Tumor detection in MR liver images by integrating edge and region information

Abstract

Abstract. This paper describes a segmentation technique for 2D interventional MR images of liver tumours. Two features of MR data were likely to challenge existing segmentation methods. The first one is the inhomogeneous intratumoral texture, while the second one is the "blurred" appearance and the non-uniform sharpness of the tumour boundary. In order to detect the region of interest, we create the tumour contour map using a multithresholding technique and a measure of similarity between successive contours. Tumours presenting boundaries with non-uniform sharpness are segmented with an algorithm based on pixel aggregation and local textural information.Résumé. Cet article décrit une méthode précise et fiable de segmentation pour des images RM des tumeurs de foie. Les approches traditionnelles de segmentation d'images ne donnent pas de bons résultats dans ce cas-là,à cause de deux caractéristiques particulières des données d'entrée : l'inhomogénéité de la texture intratumorale et l'apparence floue de la paroi des tumeurs. Pour détecter la région d'intérêt, nous créons une carte des contours de la tumeur en utilisant une technique de multi-seuillage et une mesure de similarité entre les contours successifs. Les tumeurs qui présentent des contours flous de contraste variable sont détectées avec un algorithme basé sur l'agrégation des pixels et sur l'information locale de texture.

Automatic bone segmentation and bone-cartilage interface extraction for the shoulder joint from magnetic resonance images

“…Graichen et al (2000) constructed 3D models of the humerus, clavicle and scapula for motion analysis using a region-growing based semi-automatic segmentation method followed by shape-based interpolation from 2D MR images acquired on a 0.2 T scanner; qualitative or quantitative validation on the segmentation accuracy was not reported. Branzan-Albu et al segmented the humerus and scapula from 2D MR images using the isolabel method originally developed for tumour segmentation (Branzan Albu et al 2002) to obtain smooth 3D surface reconstructions of bone elements of the shoulder; segmentation accuracy was not reported. Nhat Tan et al (2007) extended this work by proposing a semi-automatic method using combined region-based and gradient-based supervised segmentation which was applied to contour delineation of the humerus from 2D T1-weighted images acquired at 1.5 T. An area overlap ratio of 96.32% between the semi-automated measures and manual segmentations by a radiologist was achieved on 60 slices.…”

Skalpel-Ict: Simulation Kernel Applied to the Planning and Evaluation of Image-Guided Cryotherapy

“…The radiologist is asked to select one single reference pixel located inside the tumour. Tumours with "blurred" contours of variable sharpness are detected with a pixel aggregation algorithm based on local texture information [2] (see Figure 1c). …”

Integrating region and edge information for the automatic segmentation of interventional magnetic resonance images of the shoulder complex

“…In a first step, Sobel operators [11] are used to compute the horizontal and vertical firstorder image derivatives. The convolution of the 3x3 Sobel masks (see Figure 5) with the original image generate one image for the horizontal derivative (Bx) and one image(B y ) for the vertical derivative, as follows : Since the two Sobel masks slide over the entire image, the values of the first-order partial derivatives are computed in a pixelwise manner.…”

“…A segmentation technique for 2-D interventional MR images of liver tumours is presented in [11]. This technique integrates edge and region information in order to detect textured liver tumours with blurred boundaries of non-uniform sharpness.…”