Multimodality CAD: combination of computerized classification techniques based on mammograms and 3D ultrasound volumes for improved accuracy in breast mass characterization

Abstract

Mammography and ultrasound (US) are two low-cost modalities that are commonly used by radiologists for evaluating breast masses and making biopsy recommendations. The goal of this study was to investigate computerized methods for combining information from these two modalities for mass characterization. Our data set consisted of 3D US images and mammograms of biopsy-proven solid breast masses from 60 patients. Thirty of the masses were malignant and 30 were benign. The US volume was obtained by scanning with an experimental 3D US image acquisition system. After computerized feature extraction from the 3D US images and mammograms, we investigated three methods (A, B and C) for combining the image features or classifier scores from different mammographic views and the US volumes. The classifier scores were analyzed using the receiver operating characteristic (ROC) methodology. The area A z under the ROC curve of the classifier based on US alone was 0.88±0.04 for testing Two classifiers were designed using the mammograms alone, with test A z values of 0.85±0.05 and 0.87±0.05, respectively. The test accuracy of combination methods A, B, and C were 0.89±0.04, 0.92±0.03, and 0.93±0.03, respectively. Our results indicate that combining the image features or classifier scores from the US and mammographic classification methods can improve the accuracy of computerized mass characterization.

Optimized approach to decision fusion of heterogeneous data for breast cancer diagnosis

“…12 There has been considerable CAD and CADx research based upon a rich variety of modalities and sources of medical information, such as: digitized screen-film mammograms, [13][14][15][16][17] full-field digital mammograms, 18 sonograms, [19][20][21] magnetic resonance imaging ͑MRI͒ images, 22 and gene expression profiles. 23 Current clinically implemented CADx programs tend to use only one information source, although multimodality CADx programs 24 are beginning to emerge. Moreover, most CADx research has been performed using relatively homogeneous data sets collected at one institution, acquired using one type of digitizer or digital detector, or using features drawn from one source such as human-interpreted findings versus computerextracted features.…”