Comparative Analysis of Region of Interest of Different Sizes for Breast Density Classifcation
Journal Title: International Journal of Medical Research & Health Sciences (IJMRHS) - Year 2017, Vol 6, Issue 3
Abstract
In medical feld, radiologists are more interested in region of interest (ROI) rather than whole image. ROI is a subpart of the image that contains very important information related to the diagnosis. In addition, ROI size has been known to influence the sensitivity and specifcity of the classifcation. Many researchers in the past have used ROI for texture analysis of fatty and dense mammogram. Since a ROI is used as ‘representative’ of the image and all further computations and diagnosis depends upon the ROI, therefore, it is very crucial to select an appropriate image area as ROI. In this work, experiments have been conducted to fnd the appropriate size of ROI for breast density classifcation. Comparison of different ROI sizes 50 × 50, 75 × 75, 100 × 100, 125 × 125, 150 × 150, 175 × 175, 200 × 200, 225 × 225, 250 × 250, 275 × 275 and 300 × 300 pixels for breast density classifcation has been done. Different texture models have been used to extract features from these ROIs to have reliable analysis for appropriate size of the ROI. The effect of ROI size is evaluated in terms of the performance of differentiating between the fatty and dense breast tissue. For carrying out the experiments standard publicly available mini-MIAS database has been used. After the analytical study, it has been observed that a square shaped ROI having size of 200 × 200 pixels is optimal and it should be taken from the central breast region immediately behind the nipple, as this region is the densest region of the breast excluding pectoral muscle. The optimal ROI size also reduces the computational cost in extracting the texture features from the small sized ROI. The experimental results encourage the use of 200 × 200 pixels ROI for the classifcation of breast density.
Authors and Affiliations
Vipul Sharma| Department of Computer Science and Engineering, DAV University, Jalandhar, India, Corresponding e-mail: vipuls85@gmail.com
Localization of Impacted Maxillary Canines and Root Resorption of Neighbouring Latral Incisor Using Cone Beam Computed Tomography
Canine impaction is one of the most prevalent impactions and it affects aesthetic and function of the oral cavity. Recent advances in 3D imaging has provided new facilities for precise localization of the impacted teeth...
EARLY DETECTION OF CRITICAL CONGENITAL HEART DISEASE IN NEWBORNS USING PULSE OXIMETRY SCREENING
Background: Congenital heart diseases which are dependent on the ductusarteriosus to maintain adequate oxygenation or systemic blood flow are termed as a critical congenital heart disease (CCHD). Delay in the diagnosis...
RETAINED STONE PIECE IN ANTERIOR CHAMBER: A CASE REPORT
Background: Anterior segment foreign bodies are un-common, making up only about 32% of all intraocular foreign bodies. The present case report aims to study the effects of foreign bodies in the anterior chamber. Case R...
Assessment of disk diffusion and E-test methods to determine antimicrobial activity of cefalotin and vancomycin on clinical isolates of Staphylococcus aureus
The present investigation aims to find a specific method to test the clinical isolates of Staphylococcus aureus in terms of antimicrobial susceptibility and resistance to two drugs of cefalotin and vancomycin using E-te...
Evaluation of antibacterial effects of Withania coagulans and Cynara cardunculus extracts on clinical isolates of Brucella strains
Brucellosis is a common illness zoonotic and transmitted by eating infected food products. Medicinal plants are considered as new sources for the production of agents that can act as alternatives to antibiotics in the t...