Integrated morphologic analysis for the identification and characterization of disease subtypes

Abstract

Background and objective: Morphologic variations of disease are often linked to underlying molecular events and patient outcome, suggesting that quantitative morphometric analysis may provide further insight into disease mechanisms. In this paper a methodology for the subclassification of disease is developed using image analysis techniques. Morphologic signatures that represent patient-specific tumor morphology are derived from the analysis of hundreds of millions of cells in digitized whole slide images. Clustering these signatures aggregates tumors into groups with cohesive morphologic characteristics. This methodology is demonstrated with an analysis of glioblastoma, using data from The Cancer Genome Atlas to identify a prognostically significant morphology-driven subclassification, in which clusters are correlated with transcriptional, genetic, and epigenetic events.

Materials and methods: Methodology was applied to 162 glioblastomas from The Cancer Genome Atlas to identify morphology-driven clusters and their clinical and molecular correlates. Signatures of patient-specific tumor morphology were generated from analysis of 200 million cells in 462 whole slide images. Morphology-driven clusters were interrogated for associations with patient outcome, response to therapy, molecular classifications, and genetic alterations. An additional layer of deep, genome-wide analysis identified characteristic transcriptional, epigenetic, and copy number variation events.

Results and discussion: Analysis of glioblastoma identified three prognostically significant patient clusters (median survival 15.3, 10.7, and 13.0 months, log rank p=1.4e-3). Clustering results were validated in a separate dataset. Clusters were characterized by molecular events in nuclear compartment signaling including developmental and cell cycle checkpoint pathways. This analysis demonstrates the potential of high-throughput morphometrics for the subclassification of disease, establishing an approach that complements genomics.

Figure 1

The integrative morphologic/genomic analysis framework consists of four modules. The morphology engine produces and manages quantitative descriptions of hundreds of millions of cells. The clustering engine normalizes and filters data and identifies morphology-driven patient clusters. The correlative module analyzes clusters for associations with survival, treatment response, human evaluations of pathology, and recognized genetic alterations. Genome-wide analysis performs a deeper investigation of the transcriptional, genetic, and epigenetic associations, and mines these for biological themes and pathway activation. *Gene Ontology and Pathway Analyses are performed offline with separate commercial and public software packages.

Figure 2

Glioblastoma (GBM) clusters, survival, and relationship to molecular subtypes. (A) Means-based analysis of GBM morphology reveals three patient clusters. (B) Survival differences between these clusters are statistically significant. CC, cell cycle; CM, chromatin modification; PB, protein biosynthesis.

Figure 3

Signature nuclei for: (A) cell cycle (CC), (B) chromatin modification (CM), and (C) protein biosynthesis (PB) clusters. Cluster morphology is visualized by selecting the most representative nucleus from each patient. The selection is defined by the cell with the shortest distance in feature space to the patient's morphology signature.