AdaPT: An adaptive preterm segmentation algorithm for neonatal brain MRI

Neonatal brain MRI segmentation: A review

“…Quantitative validation metrics Prastawa et al [78] Dice similarity coefficient, Cohen's kappa coefficient [119] Dice coefficient, false positive, false negative, boundary segmentation error, Surface reconstruction error Song [100] Dice coefficient Weisenfeld and Warfield [115] Dice coefficient [120] Dice coefficient, correct estimation index, over estimation index, under estimation index Shi et al [91,92,93] Dice coefficient [54] Dice coefficient, surface reconstruction error Melbourne et al [64] Dice coefficient Makropoulos et al [59] Dice coefficient, 95th-percentile Hausdorff distance Gui et al [43] Dice coefficient Anbeek et al [5] Dice coefficient, sensitivity, specificity Gousias et al [40] Dice coefficient [33] Dice coefficient, 95th-percentile Hausdorff distance Cardoso et al [17] Dice coefficient Wang et al [108] Dice coefficient, surface distance error, Hausdorff distance Wang et al [109] Dice coefficient, surface distance error, landmark curve distance error, local and global gyrification index Makropoulos et al [60] Dice coefficient works have included both neonatal and older infant/pediatric subjects in their studies; thus, such works also need to be included for the sake of completeness of the review. For instance, the 'LABEL' approach i.e.…”

“…Only a few of the available segmentation algorithms are capable of dealing with structural abnormalities of the brain such as enlarged ventricles in ventriculomegaly (Gui, 2012;Cardoso, 2013) or impaired brain maturation related to congenital heart defects (CHD) [100]. For instance, Gui et al [43] applied their algorithm to pre-terms with dilated ventricles and the adaptive approach of Cardoso et al [17] included subjects with enlarged ventricles or cystic and diffuse WM injury.…”

“…For instance, Gui et al [43] applied their algorithm to pre-terms with dilated ventricles and the adaptive approach of Cardoso et al [17] included subjects with enlarged ventricles or cystic and diffuse WM injury. Besides, the work of Song [100] employed cases of anomalous brain development linked to CHD.…”

Automatic brain tissue segmentation in MR images using Random Forests and Conditional Random Fields

“…For the brain volume extraction, we first follow the method proposed by Cardoso et al (2013b) that employs a multi-atlas based segmentation propagation scheme for skull stripping neonatal MR brain scans. In this method, we can de-135 fine templates from a bank of subjects with manual segmentations, as a binary brain mask (obtained from the manual segmentation) and the corresponding T1w MRI scan.…”

A novel diffusion tensor imaging-based computer-aided diagnostic system for early diagnosis of autism.

“…In addition to the limitations associated with each segmentation category, most of the previously described MR infant segmentation techniques were dedicated to segment infant brains either in the early infantile stage (≤5 months) or early adult-like stage (≥12 months) by using a T1 or T2 scan or the combination of both [120,122,127,128,132,134,136,141,145,147]. However, these methods would fail in the case of infants in the isointense stage (6-12 months), which is the primary focus of this thesis, because both WM and GM have roughly the same intensity levels (see Figure 20).…”