Diagnose the premalignant pancreatic cancer using high dimensional linear machine

Authors:
Yifeng Li;Alioune Ngom
Affiliations:
School of Computer Sciences, University of Windsor, Windsor, Ontario, Canada;School of Computer Sciences, University of Windsor, Windsor, Ontario, Canada
Venue:
PRIB'12 Proceedings of the 7th IAPR international conference on Pattern Recognition in Bioinformatics
Year:
2012

Citing 10
Cited 0

Matrix computations (3rd ed.)

Matrix computations (3rd ed.)
An introduction to ROC analysis

Pattern Recognition Letters - Special issue: ROC analysis in pattern recognition
Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)
Multicategory Classification Using An Extreme Learning Machine for Microarray Gene Expression Cancer Diagnosis

IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
A review of feature selection techniques in bioinformatics

Bioinformatics
Robust Face Recognition via Sparse Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face recognition breakthrough

Communications of the ACM - A Blind Person's Interaction with Technology
Ensemble-based classifiers

Artificial Intelligence Review
Gene and sample selection for cancer classification with support vectors based t-statistic

Neurocomputing
Semi-Supervised Learning

Semi-Supervised Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

High throughput mass spectrometry technique has been extensively studied for the diagnosis of cancers. The detection of the pancreatic cancer at a very early stage is important to heal patients, but is very difficult due to biological and computational challenges. This paper proposes a simple classification approach which can be applied to the premalignant pancreatic cancer detection using mass spectrometry technique. Computational experiments show that our method outperforms the benchmark methods in accuracy and sensitivity without resorting to any biomarker selection, and the comparison with previous works shows that our method can obtain competitive performance.