Cart (Loading....) | Create Account
Close category search window
 

Head and neck cancer metastasis prediction via artificial neural networks

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Darby, E. ; Dept. of Comput. Sci., Houston Univ., TX, USA ; Nettimi, T. ; Kodali, S. ; Shih, L.

Cancers in head and neck tends to spread to nearby lymph nodes. Lymph nodes trap the spreading tumor cells but then the tumor starts to grow in these nodes and then spread further. Our project is aimed to (1) predict the secondary regions of lymph nodes where a given primary tumor can metastasize, and (2) to generalize a pattern for lymph nodes metastasis of head and neck cancer by using artificial neural networks (ANN). The raw data for the analysis is provided by Dr. Lincoln Gray, Acta Otolaryngologica 2000, of 130 cases of pathologically-positive oral squamous cell carcinoma (SCC) from UK. Seven primary sites for tumors are identified: 1) buccal mucosa, 2) tongue, 3) retromolar trigone, 4) floor of mouth, 5) ventral tongue, 6) oropharynx, 7) lower alveolus. Ten secondary regions of lymph nodes metastasis are observed: five regions each on the same/opposite side (ipsilateral/contralateral) as the primary tumor site. In our oral squamous cell carcinoma study using ANN, we explore data analysis approach with two ANN methods: (1) a supervised multilayer feed forward back propagation (back-prop) method, and (2) an unsupervised self organizing map (SOM) method. This experience provides insight into implementation of ANN and directions to future investigation. The results from back-prop are comparable to that using multidimensional scaling (MDS) with respect to prediction of lymph nodes that have highest percentage of being metastasized, while SOM requires further work to identify clustering for individual primary cancer as well as next level of lymph node metastases.

Published in:

Computational Systems Bioinformatics Conference, 2005. Workshops and Poster Abstracts. IEEE

Date of Conference:

8-11 Aug. 2005

Need Help?


IEEE Advancing Technology for Humanity About IEEE Xplore | Contact | Help | Terms of Use | Nondiscrimination Policy | Site Map | Privacy & Opting Out of Cookies

A not-for-profit organization, IEEE is the world's largest professional association for the advancement of technology.
© Copyright 2014 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.