MRImmuno - platform for fast diagnostic-therapeutic
decision in patients with focal lesion of central nervous system

Currently there is no single specific parameter for multiple sclerosis (MS) enabling definite diagnosis. Despite diagnostic criteria, based mainly on MRI, it is mandatory to exclude numerous other diseases mimicking the clinical picture of MS. To date no tool has been designed which facilitates the diagnostic process of MS by combining complete medical data. Diagnosis is based mostly on doctors' experience instead of quantifiable indicators. In case of many patients protracted observation delaying therapeutic decision is necessary. Importantly, in case up to 13%  patients initially diagnosed with MS final diagnosis differs. Project aim is to elaborate an analytical tool based on deep learning (DL) network, expediting differential diagnosis of MS. Data from MR, optic coherence tomography (OCT), immune and neurodegeneration markers examinations, neuropsychological and clinical data will be collected in the system. Based on 5000 cases (MS patients ca. 50% of the study group) primary patterns. Clinical paths defined by neurologists and radiologists will include parameters and with assigned weight describing the influence of each factor on final diagnosis. Correlation between parameters will also be assessed.

The final project results:

Set of algorithms and trained DL network;
After connecting DL to the required set of data it will analyze available sets and present complete set of information in the form of a diagnostic panel, assisting and facilitating a treating physician in the final diagnostic decision;
Parameter defining the dynamics of the process will be assigned to each examination;
Value for a given patient will be estimated based on complete data.

Important features:

Automatic detection of changes of MR OCT;
Introduction of a variety of new parameters and markers which has not yet been included in the routine MS diagnostic process.
Page Created with OptimizePress