Automated tumor analysis for molecular profiling in lung cancer

Abstract

The discovery and clinical application of molecular biomarkers in solid tumors, increasingly relies on nucleic acid extraction from FFPE tissue sections and subsequent molecular profiling. This in turn requires the pathological review of haematoxylin & eosin (H&E) stained slides, to ensure sample quality, tumor DNA sufficiency by visually estimating the percentage tumor nuclei and tumor annotation for manual macrodissection. In this study on NSCLC, we demonstrate considerable variation in tumor nuclei percentage between pathologists, potentially undermining the precision of NSCLC molecular evaluation and emphasising the need for quantitative tumor evaluation. We subsequently describe the development and validation of a system called TissueMark for automated tumor annotation and percentage tumor nuclei measurement in NSCLC using computerized image analysis. Evaluation of 245 NSCLC slides showed precise automated tumor annotation of cases using Tissuemark, strong concordance with manually drawn boundaries and identical EGFR mutational status, following manual macrodissection from the image analysis generated tumor boundaries. Automated analysis of cell counts for % tumor measurements by Tissuemark showed reduced variability and significant correlation (p < 0.001) with benchmark tumor cell counts. This study demonstrates a robust image analysis technology that can facilitate the automated quantitative analysis of tissue samples for molecular profiling in discovery and diagnostics.

Delivering a research‐enabled multistakeholder partnership for enhanced patient care at a population level: The Northern Ireland Comprehensive Cancer Program

“…TissueMark was tested and validated for its ability to provide automated tumor annotation and measurement of the percentage of tumor nuclei in 245 hematoxylin and eosin‐stained slides from patients with non‐small cell lung cancer. The automated approach demonstrated strong concordance with manually drawn boundaries and automated analysis of cell counts for percentage tumor measurements by TissueMark demonstrated reduced variability and significant correlation ( P <.001) with benchmark tumor cell counts . This technology is now being applied across lung, colon, breast, and prostate cancer, thereby facilitating tissue‐based molecular assays including next‐generation sequencing.…”

“…PathXL (http://www.pathxl.com) is a digital pathology software company that spun out of the CCRCB and has become a global leader in the provision of innovative digital pathology solutions for biomarker/drug discovery research and clinical applications. The company, in partnership with the CCRCB, has pioneered a novel software algorithm (TissueMark) for automated tumor recognition and quantitative analysis for nucleic acid extraction and molecular diagnostics in solid tumors . TissueMark was tested and validated for its ability to provide automated tumor annotation and measurement of the percentage of tumor nuclei in 245 hematoxylin and eosin‐stained slides from patients with non‐small cell lung cancer.…”

Digital pathology in clinical use: where are we now and what is holding us back?

“…Hamilton et al . designed and validated an image analysis system that measures tumour area and calculates percentage of tumour cells and tumour nuclei automatically . This system exhibited better concordance than estimation by eye when compared with manually counted tumour cells.…”

Tumor Heterogeneity: Will It Change What Pathologists Do

“…It is not difficult to see that between the three, quite different results may be obtained. Fortunately, technology comes to the rescue: software algorithms are now available that allow machine-based definition of tumor versus non-tumor with much better reproducibility [31].…”