Computational tumor stroma reaction evaluation led to novel prognosis-associated fibrosis and molecular signature discoveries in high-grade serous ovarian carcinoma

Abstract

Background: As one of the key criteria to differentiate benign vs. malignant tumors in ovarian and other solid cancers, tumor-stroma reaction (TSR) is long observed by pathologists and has been found correlated with patient prognosis. However, paucity of study aims to overcome subjective bias or automate TSR evaluation for enabling association analysis to a large cohort.

Materials and methods: Serving as positive and negative sets of TSR studies, H&E slides of primary tumors of high-grade serous ovarian carcinoma (HGSOC) (n = 291) and serous borderline ovarian tumor (SBOT) (n = 15) were digitally scanned. Three pathologist-defined quantification criteria were used to characterize the extents of TSR. Scores for each criterion were annotated (0/1/2 as none-low/intermediate/high) in the training set consisting of 18,265 H&E patches. Serial of deep learning (DL) models were trained to identify tumor vs. stroma regions and predict TSR scores. After cross-validation and independent validations, the trained models were generalized to the entire HGSOC cohort and correlated with clinical characteristics. In a subset of cases tumor transcriptomes were available, gene- and pathway-level association studies were conducted with TSR scores.

Results: The trained models accurately identified the tumor stroma tissue regions and predicted TSR scores. Within tumor stroma interface region, TSR fibrosis scores were strongly associated with patient prognosis. Cancer signaling aberrations associated 14 KEGG pathways were also found positively correlated with TSR-fibrosis score.

Conclusion: With the aid of DL, TSR evaluation could be generalized to large cohort to enable prognostic association analysis and facilitate discovering novel gene and pathways associated with disease progress.

Keywords: digital pathology; high-grade serous ovarian carcinoma; molecular signature; prognostic fibrosis; tumor-stroma reaction.

FIGURE 1

Overview of our research workflow. (A) Slide scanning and annotation. (B) Tumor-stroma segmentation and TSR score estimation. (C) Tumor stroma interface area identification. (D) Tissue-level feature summarization. (E) Association analysis.

FIGURE 2

Examples of tumor-stroma segmentation and TSR scoring results. (A) Original WSIs, with HGSOC and SBOT each; (B) tumor-stroma segmentation, tumor and stroma were encoded with cyan and yellow; (C) TSR scores measured from three metrics, including fibrosis (Red), cellularity (Green) and orientation (Blue). Each metric was encoded from dark to light color, denoting TSR score from low to high. *For better visualization, TSR scores within all stroma regions were shown, but only the tumor-stroma interface regions were included for analysis.

FIGURE 3

Tumor-stroma segmentation evaluation. (A) Boxplot of three evaluation metrics, including IoU, AP and DSC. (B) Examples of segmentation. Red arrows point to missed targets in segmentation. (C) Correlation of three evaluation metrics. Each dot represents an image sample. Linear regression was used to calculate correlation.

FIGURE 4

Tumor-stroma reaction (TSR) scoring evaluation. (A) Confusion matrix of intrinsic evaluation. (B) Violine plot for three TSR metrics within HGSOC vs. SBOT. Majority of SBOT images have low TSR score, no matter in which metric.

FIGURE 5

Prognosis and molecular associations of fibrosis score. (A) Tumor-stroma reaction (TSR) score boxplots for HGSOC and SBOT groups. (B) Overall survival differences between fibrosis high vs. low. (C) The prognostic association for other established prognostic factors (age at diagnosis, stage and residual tumor after surgical debulking). (D) Correlation between fibrosis/cellularity/orientation and molecular findings.