Meeting Banner
Abstract #1743

A New Computer-Aided Algorithm for Comparing Apparent Diffusion Coefficient (ADC) Mapping and Dynamic Contrast-Enhanced (DCE) MRI Using Pharmacokinetic Model for Breast Tumor Classification

Yeun-Chung Chang1, Yan-Hao Huang2, Chin-Ho Lin2, Chiun-Sheng Huang3, Jeon-Hor Chen4, Ruey-Feng Chang2

1Department of Medical Imaging, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan, Taiwan; 2Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan, Taiwan; 3Department of Surgery, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan, Taiwan; 4Tu and Yuen Center for Functional Onco-Imaging and Department of Radiological Science, University of California Irvine, Irvine, CA, United States

To compare the performance of a new computer-aided algorithm for the dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and the diffusion-weighted magnetic resonance imaging (DWI) in differentiating benign from malignant breast lesions.

Abstract PDF Poster PDF

Keywords

accuracy aided alone analyzed apparent applied applying appropriate assist averaging backward benign best better biopsy breast cancer channel chin classification classifying coefficient coil college comparing compartment computed computer contour contrast dataset dedicated derived detection diagnose diagnostic differentiate differentiating diffusion discriminating distribution dynamic elimination engineering enhanced especially evaluate evaluating evaluation extension extracted feature features functional growing helps heterogeneity hospital identification improved increasing indexes inside item larger largest lesion lesions limitation malignant manual mapped mapping maps medical medicine might minimize model much national partridge performance placing poor potential presumed prior process proposed proved radiological registration relationship relatively robust scanner science seed segment segmented selection sensitivity specificity stratified surgery table tumor tumors type useful usefulness white