Multi-class Abnormal Breast Tissue Segmentation Using Texture Features and Analyzing the Growth Factor Using Power Law

B. Monica Jenefer^1* and V. Cyrilraj²

¹Computer Science and Engineering, Sathyabama University, Chennai, India. ²Department of Computer Science and Engineering, Dr. M.G. R. Educational and Research Institute, Chennai, India.

ABSTRACT: This paper motivated to design and develop an automatic model for multi-class breast tissue segmentation and find the growth of the cancer in breast mammogram images. Various breast tissues are categorized by a novel texture features such as PTPSA- [Piecewise Triangular Prism Surface Area], intensity difference and regular-intensity in mammogram images. Using CRF-[Classical Random Forest] method segmentation and classification of the features can be obtained in mammogram images. The input image feature values are compared to the ground-truth values for confirming the true positive rate of the proposed approach. Efficacy of abnormal breast tissue segmentation is evaluated using publicly available MIAS training dataset.In this paper, we investigate the consequences of an option, yet just as conceivable, suspicion of tumor growth, to be specific power growth law, acknowledged in direct expand in tumor breadth. We exhibit a simple model for tumor growth, whose global flow demonstrates power law growth of the tumor, much under boundless supplement supply. For corroboration, it is carried out and examined one-, two- and three-dimensional tumor growth tests both in vitro, in MCF-7 cells (breast malignancy cell line) and in vivo, in mouse xenografts.After successful tissue segmentation, the growth of the tissue is analyzed using Power Law. Performance evaluation of the proposed approach can be obtained by comparing the simulation output with the ground truth data. The accuracy of the proposed approach reaches up to 97% for MIAS database in term of tumor detection. Also, simulating radiotherapy under power law, Gompertz and exponential tumor growth, it is indicated that the power law model predicts profoundly diverse conclusions for the usually used treatment. This shows the significance of utilizing the proper tumor growth model when computing ideal measurement fractionation plan for radiotherapy.

KEYWORDS: Breast Cancer; Mammogram Images; Texture Features; Image Classification; MIAS dataset; Power Law Growth

This work is licensed under a Creative Commons Attribution 4.0 International License.