Progressive multifocal leukoencephalopathy lesion and brain parenchymal segmentation from MRI using serial deep convolutional neural networks

A rare case of progressive multifocal leukoencephalopathy

Progressive multifocal leukoencephalopathy (PML) is a rare demyelinating disease of the central nervous system (CNS) due to John Cunningham (JC) virus reactivation most often in immunocompromised patients. The brainstem and the anterior corpus callosum are uncommon locations for white matter lesions. We present a case of PML in a 40-year-old female presenting to the emergency department for a tonic seizure with transient postictal confusion. The inpatient workup revealed low cluster of differentiation cell counts (CD3 and CD4), transaminitis, positive drug screen, and abnormal electroencephalogram (EEG). The computed tomogram (CT) of the head and magnetic resonance image (MRI or MR) of the brain showed evidence of subcortical and periventricular white matter lesions in the right hemisphere extending into the brainstem and the left frontal lobe. The hospital course consisted of supportive measures, seizure treatment along with prophylaxis, and human immunodeficiency virus (HIV) management along with prophylactic antibiotics. The patient was discharged with appropriate medications and outpatient referrals. Overall, this case describes some key points. It highlights particular imaging characteristics of PML in the setting of inadequately treated HIV. For example, white matter lesions cross the anterior corpus callosum rather than the splenium, as in the "barbell" sign. In addition, the lesions extend inferiorly along the ipsilateral corticospinal tract into the midbrain and pons. This could be one of the first cases to capture both of these features given the rarity of their concomitant occurrence.

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.

Biomarkers for progressive multifocal leukoencephalopathy: emerging data for use of JC virus DNA copy number in clinical trials

Progressive multifocal leukoencephalopathy is a rare but devastating demyelinating disease caused by the JC virus (JCV), for which no therapeutics are approved. To make progress towards addressing this unmet medical need, innovations in clinical trial design are needed. Quantitative JCV DNA in CSF has the potential to serve as a valuable biomarker of progressive multifocal leukoencephalopathy disease and treatment response in clinical trials to expedite therapeutic development, as do neuroimaging and other fluid biomarkers such as neurofilament light chain. Specifically, JCV DNA in CSF could be used in clinical trials as an entry criterion, stratification factor, or predictor of clinical outcomes. Insights from the investigation of candidate biomarkers for progressive multifocal leukoencephalopathy might inform approaches to biomarker development for other rare diseases.

Radiological abnormalities in progressive multifocal leukoencephalopathy: Identifying typical and atypical imaging patterns for early diagnosis and differential considerations

Progressive multifocal leukoencephalopathy (PML) is a rare viral central nervous system (CNS) demyelinating disease primarily associated with a compromised immune system. PML is seen mainly in individuals with human immunodeficiency virus, lymphoproliferative disease, and multiple sclerosis. Patients on immunomodulators, chemotherapy, and solid organ or bone marrow transplants are predisposed to PML. Recognition of various PML-associated typical and atypical imaging abnormalities is critical for early diagnosis and differentiating it from other conditions, especially in high-risk populations. Early PML recognition should expedite efforts at immune-system restoration, allowing for a favorable outcome. This review aims to provide a practical overview of radiological abnormalities in PML patients and address differential considerations.

The neuroradiology of progressive multifocal leukoencephalopathy: a clinical trial perspective

Progressive multifocal leukoencephalopathy (PML) is an opportunistic infection of the central nervous system caused by the JC virus, which infects white and grey matter cells and leads to irreversible demyelination and neuroaxonal damage. Brain magnetic resonance imaging (MRI), in addition to the clinical presentation and demonstration of JC virus DNA either in the CSF or by histopathology, is an important tool in the detection of PML. In clinical practice, standard MRI pulse sequences are utilized for screening, diagnosis, and monitoring of PML, but validated imaging-based outcome measures for use in prospective, interventional clinical trials for PML have yet to be established. We review the existing literature regarding the use of MRI and positron emission tomography imaging in PML and discuss the implications of PML histopathology for neuroradiology. MRI not only demonstrates the localization and extent of PML lesions, but also mirrors the tissue destruction, ongoing viral spread, and resulting inflammation. Finally, we explore the potential for imaging measures to serve as an outcome in PML clinical trials and provide recommendations for current and future imaging outcome measure development in this area.

Improving Ischemic Stroke Care With MRI and Deep Learning Artificial Intelligence

ABSTRACT

Advanced magnetic resonance imaging has been used as selection criteria for both acute ischemic stroke treatment and secondary prevention. The use of artificial intelligence, and in particular, deep learning, to synthesize large amounts of data and to understand better how clinical and imaging data can be leveraged to improve stroke care promises a new era of stroke care. In this article, we review common deep learning model structures for stroke imaging, evaluation metrics for model performance, and studies that investigated deep learning application in acute ischemic stroke care and secondary prevention.