Publications (21) View all
-
Dataset: Turbyville et al Supplementary Data
-
Article: Ranked Retrieval of Segmented Nuclei for Objective Assessment of Cancer Gene Repositioning.
[show abstract] [hide abstract]
ABSTRACT: BACKGROUND: Correct 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. RESULTS: Logistic 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, comprisingapproximately 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. CONCLUSIONS: Accurate 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.BMC Bioinformatics 09/2012; 13(1):232. · 2.75 Impact Factor -
Article: Automatic segmentation and supervised learning-based selection of nuclei in cancer tissue images.
[show abstract] [hide abstract]
ABSTRACT: Analysis of preferential localization of certain genes within the cell nuclei is emerging as a new technique for the diagnosis of breast cancer. Quantitation requires accurate segmentation of 100-200 cell nuclei in each tissue section to draw a statistically significant result. Thus, for large-scale analysis, manual processing is too time consuming and subjective. Fortuitously, acquired images generally contain many more nuclei than are needed for analysis. Therefore, we developed an integrated workflow that selects, following automatic segmentation, a subpopulation of accurately delineated nuclei for positioning of fluorescence in situ hybridization-labeled genes of interest. Segmentation was performed by a multistage watershed-based algorithm and screening by an artificial neural network-based pattern recognition engine. The performance of the workflow was quantified in terms of the fraction of automatically selected nuclei that were visually confirmed as well segmented and by the boundary accuracy of the well-segmented nuclei relative to a 2D dynamic programming-based reference segmentation method. Application of the method was demonstrated for discriminating normal and cancerous breast tissue sections based on the differential positioning of the HES5 gene. Automatic results agreed with manual analysis in 11 out of 14 cancers, all four normal cases, and all five noncancerous breast disease cases, thus showing the accuracy and robustness of the proposed approach.Cytometry Part A 07/2012; 81(9):743-54. · 3.73 Impact Factor -
Article: Supervised learning framework for screening nuclei in tissue sections.
[show abstract] [hide abstract]
ABSTRACT: Accurate segmentation of cell nuclei in microscope images of tissue sections is a key step in a number of biological and clinical applications. Often such applications require analysis of large image datasets for which manual segmentation becomes subjective and time consuming. Hence automation of the segmentation steps using fast, robust and accurate image analysis and pattern classification techniques is necessary for high throughput processing of such datasets. We describe a supervised learning framework, based on artificial neural networks (ANNs), to identify well-segmented nuclei in tissue sections from a multistage watershed segmentation algorithm. The successful automation was demonstrated by screening over 1400 well segmented nuclei from 9 datasets of human breast tissue section images and comparing the results to a previously used stacked classifier based analysis framework.Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 08/2011; 2011:5989-92. -
Article: Schweinfurthin A selectively inhibits proliferation and Rho signaling in glioma and neurofibromatosis type 1 tumor cells in a NF1-GRD-dependent manner.
[show abstract] [hide abstract]
ABSTRACT: Neurofibromatosis type 1 (NF1) is the most common genetic disease affecting the nervous system. Patients typically develop many tumors over their lifetime, leading to increased morbidity and mortality. The NF1 gene, mutated in NF1, is also commonly mutated in sporadic glioblastoma multiforme (GBM). Because both NF1 and GBM are currently incurable, new therapeutic approaches are clearly needed. Natural products represent an opportunity to develop new therapies, as they have been evolutionarily selected to play targeted roles in organisms. Schweinfurthin A is a prenylated stilbene natural product that has previously shown specific inhibitory activity against brain and hematopoietic tumor lines. We show that patient-derived GBM and NF1 malignant peripheral nerve sheath tumor (MPNST) lines, as well as tumor lines derived from the Nf1-/+;Trp53-/+ (NPcis) mouse model of astrocytoma and MPNST are highly sensitive to inhibition by schweinfurthin A and its synthetic analogs. In contrast, primary mouse astrocytes are resistant to the growth inhibitory effects of schweinfurthin A, suggesting that schweinfurthin A may act specifically on tumor cells. Stable transfection of the GTPase-activating protein related domain of Nf1 into Nf1-/-;Trp53-/- astrocytoma cells confers resistance to schweinfurthin A. In addition, the profound effect of schweinfurthin A on dynamic reorganization of the actin cytoskeleton led us to discover that schweinfurthin A inhibits growth factor-stimulated Rho signaling. In summary, we have identified a class of small molecules that specifically inhibit growth of cells from both central and peripheral nervous system tumors and seem to act on NF1-deficient cells through cytoskeletal reorganization correlating to changes in Rho signaling.Molecular Cancer Therapeutics 05/2010; 9(5):1234-43. · 5.23 Impact Factor
