Deciphering the Morphology of Tumor-Stromal Features in Invasive Breast Cancer Using Artificial Intelligence

Nehal M Atallah; Noorul Wahab; Michael S Toss; Shorouk Makhlouf; Asmaa Y Ibrahim; Ayat G Lashen; Suzan Ghannam; Nigel P Mongan; Mostafa Jahanifar; Simon Graham; Mohsin Bilal; Abhir Bhalerao; Shan E Ahmed Raza; David Snead; Fayyaz Minhas; Nasir Rajpoot; Emad Rakha

doi:10.1016/j.modpat.2023.100254

Deciphering the Morphology of Tumor-Stromal Features in Invasive Breast Cancer Using Artificial Intelligence

Mod Pathol. 2023 Oct;36(10):100254. doi: 10.1016/j.modpat.2023.100254. Epub 2023 Jun 26.

Authors

Nehal M Atallah¹, Noorul Wahab², Michael S Toss³, Shorouk Makhlouf⁴, Asmaa Y Ibrahim⁵, Ayat G Lashen¹, Suzan Ghannam⁶, Nigel P Mongan⁷, Mostafa Jahanifar², Simon Graham², Mohsin Bilal², Abhir Bhalerao², Shan E Ahmed Raza², David Snead⁸, Fayyaz Minhas², Nasir Rajpoot⁹, Emad Rakha¹⁰

Affiliations

¹ Academic Unit for Translational Medical Sciences, School of Medicine, University of Nottingham, Nottingham, UK; Department of Pathology, Faculty of Medicine, Menoufia University, Egypt.
² Tissue Image Analytics Centre, University of Warwick, Conventry, UK.
³ Academic Unit for Translational Medical Sciences, School of Medicine, University of Nottingham, Nottingham, UK; Histopathology Department, Royal Hallamshire Hospital, Sheffield Teaching Hospitals NHS Foundation Trust, Sheffield, UK.
⁴ Academic Unit for Translational Medical Sciences, School of Medicine, University of Nottingham, Nottingham, UK; Department of Pathology, Faculty of Medicine, Assiut University, Egypt.
⁵ Academic Unit for Translational Medical Sciences, School of Medicine, University of Nottingham, Nottingham, UK; Department of Pathology, Faculty of Medicine, Suez Canal University, Egypt.
⁶ Academic Unit for Translational Medical Sciences, School of Medicine, University of Nottingham, Nottingham, UK; Department of Histology and Cell Biology, Faculty of Medicine, Suez Canal University, Egypt.
⁷ Biodiscovery Institute, School of Veterinary Medicine and Sciences, University of Nottingham, Sutton Bonington, UK; Department of Pharmacology, Weill Cornell Medicine, New York.
⁸ Cellular Pathology, University Hospitals Coventry and Warwickshire NHS Trust, UK.
⁹ Tissue Image Analytics Centre, University of Warwick, Conventry, UK. Electronic address: N.M.Rajpoot@warwick.ac.uk.
¹⁰ Academic Unit for Translational Medical Sciences, School of Medicine, University of Nottingham, Nottingham, UK; Department of Pathology, Faculty of Medicine, Menoufia University, Egypt; Pathology Department, Hamad Medical Corporation, Doha, Qatar. Electronic address: emad.rakha@nottingham.ac.uk.

PMID: 37380057
DOI: 10.1016/j.modpat.2023.100254

Abstract

Tumor-associated stroma in breast cancer (BC) is complex and exhibits a high degree of heterogeneity. To date, no standardized assessment method has been established. Artificial intelligence (AI) could provide an objective morphologic assessment of tumors and stroma, with the potential to identify new features not discernible by visual microscopy. In this study, we used AI to assess the clinical significance of (1) stroma-to-tumor ratio (S:TR) and (2) the spatial arrangement of stromal cells, tumor cell density, and tumor burden in BC. Whole-slide images of a large cohort (n = 1968) of well-characterized luminal BC cases were examined. Region and cell-level annotation was performed, and supervised deep learning models were applied for automated quantification of tumor and stromal features. S:TR was calculated in terms of surface area and cell count ratio, and the S:TR heterogeneity and spatial distribution were also assessed. Tumor cell density and tumor size were used to estimate tumor burden. Cases were divided into discovery (n = 1027) and test (n = 941) sets for validation of the findings. In the whole cohort, the stroma-to-tumor mean surface area ratio was 0.74, and stromal cell density heterogeneity score was high (0.7/1). BC with high S:TR showed features characteristic of good prognosis and longer patient survival in both the discovery and test sets. Heterogeneous spatial distribution of S:TR areas was predictive of worse outcome. Higher tumor burden was associated with aggressive tumor behavior and shorter survival and was an independent predictor of worse outcome (BC-specific survival; hazard ratio: 1.7, P = .03, 95% CI, 1.04-2.83 and distant metastasis-free survival; hazard ratio: 1.64, P = .04, 95% CI, 1.01-2.62) superior to absolute tumor size. The study concludes that AI provides a tool to assess major and subtle morphologic stromal features in BC with prognostic implications. Tumor burden is more prognostically informative than tumor size.

Keywords: ER-positive breast cancer; artificial intelligence; stroma-to-tumor ratio; tumor-associated stroma.