On detecting abnormalities in digital mammography

Abstract

Breast cancer is the most common cancer in many countries all over the world. Early detection of cancer, in either diagnosis or screening programs, decreases the mortality rates. Computer Aided Detection (CAD) is software that aids radiologists in detecting abnormalities in medical images. In this article we present our approach in detecting abnormalities in mammograms using digital mammography. Each mammogram in our dataset is manually processed-using software specially developed for that purpose-by a radiologist to mark and label different types of abnormalities. Once marked, processing henceforth is applied using computer algorithms. The majority of existing detection techniques relies on image processing (IP) to extract Regions of Interests (ROI) then extract features from those ROIs to be the input of a statistical learning machine (classifier). Detection, in this approach, is basically done at the IP phase; while the ultimate role of classifiers is to reduce the number of False Positives (FP) detected in the IP phase. In contrast, processing algorithms and classifiers, in pixel-based approach, work directly at the pixel level. We demonstrate the performance of some methods belonging to this approach and suggest an assessment metric in terms of the Mann Whitney statistic.

Method and System for Image Analysis to Detect Cancer

“…2.3.2) rather than our featureless pixel-based approach. We have reported in [13] the accuracy of the KNN classifier measured in AUC for some of these approaches including IRIS filter and template matching. Our feature-less pixel-based approach along with the KNN classifier is the overall winner among all other features and classifiers.…”

“…To fulfill the three objectives just mentioned above, we launched this project in which we were able to design a novel method (a set of algorithms) and a novel system (software architecture) detailed in this article. Some results of early stages of this project had been published in [13][14][15]. The present article is the main publication of the project, and is almost selfcontained, where all algorithms and experiments are detailed.…”

“…For the assessment of pixel based methods, in [13] we suggested the use of the MannWhitney statistic directly on the score image before postprocessing. The AUC of a score image is defined as…”

Matlab vs. OpenCV: A Comparative Study of Different Machine Learning Algorithms

“…The motivation behind the present article was a real life project for developing a Computer Aided Detection (CAD) to detect breast cancer in digital mammograms [12,1]. Using Matlab was extremely efficient in trying dozens of machine learning and image processing algorithms.…”