Normalization of multicolor fluorescence in situ hybridization (M‐FISH) images for improving color karyotyping

Abstract

Background: Multiplex or multicolor fluorescence in situ hybridization (M-FISH) is a recently developed cytogenetic technique for cancer diagnosis and research on genetic disorders. By simultaneously viewing the multiply labeled specimens in different color channels, M-FISH facilitates the detection of subtle chromosomal aberrations. The success of this technique largely depends on the accuracy of pixel classification (color karyotyping). Improvements in classifier performance would allow the elucidation of more complex and more subtle chromosomal rearrangements. Normalization of M-FISH images has a significant effect on the accuracy of classification. In particular, misalignment or misregistration across multiple channels seriously affects classification accuracy. Image normalization, including automated registration, must be done before pixel classification. Methods and Results:We studied several image normalization approaches that affect image classification. In particular, we developed an automated registration technique to correct misalignment across the different fluor images (caused by chromatic aberration and other factors). This new registration algorithm is based on wavelets and spline approximations that have computational advantages and improved accuracy. To evaluate the performance improvement brought about by these data normalization approaches, we used the downstream pixel classification accuracy as a measurement. A Bayesian classifier assumed that each of 24 chromosome classes had a normal probability distribution. The effects that this registration and other normalization steps have on subsequent classification accuracy were evaluated on a comprehensive M-FISH database established by Advanced Digital Imaging Research (http://www.adires.com/05/Project/ MFISH_DB/MFISH_DB.shtml). Conclusions: Pixel misclassification errors result from different factors. These include uneven hybridization, spectral overlap among fluors, and image misregistration. Effective preprocessing of M-FISH images can decrease the effects of those factors and thereby increase pixel classification accuracy. The data normalization steps described in this report, such as image registration and background flattening, can significantly improve subsequent classification accuracy. An improved classifier in turn would allow subtle DNA rearrangements to be identified in genetic diagnosis and cancer research. © 2005 Wiley-Liss, Inc.Key terms: classification; registration; translocation; wavelets; chromosome image analysis; fluorescence in situ hybridization; automated cytogeneticsThe progress of cytogenetics has become significantly faster since the discovery of chromosome banding and molecular fluorescence in situ hybridization (FISH) techniques (1-8). FISH-based methodologies greatly enhance the detection of genetic abnormalities in normal and cancer cells. Multiplex FISH (M-FISH) of human chromosomes is based on the simultaneous hybridization of a pool of 24 chromosome-specific probes (3). Figure 1 is an M-FISH image dataset that is ...

Semi unsupervised M-FISH chromosome image classification

“…The performance was measured by means of accuracy: Acc = #of correctly chromosome classified pixels . (8) total # of chromosome pixels An example of the application of our method with/without normalizing the features is illustrated in Fig. 3.…”

Classification of multi-spectral florescence in situ hybridization images with fuzzy clustering and multiscale feature selection

“…Among them, Bayesian classifier is widely used and implemented in commercial software packages [3]. We introduce a more sophisticated model based on fuzzy clustering.…”

“…Especially, the redundancy between multiple spectral channels could cause the subsequent classification to be less accurate [3]. In the paper, we introduce a novel approach to perform feature selection that combines the advantage of conventional principal component analysis (PCA) with an un-decimated wavelet transform.…”

“…In the paper, we introduce a novel approach to perform feature selection that combines the advantage of conventional principal component analysis (PCA) with an un-decimated wavelet transform. In the classification procedure, the Bayesian classifier has been widely used and implemented in commercial software pack- ages [3]. We proposed a more accurate model that is based on the fuzzy clustering [2].…”

Classification of multicolor fluorescence in-situ hybridization (M-FISH) image using regularized multinomial logistic regression

“…In classification, some researchers used pixel by pixel method [4] while others used region-based classifier [3]by considering the relationship of neighboring pixels. We have developed Bayesian classifier [5], adaptive fuzzy cmeans (AFCM) method [6] and sparse representations based classifier [7]. However, all the classification accuracy is less than 90%, impractical for clinical use.…”