Whole-slide cytometric feature mapping for distinguishing tumor genomic subtypes in HNSCC whole slide images.

Abstract

Head and neck squamous cell carcinoma (HNSCC) is a heterogenous disease where, in advanced stages, clinical and pathological stages do not correlate with outcome. Molecular and genomic biomarkers for HNSCC classification have shown promise for prognostic and therapeutic applications. In this study, we utilize automated image analysis techniques in whole slide images of HNSCC tumors to identify relationships between cytometric features and genomic phenotypes. Hematoxylin and eosin-stained slides of HNSCC tumors (N=49) were obtained from the Cancer Imaging Archive (TCIA), along with accompanying clinical, pathological, genomic, and proteomic reports. Automated nuclear detection was performed across the entirety of slides, and cytometric feature maps were generated. Forty-one cytometric features were evaluated for associations with tumor grade, tumor stage, tumor subsite, and integrated genomic subtype (IGS). Thirty-two features demonstrated significant association with IGS when corrected for multiple comparisons. In particular, the basal subtype was visually distinguishable from the chromosomal instability and immune subtypes based on cytometric feature measurements. No features were significantly associated with tumor grade, stage, or subsite. This study provides preliminary evidence that features derived from tissue pathology slides could provide insights into genomic phenotypes of HNSCC.