Automated cerebral microbleed detection using selective 3D gradient co-occurance matrix and convolutional neural network

Review of methods for automatic cerebral microbleeds detection

“…However, this kind of operations were used at all the stages described in this paper, as they were also useful for CMB candidates verification. Next, the detecting procedures evolved to include more complicated voxel features, such as: eigenvalues in [20] -scalars associated with the given linear transformation, line detection in [41] -defining the line where edge points are located, Gaussian filter in [20] and Laplacian of Gaussian operator in [28,27,20], which highlight the rapid change of the image intensity, Hough transform in [2] that enables shape detection by finding objects -local maxima, Canny filter in [2] which enables edge detection watershed transform in [137] -transforming images to grayscale topographic like map, and distinguishing objects on the basis of its intensity value or Frangi filters in [20] -a dedicated filter enabling vessel distinction, or 3D gradient co-occurrence matrix (3D GCM) in [72], which indicates the differences between intensity of two adjacent pixels.…”

“…Although their reliability based on intra-and inter-observer agreement is reported, details of the methods used are usually not described [109]. [32,33], Traumatic Brain Injury (TBI) [45,29,5,44,140], stroke [31,5,73,20], Intracerebral Haemorrhages (ICH) [34,20], gliomas [26,51,17], hemodialysis cases [5], Cerebral Amyloid Angiopathy (CAA) [34], atherosclerosis [6], or did not distinguish any particular disease besides the appearance of CMBs [1,30,42,43,3,80,79,24,18,19,76,22,13,72,20,126,138,137]. Datasets used in the first category of researches focused on AD [81,82,83,36,84,85], SMART [37], TBI [86], stroke [86,…”

“…This enables bias reduction in the next stages of system creation. It was applied by [32,73,25,33,35,26,41,28,27,42,43,45,5,6,18,72].…”

“…Further, there are typically neurological masks such as cerebrovascular fluid (CSF) mask, gray-white matter (GWM) mask and white-matter (WM) mask. Masks were generated in [32,73,33,35,26,41,28,27,45,29,78,17,126,23,76,2,72].…”

“…Padding is performing an artificial size change by addition of a black frame to obtain a desired image size without applying resize. It was utilized by [6,18,72].…”