Invariant Delineation of Nuclear Architecture in Glioblastoma Multiforme for Clinical and Molecular Association

IEEE transactions on medical imaging 12/2012; DOI: 10.1109/TMI.2012.2231420
Source: PubMed


Automated analysis of whole mount tissue sections can provide insights into tumor subtypes and the underlying molecular basis of neoplasm. However, since tumor sections are collected from different laboratories, inherent technical and biological variations impede analysis for very large datasets such as The Cancer Genome Atlas (TCGA). Our objective is to characterize tumor histopathology, through the delineation of the nuclear regions, from hematoxylin and eosin (H\E) stained tissue sections. Such a representation can then be mined for intrinsic subtypes across a large dataset for prediction and molecular association. Furthermore, nuclear segmentation is formulated within a multi-reference graph framework with geodesic constraints, which enables computation of multidimensional representations, on a cell-by-cell basis, for functional enrichment and bioinformatics analysis. Here, we present a novel method, multi-reference graph cut (MRGC), for nuclear segmentation that overcomes technical variations associated with sample preparation by incorporating prior knowledge from manually annotated reference images and local image features. The proposed approach has been validated on manually annotated samples and then applied to a dataset of 377 Glioblastoma Multiforme (GBM) whole slide images from 146 patients. For the GBM cohort, multidimensional representation of the nuclear features and their organization have identified 1) statistically significant subtypes based on several morphometric indexes, 2) whether each subtype can be predictive or not, and 3) that the molecular correlates of predictive subtypes are consistent with the literature.

Download full-text


Available from: Bahram Parvin, Oct 09, 2015
62 Reads
  • Source
    • "Several outstanding reviews for the histology sections analysis can be found in [2] [3]. From our perspective, four distinct works have defined the trends in tissue histology analysis: (i) one group of researchers proposed nuclear segmentation and organization for tumor grading and/or the prediction of tumor recurrence [4] [5] [6] [7] [8]. (ii) A second group of researchers focused on patch level analysis (e.g., small regions) based on either human engineered features [9] [10] or features from unsupervised learning [11] [12] [13], for tumor representation . "
    [Show abstract] [Hide abstract]
    ABSTRACT: Classification of histology sections from large cohorts, in terms of distinct regions of microanatomy (e.g., tumor, stroma, normal), enables the quantification of tumor composition, and the construction of predictive models of the clinical outcome. To tackle the batch effects and biological heterogeneities that are persistent in large co-horts, sparse cellular morphometric context has recently been developed for invariant representation of the underlying properties in the data, which summarizes cellular morphometric features at various locations and scales, and leads to a system with superior performance for classification of microanatomy and histopathology. However , the sparse optimization protocol for the calculation of sparse cellular morphometric features is not scalable for large scale classification. To improve the scalability of systems, based on sparse mor-phometric context, we propose the predictive sparse morphometric context in place of the original implementation, which approximates the sparse cellular morphometric feature through a non-linear re-gressor that is jointly learned with an over-complete dictionary in an unsupervised manner. Experimental results indicates over 50 times speedup compared to our previous implementation with the help of non-linear regressor; while producing competitive performance.
    IEEE Int. Symp. on Biomedical Imaging: from nano to macro; 04/2015
  • Source
    • "Our method outperforms traditional nuclei segmentation algorithms [20] [22] and is very competitive with one of the state-of-the-art algorithm [21]. Note that unlike the algorithm in [21], which is built upon human engineered prior knowledge. Proposed SCCR is a generic feature learning model and may be applicable to segmentation tasks of other tumor types. "
    International Symposium on Biomedical Imaging: from nano to macro, Brooklyn, NY; 04/2015
  • Source
    • "The binarization of nuclei based on GC is addressed in [23] with results being more accurate than global thresholding. Prior knowledge like nucleus shape [24], manual annotation and local image features [25] can be incorporated in the GC framework to allow more robust seg- mentation. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Automation-assisted reading (AAR) techniques have the potential to reduce errors and increase productivity in cervical cancer screening. The sensitivity of AAR relies heavily on automated segmentation of abnormal cervical cells, which is handled poorly by current segmentation algorithms. In this paper, a global and local scheme based on graph cut approach is proposed to segment cervical cells in images with a mix of healthy and abnormal cells. For cytoplasm segmentation, the multi-way graph cut is performed globally on the a* channel enhanced image, which can be effective when the image histogram presents a non-bimodal distribution. For segmentation of nuclei, especially when they are abnormal, we propose to use graph cut adaptively and locally, which allows the combination of intensity, texture, boundary and region information. Two concave points-based approaches are integrated to split the touching-nuclei. As part of an ongoing clinical trial, preliminary validation results obtained from 21 cervical cell images with non-ideal imaging condition and pathology show that our segmentation method achieved 93% accuracy for cytoplasm, and 88.4% F-measure for abnormal nuclei, outperforming state of the art methods in terms of accuracy. Our method has the potential to improve the sensitivity of AAR in screening for cervical cancer.
    Computerized medical imaging and graphics: the official journal of the Computerized Medical Imaging Society 07/2014; 38(5). DOI:10.1016/j.compmedimag.2014.02.001 · 1.22 Impact Factor
Show more