Ranked retrieval of segmented nuclei for objective assessment of cancer gene repositioning

Abstract

BackgroundCorrect segmentation is critical to many applications within automated microscopy image analysis. Despite the availability of advanced segmentation algorithms, variations in cell morphology, sample preparation, and acquisition settings often lead to segmentation errors. This manuscript introduces a ranked-retrieval approach using logistic regression to automate selection of accurately segmented nuclei from a set of candidate segmentations. The methodology is validated on an application of spatial gene repositioning in breast cancer cell nuclei. Gene repositioning is analyzed in patient tissue sections by labeling sequences with fluorescence in situ hybridization (FISH), followed by measurement of the relative position of each gene from the nuclear center to the nuclear periphery. This technique requires hundreds of well-segmented nuclei per sample to achieve statistical significance. Although the tissue samples in this study contain a surplus of available nuclei, automatic identification of the well-segmented subset remains a challenging task.ResultsLogistic regression was applied to features extracted from candidate segmented nuclei, including nuclear shape, texture, context, and gene copy number, in order to rank objects according to the likelihood of being an accurately segmented nucleus. The method was demonstrated on a tissue microarray dataset of 43 breast cancer patients, comprising approximately 40,000 imaged nuclei in which the HES5 and FRA2 genes were labeled with FISH probes. Three trained reviewers independently classified nuclei into three classes of segmentation accuracy. In man vs. machine studies, the automated method outperformed the inter-observer agreement between reviewers, as measured by area under the receiver operating characteristic (ROC) curve. Robustness of gene position measurements to boundary inaccuracies was demonstrated by comparing 1086 manually and automatically segmented nuclei. Pearson correlation coefficients between the gene position measurements were above 0.9 (p < 0.05). A preliminary experiment was conducted to validate the ranked retrieval in a test to detect cancer. Independent manual measurement of gene positions agreed with automatic results in 21 out of 26 statistical comparisons against a pooled normal (benign) gene position distribution.ConclusionsAccurate segmentation is necessary to automate quantitative image analysis for applications such as gene repositioning. However, due to heterogeneity within images and across different applications, no segmentation algorithm provides a satisfactory solution. Automated assessment of segmentations by ranked retrieval is capable of reducing or even eliminating the need to select segmented objects by hand and represents a significant improvement over binary classification. The method can be extended to other high-throughput applications requiring accurate detection of cells or nuclei across a range of biomedical applications.

Spatial quantitation of FISH signals in diploid versus aneuploid nuclei

“…Our results demonstrate that centromere X-2 is found in a similar (i.e., nonrandom) position in both diploid and trisomy-12 nuclei. This is an interesting observation that warrants future studies to determine whether this finding is true for the other euploid chromosomes (1)(2)(3)(4)(5)(6)(7)(8)(9)(10)(11)(13)(14)(15)(16)(17)(18)(19)(20)(21)(22). In aneuploidy, although one centromere group of the trisomic chromosome 12 occupies a unique position that is similar to diploid nuclei, there is a change in the position of the other centromere signals.…”

“…Sophisticated algorithms that allow the quantitation of FISH signals are essential to permit the accurate localization of genes and their products in cells and tissues. Accordingly, several novel image analysis tools have been proposed to allow the segmentation, assessment, and visualization of 3D FISH signals (18)(19)(20)(21). In this study, we present a 3D modeling approach for estimating the surface of nuclei and the enclosed FISH signals.…”

Comprehensive review of association estimators for the inference of gene networks

“…SS T =SS C +SS G +SS CG +SS err (32) where SS C is the SS of the experimental conditions; SS G is the SS of the genes ( t or g); SS err is the SS of the replicates in a condition.…”

Breast Cancer Diagnostics Based on Spatial Genome Organization

“…This fully automated approach identifies nuclei with ~ 80% accuracy and, importantly, with very low false positive rates. In addition to the ANN pattern recognition selection of well segmented nuclei, we have recently implemented the use of a ranked retrieval for nuclei, which used uses logistic regression to output the probability of a nucleus being correctly segmented [17]. This ensures only the best, and very accurately, segmented nuclei are used for gene positioning analysis.…”