Classification of Fourier transform infrared microscopic imaging data of human breast cells by cluster analysis and artificial neural networks

Lin Zhang; Gary W Small; Abigail S Haka; Linda H Kidder; E Neil Lewis

doi:10.1366/000370203321165151

Back

Classification of Fourier transform infrared microscopic imaging data of human breast cells by cluster analysis and artificial neural networks

Journal article

Peer reviewed

Classification of Fourier transform infrared microscopic imaging data of human breast cells by cluster analysis and artificial neural networks

Lin Zhang, Gary W Small, Abigail S Haka, Linda H Kidder and E Neil Lewis

Applied spectroscopy, Vol.57(1), pp.14-22

01/2003

DOI: 10.1366/000370203321165151

PMID: 14610931

View Online

Abstract

Cluster analysis and artificial neural networks (ANNs) are applied to the automated assessment of disease state in Fourier transform infrared microscopic imaging measurements of normal and carcinomatous immortalized human breast cell lines. K-means clustering is used to implement an automated algorithm for the assignment of pixels in the image to cell and non-cell categories. Cell pixels are subsequently classified into carcinoma and normal categories through the use of a feed-forward ANN computed with the Broyden-Fletcher-Goldfarb-Shanno training algorithm. Inputs to the ANN consist of principal component scores computed from Fourier filtered absorbance data. A grid search optimization procedure is used to identify the optimal network architecture and filter frequency response. Data from three images corresponding to normal cells, carcinoma cells, and a mixture of normal and carcinoma cells are used to build and test the classification methodology. A successful classifier is developed through this work, although differences in the spectral backgrounds between the three images are observed to complicate the classification problem. The robustness of the final classifier is improved through the use of a rejection threshold procedure to prevent classification of outlying pixels.

Algorithms

Breast Neoplasms - chemistry

Breast Neoplasms - classification

Breast Neoplasms - diagnosis

Breast Neoplasms - pathology

Carcinoma, Ductal - chemistry

Carcinoma, Ductal - classification

Carcinoma, Ductal - diagnosis

Carcinoma, Ductal - pathology

Cell Line, Tumor

Cluster Analysis

Diagnosis, Computer-Assisted - methods

Humans

Microscopy - methods

Neural Networks (Computer)

Predictive Value of Tests

Reference Values

Reproducibility of Results

Sensitivity and Specificity

Spectroscopy, Fourier Transform Infrared - methods

Details

Title: Subtitle: Classification of Fourier transform infrared microscopic imaging data of human breast cells by cluster analysis and artificial neural networks
Creators: Lin Zhang - Ohio University, Center for Intelligent Chemical Instrumentation, Department of Chemistry and Biochemistry, Clippinger Laboratories, Athens, Ohio 45701, USA
Gary W Small
Abigail S Haka
Linda H Kidder
E Neil Lewis
Resource Type: Journal article
Publication Details: Applied spectroscopy, Vol.57(1), pp.14-22
DOI: 10.1366/000370203321165151
PMID: 14610931
ISSN: 0003-7028
eISSN: 1943-3530
Language: English
Date published: 01/2003
Academic Unit: Chemistry
Record Identifier: 9984216688702771

Metrics

17 Record Views

47 Times Cited - Web of Science

See more details