DNA: Directional Neighborhood Analysis for Detection of Breast Masses in Screening Mammograms

摘要

We introduce a computer-assisted detection (CAD) system for the automated detection of breast masses in screeningmammograms. The system targets the directional behavior of the neighborhood pixels surrounding a referenceimage pixel. The underlying hypothesis is that in the presence of a mass the directional properties of the breast tissuesurrounding the mass should be altered. The hypothesis was tested using a database of 1,337 mammographic regionsof interest (ROIs) extracted from DDSM mammograms. There were 681 ROIs containing a biopsy-proven masscentered in the ROI (340 malignant, 341 benign) and 656 ROIs depicting normal breast parenchyma. Initially, eightmain directional propagations were identified and modeled given the center of the ROI as the reference pixel.Subsequently, eight novel morphological features were extracted for each direction. The features were designed tocharacterize the disturbance occurring in normal breast parenchyma due to the presence of a mass. Finally, theextracted features were merged using a back propagation neural network (BPANN). The network served as a nonlinear classifier trained to determine the presence of a mass centered at the reference image pixel. The BPANN wastrained and tested using a leave-one-out sampling scheme. Its performance was evaluated with Receiver OperatingCharacteristics (ROC) analysis. Our CAD system showed an ROC area index of Az=0.88±0.01 for discriminatingmass vs. normal ROIs. Detection performance was robust for both malignant (Az=0.88±0.01) and benign masses(Az=0.87±0.01). Thus, the proposed directional neighborhood analysis (DNA) can be applied effectively to identifysuspicious masses in screening mammograms.