In this growing technological world still disease are challenging human life. Especially the breast cancer stands the leading causes of mortality in women. Early diagnosis helps for better treatment and increase survival rate. Mammography is one among the methods to detect the breast cancer at an early stage. Some of the signs of breast cancer are clusters of micro calcifications, mass lesion, architectural distortion or asymmetry of the breast. In this paper, we focus only on mass lesion. Computer aided detection (CAD) and computer aided diagnosis (CADx) are tools to recognize abnormality at an early stage. These tools help radiologists to locate and evaluate mammographic abnormality and serve as a useful second opinion to diagnose the missed malignant cases and reduce unnecessary biopsies.
Keywords: Mass, Computer aided detection, Computer aided diagnosis, and Computer aided mammography.
[...] Monika Shinde: Computer aided diagnosis in digital mammography : classification of mass and normal tissue, M. S. Dissertation, University of South Florida Nicholas Jabari Lee: Computer- aided diagnostic systems for digital mammograms, M.S. Dissertation, B.S., Jackson State University, December Giovanni Luca Masala, “Computer Aided Detection on Mammography”, Proceedings of World Academy of Science, Enginering and Technology, Volume 15, October 2006. Polakowski WE, Cournoyer DA, Rogers SK, DeSimio MP, Ruck DW, Hoffmeister JW, Raines RA , “Computer-Aided Breast Cancer Detection and Diagnosis of Masses using Difference of Gaussians and Derivative-based Feature Saliency”, IEEE transactions on medical imaging, vol. [...]
[...] Since the shapes of masses are crucial in classification between benignancy and malignancy, four shape features are further generated and joined with the five features previously used in mass detection to be implemented in another PNN for mass classification. Obtained a Az = 0.6432 on average. Ibrahim et al., proposed a system that extracts some features from the breast tissue of digital mammogram image. Then, the discrimination power of these features is tested to avoid using non-classifying features in order to minimize the classification error. [...]
[...] The Block diagram of the CAD system is shown in figure for the diagnosis of masses consist of three stages: segmentation of mass boundary in ROI, feature extraction, and classification. In the segmentation stage, the mass is segmented from the background normal tissue. The segmentation of mass is extremely important as the success of the classification algorithm depends on this stage. The two major categories of segmentation methods are region growing and discrete contour models. Following this, features which capture the differences between malignant and benign masses are extracted. [...]
[...] The system performances have been evaluated terms of the ROC analysis, obtaining Az = 0.80 0.04 as the estimated area under the ROC curve COMPUTER-AIDED DIAGNOSTIC SYSTEMS Shinde developed an automated mass classification system for breast cancer screening and diagnosis for Digital Mammogram applications. In this work the Expectation Maximization method is developed and applied to mammograms with the aim of segmenting normal tissue from mass tissue. Both the raw data and summary data generated by Laws' texture analysis are investigated. [...]
[...] The development of this model, namely GAwNN to reduce the diagnosis time as well as increasing the accuracy percentage in classifying mass in breast to either benign, or malignant. Table illustrates the comparision among the techniques that have been employed in each stage of CAD/ CADx CONCLUSION This paper reviews a number of mass CAM systems proposed by various researchers. Basically CAM consists of two subsystems: CAD and CADx as discussed. Generally the CAD/CADx system composed of four steps namely, pre-processing, segmentation/detection, feature extraction and classification. [...]
Online readingwith our online reader
Content validatedby our reading committee