Development of a multi-task learning V-Net for pulmonary lobar segmentation on CT and application to diseased lungs

File Description SizeFormat 
CRAD_acceptedversion.pdfFile embargoed until 27 May 20237.69 MBAdobe PDF    Request a copy
Title: Development of a multi-task learning V-Net for pulmonary lobar segmentation on CT and application to diseased lungs
Authors: Boubnovski, MM
Chen, M
Linton-Reid, K
Posma, JM
Copley, SJ
Aboagye, EO
Item Type: Journal Article
Abstract: AIM To develop a multi-task learning (MTL) V-Net for pulmonary lobar segmentation on computed tomography (CT) and application to diseased lungs. MATERIALS AND METHODS The 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. RESULTS The 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. CONCLUSION Despite 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.
Issue Date: 1-Aug-2022
Date of Acceptance: 21-Apr-2022
DOI: 10.1016/j.crad.2022.04.012
ISSN: 0009-9260
Publisher: Elsevier BV
Start Page: e620
End Page: e627
Journal / Book Title: Clinical Radiology
Volume: 77
Issue: 8
Copyright Statement: © 2022 Published by Elsevier Ltd on behalf of The Royal College of Radiologists. This manuscript is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Licence
Sponsor/Funder: Medical Research Council (MRC)
Medical Research Council
Funder's Grant Number: MR/S004033/1
Keywords: Nuclear Medicine & Medical Imaging
1103 Clinical Sciences
Publication Status: Published
Embargo Date: 2023-05-27
Open Access location:
Online Publication Date: 2022-05-28
Appears in Collections:Department of Metabolism, Digestion and Reproduction
Department of Surgery and Cancer
Faculty of Medicine

This item is licensed under a Creative Commons License Creative Commons