Segmenting leukomalacia using textural information and mathematical morphology
Ewout Vansteenkiste, Alessandro Ledda, Gjenna Stippel, Bruno Huysmans, Paul P. Govaert, Wilfried R. Philips · 2003
Abstract — In this article we present a technique for seg-menting the affected tissue visible as white flaring in the ultrasound brain images of neonates with Leukomalacia (White Matter Damage). The technique combines both tex-tural information of the investigated tissue as well as math-ematical morphology in order to detect and delineate the boundaries of the affected parts of the brain. The repro-ducibility of the proposed technique is evaluated and the ex-perimental results are validated by comparing them to the manual delineations of 12 expert medical doctors from dif-ferent institutions. Although it seems hard to reach a con-sensus on the correct segmentation of the flaring, because of the lack of a golden standard in the ultrasound images, we show that our method outperforms the existing techniques based on active contours in speed and is more accurate.