Evaluation and visual exploratory analysis of DCE-MRI data of breast lesions based on morphological features and novel dimension reduction methods

Authors:
Sylvain Lespinats;Anke Meyer-Baese;Frank Steinbrücker;Thomas Schlossbauer
Affiliations:
CEA, LIST, Multisensor Intelligence and Machine Learning Laboratory, Gif-sur-Yvette, France;Department of Electrical and Computer Engineering, Florida State University, Tallahassee, FL;Department of Computer Science, University of Bonn, Germany;Department of Radiology, University of Munich, Germany
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 9
Cited 0

Pattern Recognition, Third Edition

Pattern Recognition, Third Edition
3D Content-Based Search Based on 3D Krawtchouk Moments

3DPVT '06 Proceedings of the Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT'06)
Geometric moment invariants

Pattern Recognition
A Nonlinear Mapping for Data Structure Analysis

IEEE Transactions on Computers
RankVisu: Mapping from the neighborhood network

Neurocomputing
Three-dimensional shape searching: state-of-the-art review and future trends

Computer-Aided Design
Image analysis by Krawtchouk moments

IEEE Transactions on Image Processing
Curvilinear component analysis: a self-organizing neural network for nonlinear mapping of data sets

IEEE Transactions on Neural Networks
DD-HDS: A Method for Visualization and Exploration of High-Dimensional Data

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Visual exploratory data analysis represents a well-accepted imaging modality for high-dimensional DCE-MRI-derived breast cancer data. We employ this paradigm for discriminating between malignant and benign lesions based on different shape descriptors thanks to proven and novel dimension reduction algorithms. We demonstrate that shape descriptors based on moments emphasizing local shape structure changes such as weight ed 3D Krawtchouk moments outperform global averaging moments such as geometric moment invariants in terms of discrimination of benign/malignant lesions. The best visualization of tumor shapes in a two-dimensional space is achieved based on nonlinear mapping methods, especially the ones that consider neighborhood ranks.