Background and aims: Immunohistochemistry (IHC) is an essential component of biomarker research in cancer. Automated biomarker quantification is hampered by the failure of computational algorithms to discriminate 'negative' tumour cells from 'negative' stromal cells. We sought to develop an algorithm for segmentation of tumour epithelium in colorectal cancer (CRC), irrespective of the biomarker expression in the cells.
Methods and results: We developed tumour parcellation and quantification (TuPaQ) to segment tumour epithelium and parcellate sections into 'epithelium' and 'non-epithelium'. TuPaQ comprises image pre-processing, extraction of regions of interest (ROIs) and quantification of tumour epithelium (total area occupied by epithelium and number of nuclei in the occupied area). A total of 286 TMA cores from CRC were manually annotated and analysed using the commercial halo software to provide ground truth. The performance of TuPaQ was evaluated against the ground truth using a variety of metrics. The image size of each core was 7000 × 7000 pixels and each core was analysed in a matter of seconds. Pixel × pixel analysis showed a sensitivity of 84% and specificity of 95% in detecting epithelium. The mean tumour area obtained by TuPaQ was very close to the area quantified after manual annotation (r = 0.956, P < 0.001). Moreover, quantification of tumour nuclei by TuPaQ correlated very strongly with that of halo (r = 0.891, P < 0.001).
Conclusion: TuPaQ is a very rapid and accurate method of separating the epithelial and stromal compartments of colorectal tumours. This will allow more accurate and objective analysis of immunohistochemistry.
Keywords: biomarker analysis; colorectal cancer; image segmentation; machine learning; parcellation.
© 2019 John Wiley & Sons Ltd.