Authors:
Owen Anderson
1
;
2
;
Andrew C. Kidd
3
;
Keith A. Goatman
2
;
Alexander J. Weir
2
;
Jeremy Voisey
2
;
Vismantas Dilys
2
;
Jan P. P. Siebert
1
and
Kevin G. Blyth
3
;
4
Affiliations:
1
School of Computing Science, University of Glasgow, 18 Lilybank Gardens, Glasgow, U.K.
;
2
Canon Medical Research Europe, 2 Anderson Place, Edinburgh, U.K.
;
3
Pleural Disease Unit, Queen Elizabeth University Hospital, 1345 Govan Road, Glasgow, U.K.
;
4
Institute of Infection, Immunity and Inflammation, University of Glasgow, 120 University Place, Glasgow, U.K.
Keyword(s):
Malignant Pleural Mesothelioma (MPM), Deep Learning (DL), Convolutional Neural Network (CNN), Computed Tomography (CT), Image Segmentation.
Abstract:
Malignant Pleural Mesothelioma (MPM) is a cancer associated with prior exposure to asbestos fibres. Unlike
most tumours, which are roughly spherical, MPM grows like a rind surrounding the lung. This irregular shape
poses significant clinical and technical challenges. Accurate tumour measurements are necessary to determine
treatment efficacy, but manual segmentation is tedious, time-consuming and associated with high intra- and
inter-observer variation. In addition, uncertainty is compounded by poor differentiation in the computed
tomography (CT) image between MPM and other common features. We describe herein an internal validation
of a fully automatic tool to generate volumetric segmentations of MPM tumours using a convolutional neural
network (CNN). The system was trained using the first 123 CT volumetric datasets from a planned total of 403
scans. Each scan was manually segmented to provide the expert ground truth. Evaluation was by seven-fold
cross validation on a subset
of 80/123 datasets that have full volumetric segmentations. The mean volume
of MPM tumour in these datasets is 405.1 cm3 (standard deviation 271.5 cm3). Following three-dimensional
binary closing of the manual annotations to improve inter-slice consistency, the mean volume difference
between the manual and automatic measurements is 27.2 cm3, which is not significantly different from zero
difference (p = 0:225). The 95% limits of agreement between the manual and automated measurements
are between -417 and +363 cm3. The mean Dice overlap coefficient was 0.64, which is comparable with
inter-observer measurements reported elsewhere. To our knowledge, this is the first algorithm of its kind that
fully automates and evaluates measurement of the MPM tumour volume. The next step will be to evaluate the
method on the remaining unseen multi-centre evaluation set. Such an algorithm has possible future application
to pharmaceutical trials (where it offers a repeatable study end point) and to routine care (where it allows
tumour progression to be assessed rapidly to enhance therapeutic clinical decision making).
(More)