Morphometric analysis of white matter lesions in MR images: method and validation

Abstract

The analysis of MR images is evolving from qualitative to quantitative. More and more, the question asked by clinicians is how much and where, rather than a simple statement on the presence or absence of abnormalities. The authors present a study in which the results obtained with a semiautomatic, multispectral segmentation technique are quantitatively compared to manually delineated regions. The core of the semiautomatic image analysis system is a supervised artificial neural network classifier augmented with dedicated preand postprocessing algorithms, including anisotropic noise filtering and a surface-fitting method for the correction of spatial intensity variations. The study was focused on the quantitation of white matter lesions in the human brain. A total of 36 images from six brain volumes was analyzed twice by each of two operators, under supervision of a neuroradiologist. Both the intra- and interrater variability of the methods were studied in terms of the average tissue area detected per slice, the correlation coefficients between area measurements, and a measure of similarity derived from the kappa statistic. The results indicate that, compared to a manual method, the use of the semiautomatic technique not only facilitates the analysis of the images, but also has similar or lower intra- and interrater variabilities.

Patch-based segmentation using expert priors: Application to hippocampus and ventricle segmentation

“…The kappa index (Dice coefficient or similarity index) (Zijdenbos et al, 1994) was then computed by comparing the expert-based segmentations with those obtained with our method. For two binary segmentations A and B, the kappa index was computed as:…”

Jaw tissues segmentation in dental 3D CT images using fuzzy-connectedness and morphological processing

“…Those values are remarkable considering that these indicators range from 0 to 1, where 0 represents the absence of common areas and 1 represents a perfect match. Our results are even significantly higher than the DC threshold value (DC = 0.7) from which an overlap is commonly considered good [23,24]. Regarding the distance indicators (P P D and P CD), the method has achieved significant results in accuracy.…”

Three validation metrics for automated probabilistic image segmentation of brain tumours

“…A χ 2 test of independence may be conducted between segmentations and the corresponding binary gold standard values. To evaluate the agreement between the binary segmentation and the gold standard, one may also compute the kappa statistic [11,12]. By considering spatial information, Jaccard (JSC) [13] and Dice (DSC) [14] similarity coefficients are typically used as a measure of overlap, where DSC ranges from 0, indicating no spatial alignment between these two sets of binary segmentation results, to 1, indicating complete alignment.…”