Invariant delineation of nuclear architecture in glioblastoma multiforme for clinical and molecular association

Abstract

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. Data and intermediaries for a number of tumor types (GBM, low grade glial, and kidney renal clear carcinoma) are available at: http://tcga.lbl.gov for correlation with TCGA molecular data. The website also provides an interface for panning and zooming of whole mount tissue sections with/without overlaid segmentation results for quality control.

Fig. 1

Work flow in Nuclear Segmentation for a cohort of whole mount tissue sections.

Fig. 2

Steps in Nuclear Segmentation.

Fig. 3

(a) Two diverse pinhole of tumor signatures; (b) Decompositions by [33]; (c) Blue ratio images.

Fig. 4

(a) An example of the LoG response for detection of foreground (green dot) and background (blue dot) signals indicates an excellent performance on the initial estimate; (b) Histogram of the blue ratio intensity derived from image (a) indicates that the peak of the distribution corresponds to the occurrence frequency of the background pixels.

Fig. 5

LoG responses can be either positive (e.g., potential background) or negative (e.g., foreground or part of foreground) in the transformed blue ratio image. In the blue ratio image with the most negative LoG response, the threshold is set at the minimum intensity.

Fig. 6

(a) Eight-neighborhood system: n_G = 8; (b) Contour on eight-neighborhood 2D grid; (c) One family of lines formed by edges of the graph.

Fig. 7

Steps in the delineation of overlapping nuclei: (Top row) identifying points of maximum curvature where potential folds are formed, (middle row) formation of partitioning hypotheses through triangulation, (bottom row) stepwise application of geometric constraints for deleting and pruning edges.

Fig. 8

A comparison between MCV and MRGC (as shown in (c) and (d), respectively) based on the same reference image, as shown in (a). Even though the test image and the reference image are slightly different in color space, compared with MCV, MRGC still produces 1) more accurate classification, due to the encoding of statistics from test image’s color space via local probability map; 2) less noisy classification due to the smoothness constrain.

Fig. 9

A subset of reference image ROI, with manual annotation overlaid as green contours, indicating significant amounts of technical variation. Nuclei with white hollow regions inside are pointed out by arrows.

Fig. 10

A comparison among our approach, MCV, and random forest. (a) Original image patch; (b) Detected seeds, Green: Nuclei region; Blue: background; (c) Local Nuclei Probability established based on seeds; (d) Classification by our approach; (e) Classification by MCV; (f) Classification by Random forest.

Fig. 11

Segmentation on low chromatin nuclei. (a) Original image patch; (b) Segmentation by our approach.

Fig. 12

Classification and segmentation results indicates tolerance to intrinsic variations: (a) Original images; (b) Nuclear/Background classification results via our approach(MRGC); (c) Nuclear partition results via geometric reasoning.

Fig. 13

Top and bottom rows show average classification performance and computational time as a function of number of reference images used. It is clear that the top M = 10 reference images with highest λ is a reasonable trade-off between performance and computational time.

Fig. 14

Morphometric subtyping reveals four subtypes based on cellularity index and nuclear area: (a) visualization of consensus clustering with four clusters; and (b) distribution of cellularity index per subtype.

Fig. 15

Computed subtypes with cellularity and nuclear size is predictive as a result of more aggressive therapy.

Fig. 16

Heat map representing a subset of differentially regulated transcripts for Subtype 2.

Fig. 17

Subnetwork enrichment analysis, for the predictive subtype in Figure 15(a), reveals inflammatory hubs that promote tumor differentiation and invasiveness in GBM.