MS based nonlinear methods for gastric cancer early detection

  • Authors:
  • Jun Meng;Xiangyin Liu;Fuming Qiu;Jian Huang

  • Affiliations:
  • School of Electrical Engineering, Zhejiang University, Hangzhou, China;School of Electrical Engineering, Zhejiang University, Hangzhou, China;Cancer Institute, The Second Hospital, Medical College of Zhejiang University, Hangzhou, China;Cancer Institute, The Second Hospital, Medical College of Zhejiang University, Hangzhou, China

  • Venue:
  • LSMS/ICSEE'10 Proceedings of the 2010 international conference on Life system modeling and simulation and intelligent computing, and 2010 international conference on Intelligent computing for sustainable energy and environment: Part III
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

The mortality rate of gastric cancer (GC) ranks the 2nd among all types of cancers. The earlier it is diagnosed, the better its curative effect becomes. As a powerful analyzing technique, SELDI-TOF serves as a new approach for Gastric Mass Spectrometry (GMS) based GC early detection. This article has developed a set of nonlinear approaches for GMS to differentiate the normal persons from the GC suffers--the adapted box dimension calculation method and the clustering featured data mining method. Comparing with other popular SELDI-TOF process techniques, such as SVM, neural networks, RPS, etc, their individual particularities and perfect performance in nonlinear problem analysis, especially after featured respective working mechanism adaptation, credible outcome is well expected.