A4 Article in conference proceedings
Automatic Segmentation of Pulmonary Lobes in Pulmonary CT Images using Atlas-based Unsupervised Learning Network (2020)

Hu, R., Wang, H., Ristaniemi, T., Zhu, W., Chen, L., Shen, H., & Rao, F. (2020). Automatic Segmentation of Pulmonary Lobes in Pulmonary CT Images using Atlas-based Unsupervised Learning Network. In NSS/MIC 2020 : IEEE Nuclear Science Symposium and Medical Imaging Conference. IEEE. https://doi.org/10.1109/NSS/MIC42677.2020.9507753

JYU authors or editors

Publication details

All authors or editors: Hu, Ruxue; Wang, Hongkai; Ristaniemi, Tapani; Zhu, Wentao; Chen, Ling; Shen, Hui; Rao, Fan

Parent publication: NSS/MIC 2020 : IEEE Nuclear Science Symposium and Medical Imaging Conference

Conference:

Place and date of conference: Boston, USA, 31.10.-7.11.2020

ISBN: 978-1-7281-7694-9

eISBN: 978-1-7281-7693-2

ISSN: 1082-3654

eISSN: 2577-0829

Publication year: 2020

Publication date: 31/10/2020

Publisher: IEEE

Publication country: United States

Publication language: English

DOI: https://doi.org/10.1109/NSS/MIC42677.2020.9507753

Publication open access: Not open

Publication channel open access:

Abstract

Pulmonary lobes segmentation of pulmonary CT images is important for assistant therapy and diagnosis of pulmonary disease in many clinical tasks. Recently supervised deep learning methods are applied widely in fast automatic medical image segmentation including pulmonary lobes segmentation of pulmonary CT images. However, they require plenty of ground truth due to their supervised learning scheme, which are always difficult to realize in practice. To address this issue, in this study we extend an existed unsupervised learning network with an extra pulmonary mask constraint to develop a deformable pulmonary lobes atlas and apply it for fast automatic segmentation of pulmonary lobes in pulmonary CT images. The experiment on 40 pulmonary CT images shows that our method can segment the pulmonary lobes in seconds, and achieve average Dice of 0.906 ± 0.044 and average surface distance of 0.495 ± 0.380 mm, which outperforms the state-of-the-art methods in segmentation accuracy. Our method successfully combines the advantages of both deformable atlas and unsupervised learning for automatic segmentation and ensures the consistent and topology preserving of pulmonary lobes without any postprocessing.

Keywords: imaging; computed tomography; segmentation; lungs; machine learning

Free keywords: automatic segmentation; computed tomography

Contributing organizations

Ministry reporting: Yes

Reporting Year: 2021

JUFO rating: 1