Background: Artificial intelligence (AI) has recently made unprecedented contributions in every walk of life, but it has not been able to work its way into diagnostic medicine and standard clinical practice yet. Although data scientists, researchers, and medical experts have been working in the direction of designing and developing computer aided diagnosis (CAD) tools to serve as assistants to doctors, their large-scale adoption and integration into the healthcare system still seems far-fetched. Diagnostic radiology is no exception. Imagining techniques like magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET) scans have been widely and very effectively employed by radiologists and neurologists for the differential diagnoses of neurological disorders for decades, yet no AI-powered systems to analyze such scans have been incorporated into the standard operating procedures of healthcare systems. Why? It is absolutely understandable that in diagnostic medicine, precious human lives are on the line, and hence there is no room even for the tiniest of mistakes. Nevertheless, with the advent of explainable artificial intelligence (XAI), the old-school black boxes of deep learning (DL) systems have been unraveled. Would XAI be the turning point for medical experts to finally embrace AI in diagnostic radiology? This review is a humble endeavor to find the answers to these questions. Methods: In this review, we present the journey and contributions of AI in developing systems to recognize, preprocess, and analyze brain MRI scans for differential diagnoses of various neurological disorders, with special emphasis on CAD systems embedded with explainability. A comprehensive review of the literature from 2017 to 2024 was conducted using host databases. We also present medical domain experts’ opinions and summarize the challenges up ahead that need to be addressed in order to fully exploit the tremendous potential of XAI in its application to medical diagnostics and serve humanity. Results: Forty-seven studies were summarized and tabulated with information about the XAI technology and datasets employed, along with performance accuracies. The strengths and weaknesses of the studies have also been discussed. In addition, the opinions of seven medical experts from around the world have been presented to guide engineers and data scientists in developing such CAD tools. Conclusions: Current CAD research was observed to be focused on the enhancement of the performance accuracies of the DL regimens, with less attention being paid to the authenticity and usefulness of explanations. A shortage of ground truth data for explainability was also observed. Visual explanation methods were found to dominate; however, they might not be enough, and more thorough and human professor-like explanations would be required to build the trust of healthcare professionals. Special attention to these factors along with the legal, ethical, safety, and security issues can bridge the current gap between XAI and routine clinical practice.

The automatic diagnosis of neurological disorders using Magnetic Resonance Imaging (MRI) is a widely researched problem. MRI is a non-invasive and highly informative imaging modality, which is one of the most widely accepted and used neuroimaging modalities for visualizing the human brain. The advent of tremendous processing capabilities, multi-modal data, and deep-learning techniques has enabled researchers to develop intelligent, sufficiently accurate classification methods. A comprehensive literature review has revealed extensive research on the automatic diagnosis of neurological disorders. However, despite numerous studies, a systematically developed framework is lacking, that relies on a sufficiently robust dataset or ensures reliable accuracy. To date, no consolidated framework has been established to classify multiple diseases and their subtypes effectively based on various types and their planes of orientation in structural and functional MR images. This systematic review provides a detailed and comprehensive analysis of research reported from 2000 to 2023. Systems developed in prior art have been categorized according to their disease diagnosis capabilities. The datasets employed and the tools developed are also summarized to assist researchers to conduct further studies in this crucial domain. The contributions of this research include facilitating the design of a unified framework for multiple neurological disease diagnoses, resulting in the development of a generic assistive tool for hospitals and neurologists to diagnose disorders precisely and swiftly thus potentially saving lives, in addition to increasing the quality of life of patients suffering from neurodegenerative disorders.

