%0 Journal Article
%T Feature Selection for the Automated Detection of Metaphase Chromosomes: Performance Comparison Using a Receiver Operating Characteristic Method
%A Yuchen Qiu
%A Jie Song
%A Xianglan Lu
%A Yuhua Li
%A Bin Zheng
%A Shibo Li
%A Hong Liu
%J Analytical Cellular Pathology
%D 2014
%R 10.1155/2014/565392
%X Background. The purpose of this study is to identify a set of features for optimizing the performance of metaphase chromosome detection under high throughput scanning microscopy. In the development of computer-aided detection (CAD) scheme, feature selection is critically important, as it directly determines the accuracy of the scheme. Although many features have been examined previously, selecting optimal features is often application oriented. Methods. In this experiment, 200 bone marrow cells were first acquired by a high throughput scanning microscope. Then 9 different features were applied individually to group captured images into the clinically analyzable and unanalyzable classes. The performance of these different methods was assessed by a receiving operating characteristic (ROC) method. Results. The results show that using the number of labeled regions on each acquired image is suitable for the first on-line CAD scheme. For the second off-line CAD scheme, it would be suggested to combine four feature extraction methods including the number of labeled regions, average regions area, average region pixel value, and the standard deviation of either region distance or circularity. Conclusion. This study demonstrates an effective method of feature selection and comparison to facilitate the optimization of the CAD schemes for high throughput scanning microscope in the future. 1. Introduction Chromosome imaging and karyotyping is an important and widely used clinical method for the diagnosis of genetic related diseases and cancers [1¨C3]. For this technique, identifying a sufficiently large number of pathologically analyzable metaphase chromosomes is critically important for the final accuracy of cancer diagnosis and residual cancer cell detection. At present, the chromosome identification is a two-step semiautomatic procedure [4]. Commercialized automatic scanners first scan and locate the clinically useful cells under low magnification state (i.e., 10x objective lens). Second, clinicians have to manually move back to these detected locations again for high resolution image acquisition (i.e., under 100x objective lens), which is labor intensive and time consuming. In addition, it also creates substantial interobserver variation due to the bias of cell selection (i.e., the tendency towards selecting cells with good morphology). Therefore, the automatic scanning techniques are proposed and developed in the last 20 years, in an attempt to reduce the cliniciansĄŻ workload and improve the diagnostic accuracy and consistency [5]. Recently, a new high
%U http://www.hindawi.com/journals/acp/2014/565392/