Application of deep-learning to the seronegative side of the NMO spectrum

Update on aquaporin-4 antibody detection: the early diagnosis of neuromyelitis optica spectrum disorders

Neuromyelitis optica spectrum disorder (NMOSD) is an autoimmune-mediated primary inflammatory myelinopathy of the central nervous system that primarily affects the optic nerve and spinal cord. The aquaporin 4 antibody (AQP4-Ab) is a specific autoantibody marker for NMOSD. Most patients with NMOSD are seropositive for AQP4-Ab, thus aiding physicians in identifying ways to treat NMOSD. AQP4-Ab has been tested in many clinical and laboratory studies, demonstrating effectiveness in diagnosing NMOSD. Recently, novel assays have been developed for the rapid and accurate detection of AQP4-Ab, providing further guidance for the diagnosis and treatment of NMOSD. This article summarizes the importance of rapid and accurate diagnosis for treating NMOSD based on a review of the latest relevant literature. We discussed current challenges and methods for improvement to offer new ideas for exploring rapid and accurate AQP4-Ab detection methods, aiming for early diagnosis of NMOSD.

Clinical applications of deep learning in neuroinflammatory diseases: A scoping review

BACKGROUND

Deep learning (DL) is an artificial intelligence technology that has aroused much excitement for predictive medicine due to its ability to process raw data modalities such as images, text, and time series of signals.

OBJECTIVES

Here, we intend to give the clinical reader elements to understand this technology, taking neuroinflammatory diseases as an illustrative use case of clinical translation efforts. We reviewed the scope of this rapidly evolving field to get quantitative insights about which clinical applications concentrate the efforts and which data modalities are most commonly used.

METHODS

We queried the PubMed database for articles reporting DL algorithms for clinical applications in neuroinflammatory diseases and the radiology.healthairegister.com website for commercial algorithms.

RESULTS

The review included 148 articles published between 2018 and 2024 and five commercial algorithms. The clinical applications could be grouped as computer-aided diagnosis, individual prognosis, functional assessment, the segmentation of radiological structures, and the optimization of data acquisition. Our review highlighted important discrepancies in efforts. The segmentation of radiological structures and computer-aided diagnosis currently concentrate most efforts with an overrepresentation of imaging. Various model architectures have addressed different applications, relatively low volume of data, and diverse data modalities. We report the high-level technical characteristics of the algorithms and synthesize narratively the clinical applications. Predictive performances and some common a priori on this topic are finally discussed.

CONCLUSION

The currently reported efforts position DL as an information processing technology, enhancing existing modalities of paraclinical investigations and bringing perspectives to make innovative ones actionable for healthcare.

Double-negative neuromyelitis optica spectrum disorder

Most patients with neuromyelitis optica spectrum disorders (NMOSD) test positive for aquaporin-4 antibody (AQP4-IgG) or myelin oligodendrocyte glycoprotein antibodies (MOG-IgG). Those who are negative are termed double-negative (DN) NMOSD and may constitute a diagnostic and therapeutic challenge. DN NMOSD is a syndrome rather than a single disease, ranging from a (postinfectious) monophasic illness to a more chronic syndrome that can be indistinguishable from AQP4-IgG+ NMOSD or develop into other mimics such as multiple sclerosis. Thus, underlying disease mechanisms are likely to be heterogeneous. This topical review aims to (1) reappraise antibody-negative NMOSD definition as it has changed over time with the development of the AQP4 and MOG-IgG assays; (2) outline clinical characteristics and the pathophysiological nature of this rare entity by contrasting its differences and similarities with antibody-positive NMOSD; (3) summarize laboratory characteristics and magnetic resonance imaging findings of DN NMOSD; and (4) discuss the current treatment for DN NMOSD.

Transformer-Based Deep-Learning Algorithm for Discriminating Demyelinating Diseases of the Central Nervous System With Neuroimaging

Background

Differential diagnosis of demyelinating diseases of the central nervous system is a challenging task that is prone to errors and inconsistent reading, requiring expertise and additional examination approaches. Advancements in deep-learning-based image interpretations allow for prompt and automated analyses of conventional magnetic resonance imaging (MRI), which can be utilized in classifying multi-sequence MRI, and thus may help in subsequent treatment referral.

Methods

Imaging and clinical data from 290 patients diagnosed with demyelinating diseases from August 2013 to October 2021 were included for analysis, including 67 patients with multiple sclerosis (MS), 162 patients with aquaporin 4 antibody-positive (AQP4+) neuromyelitis optica spectrum disorder (NMOSD), and 61 patients with myelin oligodendrocyte glycoprotein antibody-associated disease (MOGAD). Considering the heterogeneous nature of lesion size and distribution in demyelinating diseases, multi-modal MRI of brain and/or spinal cord were utilized to build the deep-learning model. This novel transformer-based deep-learning model architecture was designed to be versatile in handling with multiple image sequences (coronal T2-weighted and sagittal T2-fluid attenuation inversion recovery) and scanning locations (brain and spinal cord) for differentiating among MS, NMOSD, and MOGAD. Model performances were evaluated using the area under the receiver operating curve (AUC) and the confusion matrices measurements. The classification accuracy between the fusion model and the neuroradiological raters was also compared.

Results

The fusion model that was trained with combined brain and spinal cord MRI achieved an overall improved performance, with the AUC of 0.933 (95%CI: 0.848, 0.991), 0.942 (95%CI: 0.879, 0.987) and 0.803 (95%CI: 0.629, 0.949) for MS, AQP4+ NMOSD, and MOGAD, respectively. This exceeded the performance using the brain or spinal cord MRI alone for the identification of the AQP4+ NMOSD (AUC of 0.940, brain only and 0.689, spinal cord only) and MOGAD (0.782, brain only and 0.714, spinal cord only). In the multi-category classification, the fusion model had an accuracy of 81.4%, which was significantly higher compared to rater 1 (64.4%, p=0.04<0.05) and comparable to rater 2 (74.6%, p=0.388).

Conclusion

The proposed novel transformer-based model showed desirable performance in the differentiation of MS, AQP4+ NMOSD, and MOGAD on brain and spinal cord MRI, which is comparable to that of neuroradiologists. Our model is thus applicable for interpretating conventional MRI in the differential diagnosis of demyelinating diseases with overlapping lesions.