Medical imaging plays a pivotal role in diagnostic medicine with technologies like Magnetic Resonance Imagining (MRI), Computed Tomography (CT), Positron Emission Tomography (PET), and ultrasound scans being widely used to assist radiologists and medical experts in reaching concrete diagnosis. Given the recent massive uplift in the storage and processing capabilities of computers, and the publicly available big data, Artificial Intelligence (AI) has also started contributing to improving diagnostic radiology. Edge computing devices and handheld gadgets can serve as useful tools to process medical data in remote areas with limited network and computational resources. In this research, the capabilities of multiple platforms are evaluated for the real-time deployment of diagnostic tools. MRI classification and segmentation applications developed in previous studies are used for testing the performance using different hardware and software configurations. Cost–benefit analysis is carried out using a workstation with a NVIDIA Graphics Processing Unit (GPU), Jetson Xavier NX, Raspberry Pi 4B, and Android phone, using MATLAB, Python, and Android Studio. The mean computational times for the classification app on the PC, Jetson Xavier NX, and Raspberry Pi are 1.2074, 3.7627, and 3.4747 s, respectively. On the low-cost Android phone, this time is observed to be 0.1068 s using the Dynamic Range Quantized TFLite version of the baseline model, with slight degradation in accuracy. For the segmentation app, the times are 1.8241, 5.2641, 6.2162, and 3.2023 s, respectively, when using JPEG inputs. The Jetson Xavier NX and Android phone stand out as the best platforms due to their compact size, fast inference times, and affordability.

Neurological disorders are debilitating diseases and cause significant morbidity worldwide, with some resulting in mortality. Magnetic Resonance Imagining (MRI) is the prime modality to evaluate most of the diseases involving the brain. The organic diseases of the brain show lesions which are well-appreciated on MRI, but require radiologists and medical experts for delineation. This is crucial for the differential diagnosis of diseases producing similar plaque patterns on the brain. Artificial Intelligence (AI) techniques can help in automatic brain lesion segmentation using massive publicly available data to train Computer-Aided Differential Diagnosis (CADD) algorithms. The accuracy of such CADD algorithms hugely relies on the accuracy of lesion segmentation Deep Learning (DL) models. In this research, DeepLabV3+ architecture is used for semantic segmentation of brain lesions using multiple publicly available datasets. In order to enhance the accuracy, additional ground truth (GT) lesion masks from MICCAI-21 dataset were obtained from a consultant radiologist, and used for training and testing. In addition, the developed algorithm underwent testing using 5 Multiple Sclerosis (MS) and 5 Neuromyelitis Optica (NMO) cases obtained from UiTM Hospital, and 35 MS and 27 NMO cases from HCTM Malaysia, and annotated by radiologists. The Dice score of the trained DL model on test data from MICCAI-21, MICCAI-16, Baghdad Teaching Hospital dataset, HCTM, and UiTM data is 0.7304, 0.6426, 0.4117, 0.5308, and 0.4951, respectively. The model is embedded in an app called NeuroImaging Lesion Extractor (NILE) and is available for public use. This app can serve as an assistive tool for experts in developing differential diagnosis algorithms for demyelinating diseases like MS and NMO.

Brain extraction is an important preprocessing step in Computer Aided Diagnosis (CAD) from brain MRI. It facilitates stripping off irrelevant extra-cranial tissues including skull, eyes, and neck muscles, thereby enhancing accuracy of inference of an AI CAD system. Numerous studies have been conducted to achieve this task ranging from old-school image processing techniques to more sophisticated deep learning approaches. This research investigates the performance of two deep learning-based semantic segmentation techniques, DeepLabV3+ and U-Net for brain extraction of brain MRI scanning images. The two networks were trained using the largest human brain MRI images dataset having more than 160 thousand training images and the performance is compared with SynthStrip from MIT, as the current state of the art system. Besides, the trained networks were also tested using newly collected MRI images from a private hospital, AIH, Islamabad. The result indicates that DeepLabV3+ outperforms SynthStrip and U-Net in all public datasets and produces comparable results from the new dataset with a mean Dice score of 0.98. Using the trained DeepLabV3+, an app called NIVE is developed for public use. Since the DeepLabV3+ was trained using the most comprehensive human brain MRI dataset to date, NIVE is essentially the most versatile brain extraction app capable of handling MRI images in all types of file formats, sequences, orientations, acquisition hardware, and subject age.