Toward an automatic tool for oligoclonal band detection in cerebrospinal fluid and tears for multiple sclerosis diagnosis: lane segmentation based on a ribbon univariate open active contour

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

“…The scanned images were then cropped vertically to remove the blank sample-free margins (2.12 cm (505 pixels) at the top of the image and 0.42 cm (100 pixels) at the bottom). Each lanes’ left and right edges ( were simultaneously delineated using our innovative automatic lane segmentation approach, which was developed for highly distorted and low-contrast lanes [ 11 ]. This approach is a new formulation of the classic parametric active contour problem, in which an open active contour is constrained to move from the top to the bottom of the image and the x-axis coordinate is expressed as a function of the y-axis coordinate (lane segmentations are shown in blue lines in Figure 1 ).…”

“… Example of a CSF IEF membrane with different types of band deformation: the left and right contours of each lane are delineated (blue lines) using our automatic lane segmentation method described in [ 11 ]. …”

“…We are currently developing the first automatic tool for OCB detection in CSF and tear samples [ 9 , 10 , 11 ]. Our objective is to provide an easy-to-use solution with a reasonable processing time, to ensure its adoption by hospital physicians.…”

“…Correcting geometric distortion and hence restoring ideal IEF images are the first steps in the automatic analysis of IEF membranes. Our previous work addressed the automatic segmentation of distorted lanes [ 11 ]; in Figure 1 , the blue lines correspond to the segmentation results for each lane. Here, we address the problem of distorted bands in IEF images.…”