelligence for Human-Machine Interaction in Brain Tumor Localization

Abstract

Primary malignancies in adult brains are globally fatal. Computer vision, especially recent developments in artificial intelligence (AI), have created opportunities to automatically characterize and diagnose tumor lesions in the brain. AI approaches have provided scores of unprecedented accuracy in different image analysis tasks, including differentiating tumor-containing brains from healthy brains. AI models, however, perform as a black box, concealing the rational interpretations that are an essential step towards translating AI imaging tools into clinical routine. An explainable AI approach aims to visualize the high-level features of trained models or integrate into the training process. This study aims to evaluate the performance of selected deep-learning algorithms on localizing tumor lesions and distinguishing the lesion from healthy regions in magnetic resonance imaging contrasts. Despite a significant correlation between classification and lesion localization accuracy (R = 0.46, p = 0.005), the known AI algorithms, examined in this study, classify some tumor brains based on other non-relevant features. The results suggest that explainable AI approaches can develop an intuition for model interpretability and may play an important role in the performance evaluation of deep learning models. Developing explainable AI approaches will be an essential tool to improve human–machine interactions and assist in the selection of optimal training methods.

Computational Pathology for Brain Disorders

“…These methods can be used to generate visual explainability maps for deep learning models like 2D and 3D CNN, VGG [85], and Resnet-50 [86] (for classification) and 2D/3D U-Net (for segmentation). In [87], the high-level features of three deep convolutional neural networks (DenseNet-121, GoogLeNet, MobileNet) are analysed using the Grad-CAM explainability technique. The Grad-CAM outputs helped distinguish these three models' brain tumor lesion localization capabilities.…”

Brain Tumor Detection and Localization: An Inception V3 - Based Classification Followed By RESUNET-Based Segmentation Approach

“…The purpose of this research (Esmaeili et al, 2021) is to examine how effective specific deep-learning approaches are at detecting tumor lesions and separating them from healthy regions in magnetic resonance imaging comparisons. Regardless of the fact that there is indeed a significant relationship between category and tumor localized accuracy (p = 0.005, R = 0.46), the recognized AI arrangements examined in this learning detect specific tumor brains based on irrelevant criteria.…”

Explainability of deep neural networks for MRI analysis of brain tumors

“…For brain cancer classification, Windisch et al [ 28 ] applied 2D Grad-CAM to generate heatmaps indicating which areas of the input MRI made the classifier decide on the category of the existence of a brain tumor. Similarly, 2D Grad-CAM was used in [ 29 ] to evaluate the performance of three DL models in brain tumor classification. The key limitation of these studies is that experiments were concluded on 2D MRI slices without investigating the model on 3D medical applications.…”