Recent Advances in Explainable Artificial Intelligence for Magnetic Resonance Imaging

Abstract

Advances in artificial intelligence (AI), especially deep learning (DL), have facilitated magnetic resonance imaging (MRI) data analysis, enabling AI-assisted medical image diagnoses and prognoses. However, most of the DL models are considered as “black boxes”. There is an unmet need to demystify DL models so domain experts can trust these high-performance DL models. This has resulted in a sub-domain of AI research called explainable artificial intelligence (XAI). In the last decade, many experts have dedicated their efforts to developing novel XAI methods that are competent at visualizing and explaining the logic behind data-driven DL models. However, XAI techniques are still in their infancy for medical MRI image analysis. This study aims to outline the XAI applications that are able to interpret DL models for MRI data analysis. We first introduce several common MRI data modalities. Then, a brief history of DL models is discussed. Next, we highlight XAI frameworks and elaborate on the principles of multiple popular XAI methods. Moreover, studies on XAI applications in MRI image analysis are reviewed across the tissues/organs of the human body. A quantitative analysis is conducted to reveal the insights of MRI researchers on these XAI techniques. Finally, evaluations of XAI methods are discussed. This survey presents recent advances in the XAI domain for explaining the DL models that have been utilized in MRI applications.

Diagnosis of skull-base invasion by nasopharyngeal tumors on CT with a deep-learning approach

“…However, most DL models are often considered ‘black boxes’ due to their nonlinear underlying structures. This has led to the emergence of explainable artificial intelligence (XAI) research, which aims to enhance transparency in AI models and interpret the fidelity of their inferences [ 18 ]. Gradient-weighted class activation mapping (Grad-CAM) is one of the most commonly used XAI methods for enhancing the visual evaluation of the site at which a CNN model is focusing its attention during inference [ 19 ].…”

An Umbrella Review of the Fusion of fMRI and AI in Autism

“…Artificial intelligence (AI) plays a fundamental role in the interpretation and processing of data from fMRI, providing sophisticated tools to analyze in depth the functioning of the human brain [12][13][14][15][16][17][18][19][20][21][22][23][24][25]. One high-impact area is advanced data analytics, where AI can identify complex patterns and correlations that would be difficult or impossible to identify manually [13,17,22].…”

“…Furthermore, AI is essential for automating critical processes such as brain segmentation and mapping of brain regions [14,15]. This automation significantly speeds up the analysis process and ensures greater accuracy, allowing scientists to focus more on interpreting results rather than manipulating raw data [18,19,21]. Another powerful application is the prediction of brain responses to certain stimuli or tasks based on historical fMRI data [23].…”

Ultrasound Image Analysis with Vision Transformers—Review

“…Artificial intelligence (AI) methods, particularly deep learning models, have brought about ultrasound imaging by automating image processing and enabling the automated diagnosis of disease and detection of abnormalities. Convolutional neural networks (CNNs) have played a vital role in this transformation, demonstrating improvements in various medical imaging modalities [ 4 , 5 , 6 , 7 , 8 , 9 ]. However, the limitations of CNNs in capturing long-range dependencies and contextual information led to the development of vision transformers (ViTs) [ 10 ] in image processing.…”