Abstract
According to the American Cancer Society's forecasts for 2019, there will be about 268,600 new cases in the United States with invasive breast cancer in women, about 62,930 new noninvasive cases, and about 41,760 death cases from breast cancer. As a result, there is a high demand for breast imaging specialists as indicated in a recent report for the Institute of Medicine and National Research Council. One way to meet this demand is through developing Computer-Aided Diagnosis (CAD) systems for breast cancer detection and diagnosis using mammograms. This study aims to review recent advancements and developments in CAD systems for breast cancer detection and diagnosis using mammograms and to give an overview of the methods used in its steps starting from preprocessing and enhancement step and ending in classification step. The current level of performance for the CAD systems is encouraging but not enough to make CAD systems standalone detection and diagnose clinical systems. Unless the performance of CAD systems enhanced dramatically from its current level by enhancing the existing methods, exploiting new promising methods in pattern recognition like data augmentation in deep learning and exploiting the advances in computational power of computers, CAD systems will continue to be a second opinion clinical procedure.
Highlights
Cancer is a disease that occurs when abnormal cells grow in an uncontrolled manner in a way that disregards the normal rules of cell division, which may cause uncontrolled growth and proliferation of the abnormal cells. is can be fatal if the proliferation is allowed to continue and spread in such a way that leads to metastasis formation. e tumor is called malignant or cancer if it invades surrounding tissues or spreads to other parts of the body [1]
A recent study [29] and an older study [30] showed that the detection rate of double reading was not statistically different from the detection rate of a single reading in digital mammograms and the double reading is not a costeffective strategy in digital mammography. e inconsistency in the results shows that there is a need for further studies in this area
We shed some light on Computer-Aided Diagnosis (CAD) methods used in breast cancer detection and diagnosis using mammograms
Summary
Cancer is a disease that occurs when abnormal cells grow in an uncontrolled manner in a way that disregards the normal rules of cell division, which may cause uncontrolled growth and proliferation of the abnormal cells. is can be fatal if the proliferation is allowed to continue and spread in such a way that leads to metastasis formation. e tumor is called malignant or cancer if it invades surrounding tissues or spreads to other parts of the body [1]. E main difference between CADe and CADx is that CADe stands for Computer-Aided Detection system, in which CADe systems do not present the radiological characteristics of tumors but help in locating and identifying possible abnormalities in the image and leaving the interpretation to the radiologist. Like any other algorithm for a classification problem, the CAD system can be divided into three distinct areas: feature extraction, feature selection, and classification methodologies On top of these three major areas, CAD systems depend heavily on an image enhancement step to prepare the mammogram for further analysis. We are presenting the developments of CAD methods used in breast cancer detection and diagnosis using mammograms, which include preprocessing and contrast enhancement, features extraction, features selection, and classification methods. We are presenting the developments of CAD methods used in breast cancer detection and diagnosis using mammograms, which include preprocessing and contrast enhancement, features extraction, features selection, and classification methods. e rest of the paper will be organized based on the schema in Figure 1 as follows: Section 2 presents the preprocessing and enhancement step, Section 3 discusses features selection and features extraction step, Section 4 is devoted to discussing classification through classifiers and combined classifiers, and Section 5 presents the conclusions
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
