On fully automatic feature measurement for banded chromosome classification

Abstract

Procedures for fully automatic location of chromosome axis and centromere in metaphase chromosomes are described for a practical interactive chromosome analysis system that omits the usual stages of interactive axis and centromere correction. Accuracy of centromere finding and consequential determination of a chromosome's polarity, i.e., which end is which, is measured experimentally. The saving in interaction by not correcting centromeres is compared to the increase in errors at the classification stage and the consequent increase in interaction needed to correct these errors. Some previously unreported features for banded chromosome classification are described, and in particular a set of global shape features is introduced. The discrimination capability of the feature measurements is evaluated by use of simple statistics and by reference to the performance of classifiers trained with various feature subsets. Class discrimination capability of the global shape feature set is shown to be comparable to that of centromere position, a widely used local shape feature. The variability of feature measurements that might occur in data from different laboratories on account of differing tissue, preparation methods, and digitiser hardware is assessed using three data bases of G‐banded human metaphase cells. It is shown that the differences can be considerable and that appropriate feature selection and classifier training substantially improve classification performance.

Karyotyping of comparative genomic hybridization human metaphases by using support vector machines

“…Conventional chromosome classification is based on complex feature extraction procedures (1,2). However, the features of CGH images are quite different from those of G-banded images.…”

“…The centromere of a chromosome is determined as the position on the medial axis with the largest average gray value. If the largest value is zero, the centromere is found using the method described by Piper and Granum (2). Then, the end of the short arm is determined and the profiles are arranged in the same order.…”

“…Usually, a human chromosome is characterized by its size, banding pattern, and centromere position (1,2). Density profiles and width profiles are generated to represent these characteristics (1).…”

Automatic scoring of sister chromatid exchanges by image analysis in a dose response experiment

“…Chromosome axes, "shape" profiles, and centromeres were found by the methods described by Piper and Granum [1989]. Additionai "half-profiles" of integrated density on either side of the axis were computed.…”

Automatic chromosome pairing using mutual information

“…For instance, the most widely used commercial packages available for cytogenetic analysis like Leica TM , Metasystems TM and Cytovision TM are still very ineffective with respect to chromosome classification and/or pairing. In fact, the problem of the automated chromosome classification has been an active field of research in the last 20 years and it still is an open problem [2]- [7]. This paper is focused in the specific task of pairing in the scope of karyotyping procedure.…”