Differentiation of relapsing-remitting and secondary progressive multiple sclerosis: a magnetic resonance spectroscopy study based on machine learning

Applications of magnetic resonance spectroscopy in diagnosis of neurodegenerative diseases: A systematic review

Background

Magnetic resonance spectroscopy (MRS) is an imaging technique used to measure metabolic changes in the tissue. Due to the lack of evidence, MRS is not a priority in diagnosing neurodegenerative diseases because it is a relatively specialized technique that requires specialized equipment and expertise to perform and interpret. This systematic review aimed to present a comprehensive collection of MRS results in the most common neurodegenerative diseases.

Methods

A systematic search of four electronic databases (PubMed, Scopus, Web of Science, and ScienceDirect) was conducted for studies published from 2017 to 2022. Articles that provided specific biomarker levels were selected, and studies that assessed the diseases via treatment, featured MRS applying nuclei other than 1H, or compared different animal models were excluded.

Results

A total of 25 articles, plus 3 articles for extra information in the introduction, were included in this review. Six of the most common neurodegenerative diseases, i.e., Alzheimer's and Parkinson's disease, Huntington chorea, ataxia, multiple sclerosis (MS), multiple system atrophy (MSA), and progressive supranuclear palsy (PSP) were examined via MRS. The changes and ratios of N-acetylaspartate (NAA) could be seen in all of these disorders, which could lead to early diagnosis. However, there are other biomarkers, such as Cr and Chon, which can give convincing results.

Discussion

This observational study is the first synthesis of the latest evidence proving metabolic changes during neurodegenerative diseases using MRS as a diagnosis method. The findings indicate decreased N-acetylaspartate (NAA) and NAA/Cr ratios in Alzheimer's disease (AD), Parkinson's disease (PD), ataxias, and MS, reflecting neuronal loss or dysfunction. Increased choline and myo-inositol were noted in some studies, suggesting cell membrane turnover and neuroinflammation. Findings were less consistent for other metabolites like glutamate and gamma-aminobutyric acid. However, there were limitations due to the lack of studies on the same volumes of interest (VOIs) and the small number of participants.

Role of artificial intelligence in MS clinical practice

•

For medical applications, machine learning (including deep learning) are the most commonly used artificial intelligence (AI) approaches.

•

It can improve multiple sclerosis (MS) diagnosis, prognostication and treatment monitoring.

•

Thanks to AI, MRI and cognitive phenotypes of MS patients were identified.

•

AI can shorten MRI protocols for MS, allowing the application of advanced techniques.

•

It can reduce the human effort for MRI analysis, especially for lesion segmentation.

Machine learning (ML) and its subset, deep learning (DL), are branches of artificial intelligence (AI) showing promising findings in the medical field, especially when applied to imaging data. Given the substantial role of MRI in the diagnosis and management of patients with multiple sclerosis (MS), this disease is an ideal candidate for the application of AI techniques. In this narrative review, we are going to discuss the potential applications of AI for MS clinical practice, together with their limitations. Among their several advantages, ML algorithms are able to automate repetitive tasks, to analyze more data in less time and to achieve higher accuracy and reproducibility than the human counterpart. To date, these algorithms have been applied to MS diagnosis, prognosis, disease and treatment monitoring. Other fields of application have been improvement of MRI protocols as well as automated lesion and tissue segmentation. However, several challenges remain, including a better understanding of the information selected by AI algorithms, appropriate multicenter and longitudinal validations of results and practical aspects regarding hardware and software integration. Finally, one cannot overemphasize the paramount importance of human supervision, in order to optimize the use and take full advantage of the potential of AI approaches.