On local active contour model for automatic detection of tumor in MRI and mammogram images

Abstract

Tumor segmentation in medical images is an important step to determine and predict the stage, size and progression of tumors in realistic geometries and may be used for diagnosis and treatment follow-up in MRI and mammogram images. Automating this challenging task helps radiologists to reduce the high manual workload of brain or breast cancer analysis. Detecting tumor in medical images means to quantify the structure contents of the tumor. In this paper, we propose a model for quantifying the structure contents of the tumor in MRI and mammogram images. The proposed model is based on optimized Laplacian of Gaussian, which is useful in smoothing the homogeneous region and highlight the boundaries of the tumor structure. The proposed model uses local intensity information in later stage of segmentation as image data fitting. For this purpose, local Gaussian distribution is used for fitting image data and is combined with level set function. Due to usage of local intensities and level set, the proposed model is able to deal with intensity inhomogeneity and capture different topologies. To stop the leakage of contour at the boundary of tumor, we take some geometrical points near the tumor's boundary and introduce a distance constraint in model. The gradient flow equation and other optimal values are obtained through minimization of the energy functional. The gradient flow equation is solved by using additive operator splitting method. The experimental results of the proposed model are validated by comparing it with existing state of the art models both qualitatively and quantitatively. The proposed model achieves average values of 99.96%, 99.88%, 99.91%, 99.91%, 99.95% for Jaccard similarity, dice coefficient, accuracy, sensitivity and specificity respectively, which are better than the existing models in comparison.