Optimisation of deep learning methods for visualisation of tumour heterogeneity and brain tumour grading through digital pathology
File(s)
Published version
Author(s)
Truong, An Hoai
Sharmanska, Viktoriia
Limback-Stanic, Clara
Grech-Sollars, Matthew
Type
Journal Article
Abstract
Background
Variations in prognosis and treatment options for gliomas are dependent on tumour grading. When tissue is available for analysis, grade is established based on histological criteria. However, histopathological diagnosis is not always reliable or straight-forward due to tumour heterogeneity, sampling error and subjectivity, and hence there is great inter-observer variability in readings.
Methods
We trained convolutional neural network models to classify digital whole-slide histopathology images from The Cancer Genome Atlas. We tested a number of optimisation parameters.
Results
Data augmentation did not improve model training, while smaller batch size helped to prevent overfitting and led to improved model performance. There was no significant difference in performance between a modular 2-class model and a single 3-class model system. The best models trained achieved a mean accuracy of 73% in classifying glioblastoma from other grades, and 53% between WHO grade II and III gliomas. A visualisation method was developed to convey the model output in a clinically relevant manner by overlaying colour-coded predictions over the original whole slide image.
Conclusions
Our developed visualisation method reflects the clinical decision-making process by highlighting the intra-tumour heterogeneity and may be used in clinical setting to aid diagnosis. Explainable AI techniques may allow further evaluation of the model and underline areas for improvements such as biases. Due to intra-tumour heterogeneity, data annotation for training was imprecise, and hence performance was lower than expected. The models may be further improved by employing advanced data augmentation strategies and using more precise semi-automatic or manually labelled training data.
Variations in prognosis and treatment options for gliomas are dependent on tumour grading. When tissue is available for analysis, grade is established based on histological criteria. However, histopathological diagnosis is not always reliable or straight-forward due to tumour heterogeneity, sampling error and subjectivity, and hence there is great inter-observer variability in readings.
Methods
We trained convolutional neural network models to classify digital whole-slide histopathology images from The Cancer Genome Atlas. We tested a number of optimisation parameters.
Results
Data augmentation did not improve model training, while smaller batch size helped to prevent overfitting and led to improved model performance. There was no significant difference in performance between a modular 2-class model and a single 3-class model system. The best models trained achieved a mean accuracy of 73% in classifying glioblastoma from other grades, and 53% between WHO grade II and III gliomas. A visualisation method was developed to convey the model output in a clinically relevant manner by overlaying colour-coded predictions over the original whole slide image.
Conclusions
Our developed visualisation method reflects the clinical decision-making process by highlighting the intra-tumour heterogeneity and may be used in clinical setting to aid diagnosis. Explainable AI techniques may allow further evaluation of the model and underline areas for improvements such as biases. Due to intra-tumour heterogeneity, data annotation for training was imprecise, and hence performance was lower than expected. The models may be further improved by employing advanced data augmentation strategies and using more precise semi-automatic or manually labelled training data.
Date Issued
2020-08-29
Date Acceptance
2020-08-21
Citation
Neuro-Oncology Advances, 2020, 2 (1)
ISSN
2632-2498
Publisher
Oxford University Press (OUP)
Journal / Book Title
Neuro-Oncology Advances
Volume
2
Issue
1
Copyright Statement
© The Author(s) 2020. Published by Oxford University Press, the Society for Neuro-Oncology and the European Association of Neuro-Oncology. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
License URL
Sponsor
Imperial College London
Subjects
brain tumor
deep learning
digital pathology
machine learning
tumor heterogeneity
Publication Status
Published
Date Publish Online
2020-08-29