CellOMaps: A compact representation for robust classification of lung adenocarcinoma growth patterns.

Journal: Computers in biology and medicine
Published Date:

Abstract

Lung adenocarcinoma (LUAD) is a morphologically heterogeneous disease, characterized by five primary histological growth patterns. The classification of such patterns is crucial due to their direct relation to prognosis but the high subjectivity and observer variability pose a major challenge. Related studies in the literature focus on machine learning methods for growth pattern classification, often formulating the problem as a slide-level predominant pattern classification problem. We propose a generalizable machine learning pipeline capable of classifying lung tissue into one of the five patterns or as non-tumor. The proposed pipeline's strength lies in a novel compact Cell Organization Maps (cellOMaps) representation that captures the cellular spatial patterns from Hematoxylin and Eosin (H&E) whole slide images (WSIs). The proposed pipeline provides state-of-the-art performance on LUAD growth pattern classification when evaluated on both internal unseen slides and external datasets, comparing favorably with the current approaches. In addition, our preliminary results show that the model's outputs can be used to predict patients Tumor Mutational Burden (TMB) levels.

Authors

  • Arwa Al-Rubaian
    Tissue Image Analytics Centre, Department of Computer Science, University of Warwick, UK. Electronic address: arwa.alrubaian@warwick.ac.uk.
  • Gozde N Gunesli
    Tissue Image Analytics Centre, Department of Computer Science, University of Warwick, UK.
  • Wajd A Althakfi
    Histopathology Unit, Department of Pathology, King Saud University, Riyadh, Kingdom of Saudi Arabia.
  • Ayesha Azam
    Department of Computer Science, University of Warwick, UK; University Hospitals Coventry and Warwickshire, Coventry, UK.
  • David Snead
    Department of Pathology, University Hospitals Coventry and Warwickshire, Coventry, UK.
  • Nasir M Rajpoot
  • Shan E Ahmed Raza
    Division of Molecular Pathology, The Institute of Cancer Research, UK; Department of Computer Science, University of Warwick, UK; Centre for Evolution and Cancer, The Institute of Cancer Research, London, UK. Electronic address: shan.raza@icr.ac.uk.