Multifactorial estimation of clinical outcome in HPV-associated oropharyngeal squamous cell carcinoma via automated image analysis of routine diagnostic H&E slides and neural network modelling

TY - JOUR

T1 - Multifactorial estimation of clinical outcome in HPV-associated oropharyngeal squamous cell carcinoma via automated image analysis of routine diagnostic H&E slides and neural network modelling

AU - Hue, Jonas

AU - Valinciute, Zaneta

AU - Thavaraj, Selvam

AU - Veschini, Lorenzo

N1 - Copyright © 2023 The Authors. Published by Elsevier Ltd.. All rights reserved. Funding Information: This research was supported by the British Society for Oral & Maxillofacial Pathology Research Grants Scheme. Publisher Copyright: © 2023 The Authors

PY - 2023/6

Y1 - 2023/6

N2 - Objective: Routine haematoxylin and eosin (H&E) photomicrographs from human papillomavirus-associated oropharyngeal squamous cell carcinomas (HPV + OpSCC) contain a wealth of prognostic information. In this study, we developed a high content image analysis (HCIA) workflow to quantify features of H&E images from HPV + OpSCC patients to identify prognostic features and predict patient outcomes. Methods: First, we have developed an open-source HCIA tool for single-cell segmentation and classification of H&E images. Subsequently, we have used our HCIA tool to analyse a set of 889 images from diagnostic H&E slides in a retrospective cohort of HPV + OpSCC patients with favourable (FO, n = 60) or unfavourable (UO, n = 30) outcomes. We have identified and measured 31 prognostic features which were quantified in each sample and used to train a neural network (NN) model to predict patient outcomes. Results: Univariate and multivariate statistical analyses revealed significant differences between FO and UO patients in 31 and 17 variables, respectively (P < 0.05). At the single-image level, the NN model had an overall accuracy of 72.5% and 71.2% in recognising FO and UO patients when applied to test or validation sets, respectively. When considering 10 images per patient, the accuracy of the NN model increased to 86.7% in the test set. Conclusion: Our open-source H&E analysis workflow and predictive models confirm previously reported prognostic features and identifies novel factors which predict HPV + OpSCC outcomes with promising accuracy. Our work supports the use of machine learning in digital pathology to exploit clinically relevant features in routine diagnostic pathology without additional biomarkers.

AB - Objective: Routine haematoxylin and eosin (H&E) photomicrographs from human papillomavirus-associated oropharyngeal squamous cell carcinomas (HPV + OpSCC) contain a wealth of prognostic information. In this study, we developed a high content image analysis (HCIA) workflow to quantify features of H&E images from HPV + OpSCC patients to identify prognostic features and predict patient outcomes. Methods: First, we have developed an open-source HCIA tool for single-cell segmentation and classification of H&E images. Subsequently, we have used our HCIA tool to analyse a set of 889 images from diagnostic H&E slides in a retrospective cohort of HPV + OpSCC patients with favourable (FO, n = 60) or unfavourable (UO, n = 30) outcomes. We have identified and measured 31 prognostic features which were quantified in each sample and used to train a neural network (NN) model to predict patient outcomes. Results: Univariate and multivariate statistical analyses revealed significant differences between FO and UO patients in 31 and 17 variables, respectively (P < 0.05). At the single-image level, the NN model had an overall accuracy of 72.5% and 71.2% in recognising FO and UO patients when applied to test or validation sets, respectively. When considering 10 images per patient, the accuracy of the NN model increased to 86.7% in the test set. Conclusion: Our open-source H&E analysis workflow and predictive models confirm previously reported prognostic features and identifies novel factors which predict HPV + OpSCC outcomes with promising accuracy. Our work supports the use of machine learning in digital pathology to exploit clinically relevant features in routine diagnostic pathology without additional biomarkers.

UR - http://www.scopus.com/inward/record.url?scp=85153052254&partnerID=8YFLogxK

U2 - 10.1016/j.oraloncology.2023.106399

DO - 10.1016/j.oraloncology.2023.106399

M3 - Article

C2 - 37098302

SN - 1368-8375

VL - 141

SP - 106399

JO - ORAL ONCOLOGY

JF - ORAL ONCOLOGY

M1 - 106399

ER -