Imperial College London
Alternate

ProfessorEricAboagye

Faculty of Medicine, Department of Surgery & Cancer

Professor
 
 
 
//

Contact

 

+44 (0)20 3313 3759eric.aboagye

 
 
//

Assistant

 

Mrs Maureen Francis +44 (0)20 7594 2793

 
//

Location

 

GN1Commonwealth BuildingHammersmith Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Boubnovski:2022:10.1016/j.crad.2022.04.012,
author = {Boubnovski, MM and Chen, M and Linton-Reid, K and Posma, JM and Copley, SJ and Aboagye, EO},
doi = {10.1016/j.crad.2022.04.012},
journal = {Clinical Radiology},
pages = {e620--e627},
title = {Development of a multi-task learning V-Net for pulmonary lobar segmentation on CT and application to diseased lungs},
url = {http://dx.doi.org/10.1016/j.crad.2022.04.012},
volume = {77},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - AIMTo develop a multi-task learning (MTL) V-Net for pulmonary lobar segmentation on computed tomography (CT) and application to diseased lungs.MATERIALS AND METHODSThe described methodology utilises tracheobronchial tree information to enhance segmentation accuracy through the algorithm's spatial familiarity to define lobar extent more accurately. The method undertakes parallel segmentation of lobes and auxiliary tissues simultaneously by employing MTL in conjunction with V-Net-attention, a popular convolutional neural network in the imaging realm. Its performance was validated by an external dataset of patients with four distinct lung conditions: severe lung cancer, COVID-19 pneumonitis, collapsed lungs, and chronic obstructive pulmonary disease (COPD), even though the training data included none of these cases.RESULTSThe following Dice scores were achieved on a per-segment basis: normal lungs 0.97, COPD 0.94, lung cancer 0.94, COVID-19 pneumonitis 0.94, and collapsed lung 0.92, all at p<0.05.CONCLUSIONDespite severe abnormalities, the model provided good performance at segmenting lobes, demonstrating the benefit of tissue learning. The proposed model is poised for adoption in the clinical setting as a robust tool for radiologists and researchers to define the lobar distribution of lung diseases and aid in disease treatment planning.
AU  - Boubnovski,MM
AU  - Chen,M
AU  - Linton-Reid,K
AU  - Posma,JM
AU  - Copley,SJ
AU  - Aboagye,EO
DO  - 10.1016/j.crad.2022.04.012
EP  - 627
PY  - 2022///
SN  - 0009-9260
SP  - 620
TI  - Development of a multi-task learning V-Net for pulmonary lobar segmentation on CT and application to diseased lungs
T2  - Clinical Radiology
UR  - http://dx.doi.org/10.1016/j.crad.2022.04.012
UR  - https://www.sciencedirect.com/science/article/pii/S0009926022002197?via%3Dihub
UR  - http://hdl.handle.net/10044/1/97131
VL  - 77
ER  -
Download