IRUS Total

Multi-class semantic segmentation and quantification of traumatic brain injury lesions on head CT using deep learning – an algorithm development and multi-centre validation study

File Description SizeFormat 
Multiclass semantic segmentation.pdfPublished version394.8 kBAdobe PDFView/Open
Title: Multi-class semantic segmentation and quantification of traumatic brain injury lesions on head CT using deep learning – an algorithm development and multi-centre validation study
Authors: Monteiro, M
Newcombe, VFJ
Mathieu, F
Adatia, K
Kamnitsas, K
Ferrante, E
Das, T
Whitehouse, D
Rueckert, D
Menon, DK
Glocker, B
Item Type: Journal Article
Abstract: Background CT is the most common imaging modality in traumatic brain injury (TBI). However, its conventional use requires expert clinical interpretation and does not provide detailed quantitative outputs, which may have prognostic importance. We aimed to use deep learning to reliably and efficiently quantify and detect different lesion types. Methods Patients were recruited between Dec 9, 2014, and Dec 17, 2017, in 60 centres across Europe. We trained and validated an initial convolutional neural network (CNN) on expert manual segmentations (dataset 1). This CNN was used to automatically segment a new dataset of scans, which we then corrected manually (dataset 2). From this dataset, we used a subset of scans to train a final CNN for multiclass, voxel-wise segmentation of lesion types. The performance of this CNN was evaluated on a test subset. Performance was measured for lesion volume quantification, lesion progression, and lesion detection and lesion volume classification. For lesion detection, external validation was done on an independent set of 500 patients from India. Findings 98 scans from one centre were included in dataset 1. Dataset 2 comprised 839 scans from 38 centres: 184 scans were used in the training subset and 655 in the test subset. Compared with manual reference, CNN-derived lesion volumes showed a mean difference of 0·86 mL (95% CI –5·23 to 6·94) for intraparenchymal haemorrhage, 1·83 mL (–12·01 to 15·66) for extra-axial haemorrhage, 2·09 mL (–9·38 to 13·56) for perilesional oedema, and 0·07 mL (–1·00 to 1·13) for intraventricular haemorrhage. Interpretation We show the ability of a CNN to separately segment, quantify, and detect multiclass haemorrhagic lesions and perilesional oedema. These volumetric lesion estimates allow clinically relevant quantification of lesion burden and progression, with potential applications for personalised treatment strategies and clinical research in TBI. Funding European Union 7th Framework Programme, Hannelore Kohl Stiftung, OneMind, NeuroTrauma Sciences, Integra Neurosciences, European Research Council Horizon 2020
Issue Date: 1-Jun-2020
Date of Acceptance: 9-Apr-2020
URI: http://hdl.handle.net/10044/1/79148
DOI: 10.1016/S2589-7500(20)30085-6
ISSN: 2589-7500
Publisher: Elsevier
Start Page: e314
End Page: e322
Journal / Book Title: The Lancet. Digital Health
Volume: 2
Issue: 6
Copyright Statement: © 2020 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license (https://creativecommons.org/licenses/by/4.0/).
Sponsor/Funder: Engineering & Physical Science Research Council (E
Commission of the European Communities
Commission of the European Communities
Funder's Grant Number: EP/R511547/1
H2020 - 757173
Keywords: Science & Technology
Life Sciences & Biomedicine
Medical Informatics
Medicine, General & Internal
General & Internal Medicine
Publication Status: Published
Online Publication Date: 2020-05-14
Appears in Collections:Computing
Faculty of Engineering