Malignant Mesothelioma subtyping via sampling driven multiple instance prediction on tissue image and cell morphology data

Artificial Intelligence in Medicine, vol. 143, pp. 102628

Abstract

Malignant Mesothelioma is a difficult to diagnose and highly lethal cancer usually associated with asbestos exposure. It can be broadly classified into three subtypes: Epithelioid, Sarcomatoid, and a hybrid Biphasic subtype in which significant components of both of the previous subtypes are present. Early diagnosis and identification of the subtype informs treatment and can help improve patient outcome. However, the subtyping of malignant mesothelioma, and specifically the recognition of transitional features from routine histology slides has a high level of inter-observer variability. In this work, we propose an end-to-end multiple instance learning (MIL) approach for malignant mesothelioma subtyping. This uses an adaptive instance-based sampling scheme for training deep convolutional neural networks on bags of image patches that allows learning on a wider range of relevant instances compared to max or top-N based MIL approaches. We also investigate augmenting the instance representation to include aggregate cellular morphology features from cell segmentation. The proposed MIL approach enables identification of malignant mesothelial subtypes of specific tissue regions. From this a continuous characterisation of a sample according to predominance of sarcomatoid vs epithelioid regions is possible, thus avoiding the arbitrary and highly subjective categorisation by currently used subtypes. Instance scoring also enables studying tumor heterogeneity and identifying patterns associated with different subtypes. We have evaluated the proposed method on a dataset of 234 tissue micro-array cores with an AUROC of 0.89±0.05 for this task. The dataset and developed methodology is available for the community at: https://github.com/measty/PINS.

Authors 12

1. Silviu Tudor Marc

   Middlesex University London

   Affiliation as printed

   Department of Computer Science, University of Middlesex, United Kingdom

2. Xiaohong W. Gao

   Middlesex University London

   Affiliation as printed

   Department of Computer Science, University of Middlesex, United Kingdom

3. Heba Sailem

   King's College London · University of Oxford

   Affiliation as printed

   Institute of Biomedical Engineering, University of Oxford, United Kingdom; Kings College London, United Kingdom

   Institute of Biomedical Engineering, University of Oxford, United Kingdom

4. Judith Offman

   King's College London · Queen Mary University of London

   Affiliation as printed

   Kings College London, United Kingdom; Wolfson Institute of Population Health, Queen Mary University of London, United Kingdom

   Kings College London, United Kingdom

5. Emmanouíl Karteris

   Brunel University of London

   Affiliation as printed

   Brunel University, United Kingdom

6. Angeles Montero Fernandez

   University of Manchester

   Affiliation as printed

   Manchester University, United Kingdom

7. Danny David Jonigk Aachen Institute of Pathology, Medical Faculty

   RWTH Aachen University · Medizinische Hochschule Hannover

   Affiliation as printed

   German Center for Lung Research (DZL), BREATH, Hanover, Germany; Institute of Pathology, Medical Faculty of RWTH Aachen University, Aachen, Germany

   Medizinische Hochschule Hannover, Germany

8. William Cookson

   Imperial College London

   Affiliation as printed

   National Heart and Lung Institute, Imperial College London, United Kingdom

9. Miriam F. Moffatt

   Imperial College London

   Affiliation as printed

   National Heart and Lung Institute, Imperial College London, United Kingdom

10. Sanjay Popat

    Imperial College London

    Affiliation as printed

    National Heart and Lung Institute, Imperial College London, United Kingdom

11. Fayyaz Minhas

    University of Warwick

    Affiliation as printed

    Tissue Image Analytics Center, University of Warwick, United Kingdom

12. Jan Lukas Robertus

    Imperial College London

    Affiliation as printed

    National Heart and Lung Institute, Imperial College London, United Kingdom