Multiple sclerosis (MS) is a chronic disease that affects the central nervous system, showing heterogeneous clinical manifestations such as motor, cerebellar and sensory symptoms. Over the past two decades, magnetic resonance imaging (MRI) has become an indispensable tool for diagnosing MS. However, the current MRI criteria for MS diagnosis have imperfect specificity making misdiagnosis of MS relatively common, with relevant health and socioeconomic costs.

In order to distinguish MS lesions from white matter abnormalities arising from other diseases, the identification of an MRI-detectable vein traversing the center of a lesion has been proposed as a diagnostic tool. This marker is referred to as the central vein sign (CVS). However, the clinical application of the CVS as a biomarker is limited by interrater differences in the adjudication of the CVS, as well as the time burden required for the manual determination of the CVS for each lesion in a patient’s full MR imaging scan. 

The AMETISTA project aims to address these challenges by developing automatic software capable of accurately distinguishing white matter lesions with CVS from those without. Starting with MRI data, CVS assessment involves various imaging tasks that can be mathematically formalized as optimization problems. To process MRI brain images quickly and automatically for CVS identification, ad hoc numerical optimization algorithms are required, integrated into a unified processing pipeline.