Publications

BibTex format

@article{Monteiro:2020:10.1016/S2589-7500(20)30085-6,
author = {Monteiro, M and Newcombe, VFJ and Mathieu, F and Adatia, K and Kamnitsas, K and Ferrante, E and Das, T and Whitehouse, D and Rueckert, D and Menon, DK and Glocker, B},
doi = {10.1016/S2589-7500(20)30085-6},
journal = {The Lancet. Digital Health},
pages = {e314--e322},
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},
url = {http://dx.doi.org/10.1016/S2589-7500(20)30085-6},
volume = {2},
year = {2020}
}

Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Background CT is the most common imaging modality in traumatic brain injury (TBI). However, its conventional userequires expert clinical interpretation and does not provide detailed quantitative outputs, which may have prognosticimportance. 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 andvalidated an initial convolutional neural network (CNN) on expert manual segmentations (dataset 1). This CNN wasused to automatically segment a new dataset of scans, which we then corrected manually (dataset 2). From thisdataset, we used a subset of scans to train a final CNN for multiclass, voxel-wise segmentation of lesion types. Theperformance 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 wasdone 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-derivedlesion 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, and0·07 mL (–1·00 to 1·13) for intraventricular haemorrhage.Interpretation We show the ability of a CNN to separately segment, quantify, and detect multiclass haemorrhagiclesions and perilesional oedema. These volumetric lesion estimates allow clinically relevant quantification oflesion burden and progression, with potential applications for personalised treatment strategies
AU  - Monteiro,M
AU  - Newcombe,VFJ
AU  - Mathieu,F
AU  - Adatia,K
AU  - Kamnitsas,K
AU  - Ferrante,E
AU  - Das,T
AU  - Whitehouse,D
AU  - Rueckert,D
AU  - Menon,DK
AU  - Glocker,B
DO  - 10.1016/S2589-7500(20)30085-6
EP  - 322
PY  - 2020///
SN  - 2589-7500
SP  - 314
TI  - 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
T2  - The Lancet. Digital Health
UR  - http://dx.doi.org/10.1016/S2589-7500(20)30085-6
UR  - http://hdl.handle.net/10044/1/79148
VL  - 2
ER  -

Download

ProfessorDanielRueckert

Contact

Location

Summary

Citation

BibTex format

RIS format (EndNote, RefMan)