Tumour purity assessment with deep learning in colorectal cancer and impact on molecular analysis
Year: 2024
Type: article
Abstract: Tumour content plays a pivotal role in directing the bioinformatic analysis of molecular profiles such as copy number variation (CNV). In clinical application, tumour purity estimation (TPE) is achieved either through visual pathological review [conventional pathology (CP)] or the deconvolution of molecular data. While CP provides a direct measurement, it demonstrates modest reproducibility and lacks standardisation. Conversely, deconvolution methods offer an indirect assessment with uncertain accuracy, underscoring the necessity for innovative approaches. SoftCTM is an open-source, multiorgan deep-learning (DL) model for the detection of tumour and non-tumour cells in H&E-stained slides, developed within the Overlapped Cell on Tissue Dataset for Histopathology (OCELOT) Challenge 2023. Here, using three large multicentre colorectal cancer (CRC) cohorts (N = 1,097 patients) with digital pathology and multi-omic data, we compare the utility and accuracy of TPE with SoftCTM versus CP and bioinformatic deconvolution methods (RNA expression, DNA methylation) for downstream molecular analysis, including CNV profiling. SoftCTM showed technical repeatability when applied twice on the same slide (r = 1.0) and excellent correlations in paired H&E slides (r > 0.9). TPEs profiled by SoftCTM correlated highly with RNA expression (r = 0.59) and DNA methylation (r = 0.40), while TPEs by CP showed a lower correlation with RNA expression (r = 0.41) and DNA methylation (r = 0.29). We show that CP and deconvolution methods respectively underestimate and overestimate tumour content compared to SoftCTM, resulting in 6-13% differing CNV calls. In summary, TPE with SoftCTM enables reproducibility, automation, and standardisation at single-cell resolution. SoftCTM estimates (M = 58.9%, SD ±16.3%) reconcile the overestimation by molecular data extrapolation (RNA expression: M = 79.2%, SD ±10.5, DNA methylation: M = 62.7%, SD ±11.8%) and underestimation by CP (M = 35.9%, SD ±13.1%), providing a more reliable middle ground. A fully integrated computational pathology solution could therefore be used to improve downstream molecular analyses for research and clinics. © 2024 The Author(s). The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.
Source: The Journal of Pathology
DOI: 10.1002/path.6376
Authors: Lydia A Schoenpflug, Aikaterini Chatzipli, Korsuk Sirinukunwattana, Susan Richman, Andrew Blake, James Robineau, Kirsten D Mertz, Clare Verrill, Simon J Leedham, Claire Hardy, Celina Whalley, Keara Redmond, Philip Dunne, Steven Walker, Andrew D Beggs, Ultan McDermott, Graeme I Murray, Leslie M Samuel, Matthew Seymour, Ian Tomlinson, Philip Quirke, Jens Rittscher, Tim Maughan, Enric Domingo, Viktor H Koelzer
Institutions: University of Zurich, University Hospital Zurich, Wellcome Sanger Institute, University of Oxford, NIHR Oxford Biomedical Research Centre, Oxford University Hospitals NHS Trust, University of Leeds, University of Basel, University Hospital of Basel, Kantonsspital Baselland, Centre for Human Genetics, John Radcliffe Hospital, University of Birmingham, Queen's University Belfast, Almac (United Kingdom), University of Aberdeen, Aberdeen Royal Infirmary, NHS Grampian, University of Edinburgh, Ludwig Cancer Research, University of Liverpool
Language: English
Topic: AI in cancer detection
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $5,190
Funders: National Science Foundation, Wellcome Trust, Cancer Research UK, National Institute for Health and Care Research, Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung, Medical Research Council, Engineering and Physical Sciences Research Council, Biomedical Research Council, NIHR Oxford Biomedical Research Centre, National Cancer Institute
Awards: G1277543710, G1370388735, G1792222866, Seebibyte: Visual Search for the Era of Big Data, G439089712, G6352856463, G7306818829, G7692565448, MICA: Stratification in COloRectal cancer: from biology to Treatment prediction: S-CORT, Genetic profiling of the tumor stroma in colorectal cancer, G8883764206, G991008949
OpenAlex ID: W4405693458