Oligoclonal Band Straightening Based on Optimized Hierarchical Warping for Multiple Sclerosis Diagnosis.

Farah Haddad,Julien Poupart,Laurent Peyrodie,Vincent Chieux,Nicolas Vandenbroucke,Samuel Boudet,Patrick Hautecoeur,Gérard Forzy

doi:10.3390/s22030724

Abstract

The detection of immunoglobulin G (IgG) oligoclonal bands (OCB) in cerebrospinal fluid (CSF) by isoelectric focusing (IEF) is a valuable tool for the diagnosis of multiple sclerosis. Over the last decade, the results of our clinical research have suggested that tears are a non-invasive alternative to CSF. However, since tear samples have a lower IgG concentration than CSF, a sensitive OCB detection is therefore required. We are developing the first automatic tool for IEF analysis, with a view to speeding up the current visual inspection method, removing user variability, reducing misinterpretation, and facilitating OCB quantification and follow-up studies. The removal of band distortion is a key image enhancement step in increasing the reliability of automatic OCB detection. Here, we describe a novel, fully automatic band-straightening algorithm. The algorithm is based on a correlation directional warping function, estimated using an energy minimization procedure. The approach was optimized via an innovative coupling of a hierarchy of image resolutions to a hierarchy of transformation, in which band misalignment is corrected at successively finer scales. The algorithm’s performance was assessed in terms of the bands’ standard deviation before and after straightening, using a synthetic dataset and a set of 200 lanes of CSF, tear, serum and control samples on which experts had manually delineated the bands. The number of distorted bands was divided by almost 16 for the synthetic lanes and by 7 for the test dataset of real lanes. This method can be applied effectively to different sample types. It can realign minimal contrast bands and is robust for non-uniform deformations.

Highlights

isoelectric focusing (IEF) and immunoglobulin G (IgG) immunoblotting were carried on a 10 cm × 8 cm gel membrane, using the Helena Biosciences IgG IEF kit intended for IgG oligoclonal bands (OCB) detection in cerebrospinal fluid (CSF) and serum, and using a SPIFE 2000 analyser (Helena Biosciences Europe, Gateshead, UK)
This example demonstrated the robustness of OCBSA-2021 with regard to non-uniform band deformations: all the deformed bands were straightened to a satisfactory extent (Figure 5c,f)
A visual examination of the band straightening results (Figure 5c,f) illustrated the imprecision of the expert’s band delineation, which resulted in the underestimation of visually satisfactory straightening by OCBSA-2021

Summary

Introduction

There is no specific diagnosis test for MS; a number of clinical, imaging, and laboratory criteria evidence the spread of demyelinating, inflammatory MS lesions in space and over time. An inflammatory CSF profile is not specific for MS, the intrathecal synthesis of immunoglobulin G (IgG) antibodies is strongly suggestive of MS once other causes of central nervous system inflammation have been ruled out. Background subtraction unveils faint bands in low-intensity profiles. The rolling ball technique is a morphological approach to background removal and the correction of non-uniform brightness. A sphere with a chosen radius is rolled through the 3D landscape representation of the image. A background-subtracted image is obtained by removing the structures the sphere rolls into and keeping the remaining structures

Objectives

Methods

Results

Conclusion