Learn More
In this paper we investigate a new approach to the classification of mammographic images according to breast type. The classification of breast density in this study is motivated by its use as prior knowledge in the image processing pipeline. By utilising this knowledge at different stages including enhancement, segmen-tation and feature extraction, its(More)
The main aim of this paper is to propose a novel set of metrics that measure the quality of the image enhancement of mammographic images in a computer-aided detection framework aimed at automatically finding masses using machine learning techniques. Our methodology includes a novel mechanism for the combination of the metrics proposed into a single(More)
In this paper we study the identification of masses in digital mammograms using texture analysis. A number of texture measures are calculated for bilateral difference images showing regions of interest. The measurements are made on co-occurrence matrices in four different direction giving a total of seventy features. These features include the ones proposed(More)
BACKGROUND The discrepancy between minimal disease on biopsy and disease found in the subsequent prostatectomy specimen, in terms of the size and grade of tumor, extracapsular extension or positive margins, led several authors to dispute the existence of clinically insignificant impalpable tumors of the prostate. However, considering that prostate-specific(More)
Endometriosis of the urinary tract is infrequent. The ureters and kidneys are the least usual place of localization. Endometriosis of the ureter often leads to silent loss of renal function due to delayed diagnosis. We report a case of a premenopausal female with endometriosis of the left distal ureter, presenting an infection of the urinary tract and(More)
  • 1