Leveraging data complexity: Pupillary behavior of older adults with visual impairment during HCI
ACM Transactions on Computer-Human Interaction (TOCHI)
ISBRA'07 Proceedings of the 3rd international conference on Bioinformatics research and applications
A multifractal wavelet model with application to network traffic
IEEE Transactions on Information Theory
A 2D wavelet-based multiscale approach with applications to the analysis of digital mammograms
Computational Statistics & Data Analysis
| Hi-index | 0.00 |
Breast cancer is the second leading cause of death in womenin the United States. Breast Magnetic Resonance Imaging (BMRI) is anemerging tool in breast cancer diagnostics and research, and it is becomingroutine in clinical practice. Recently, the American Cancer Society(ACS) recommended that women at very high risk of developing breastcancer have annual BMRI exams, in addition to annual mammograms, toincrease the likelihood of early detection. (Saslow et al. [20]). Many medicalimages demonstrate a certain degree of self-similarity over a rangeof scales. The multifractal spectrum (MFS) summarizes possibly variabledegrees of scaling in one dimensional signals and has been widelyused in fractal analysis. In this work, we develop a generalization of MFSto three dimensions and use dynamics of the scaling as discriminatorydescriptors for the classification of BMRI images to benign and malignant.Methodology we propose was tested using breast MRI images forfour anonymous subjects (two cancer, and two cancer-free cases). Thedataset consists of BMRI scans obtained on a 1.5T GE Signa MR (withVIBRANT) scanner at Emory University. We demonstrate that meaningfuldescriptors show potential for classifying inference.