Abstract

The problem of extracting spots from DNA microarrays is a problem of considerable scientific and economic utility. In this paper we introduce a new approach based on a scale-space analysis of the image. We augment this with a machine learning system that guides an operator by classifying spots into those that require further attention and those that are already segmented correctly. We compare conventional k-nearest neighbor techniques with generalized linear models and multilayer perceptrons using confidence intervals and McNemar's test.
Original languageEnglish
Pages2934-2939
Number of pages6
DOIs
Publication statusPublished - 2003
EventProceedings of the IEEE/INNS International Joint Conference on Artificial Neural Networks (IJCNN-2003) - Portland, OR
Duration: 20 Jul 200324 Jul 2003

Conference

ConferenceProceedings of the IEEE/INNS International Joint Conference on Artificial Neural Networks (IJCNN-2003)
CityPortland, OR
Period20/07/0324/07/03

Cite this