MRI lung lobe segmentation in pediatric cystic fibrosis patients using a recurrent neural network trained with publicly accessible CT datasets.

Pusterla, Orso; Heule, Rahel; Santini, Francesco; Weikert, Thomas; Willers, Corin; Andermatt, Simon; Sandkühler, Robin; Nyilas, Sylvia; Latzin, Philipp; Bieri, Oliver; Bauman, Grzegorz (2022). MRI lung lobe segmentation in pediatric cystic fibrosis patients using a recurrent neural network trained with publicly accessible CT datasets. Magnetic resonance in medicine, 88(1), pp. 391-405. Wiley-Liss 10.1002/mrm.29184

[img]
Preview
Text
Magnetic_Resonance_in_Med_-_2022_-_Pusterla_-_MRI_lung_lobe_segmentation_in_pediatric_cystic_fibrosis_patients_using_a.pdf - Published Version
Available under License Creative Commons: Attribution-Noncommercial (CC-BY-NC).

Download (1MB) | Preview

PURPOSE

To introduce a widely applicable workflow for pulmonary lobe segmentation of MR images using a recurrent neural network (RNN) trained with chest CT datasets. The feasibility is demonstrated for 2D coronal ultrafast balanced SSFP (ufSSFP) MRI.

METHODS

Lung lobes of 250 publicly accessible CT datasets of adults were segmented with an open-source CT-specific algorithm. To match 2D ufSSFP MRI data of pediatric patients, both CT data and segmentations were translated into pseudo-MR images that were masked to suppress anatomy outside the lung. Network-1 was trained with pseudo-MR images and lobe segmentations and then applied to 1000 masked ufSSFP images to predict lobe segmentations. These outputs were directly used as targets to train Network-2 and Network-3 with non-masked ufSSFP data as inputs, as well as an additional whole-lung mask as input for Network-2. Network predictions were compared to reference manual lobe segmentations of ufSSFP data in 20 pediatric cystic fibrosis patients. Manual lobe segmentations were performed by splitting available whole-lung segmentations into lobes.

RESULTS

Network-1 was able to segment the lobes of ufSSFP images, and Network-2 and Network-3 further increased segmentation accuracy and robustness. The average all-lobe Dice similarity coefficients were 95.0 ± 2.8 (mean ± pooled SD [%]) and 96.4 ± 2.5, 93.0 ± 2.0; and the average median Hausdorff distances were 6.1 ± 0.9 (mean ± SD [mm]), 5.3 ± 1.1, 7.1 ± 1.3 for Network-1, Network-2, and Network-3, respectively.

CONCLUSION

Recurrent neural network lung lobe segmentation of 2D ufSSFP imaging is feasible, in good agreement with manual segmentations. The proposed workflow might provide access to automated lobe segmentations for various lung MRI examinations and quantitative analyses.

Item Type:

Journal Article (Original Article)

Division/Institute:

04 Faculty of Medicine > Department of Gynaecology, Paediatrics and Endocrinology (DFKE) > Clinic of Paediatric Medicine
04 Faculty of Medicine > Department of Radiology, Neuroradiology and Nuclear Medicine (DRNN) > Institute of Diagnostic, Interventional and Paediatric Radiology
04 Faculty of Medicine > Department of Gynaecology, Paediatrics and Endocrinology (DFKE) > Clinic of Paediatric Medicine > Paediatric Pneumology

UniBE Contributor:

Pusterla, Andrea Orso, Willers, Christoph Corin, Nyilas, Sylvia Meryl, Latzin, Philipp

Subjects:

600 Technology > 610 Medicine & health

ISSN:

0740-3194

Publisher:

Wiley-Liss

Language:

English

Submitter:

Anette van Dorland

Date Deposited:

30 Mar 2022 09:28

Last Modified:

08 Jun 2023 12:30

Publisher DOI:

10.1002/mrm.29184

PubMed ID:

35348244

Uncontrolled Keywords:

automated segmentation computed tomography cystic fibrosis lung MRI lung lobe neural network pediatrics

BORIS DOI:

10.48350/168408

URI:

https://boris.unibe.ch/id/eprint/168408

Actions (login required)

Edit item Edit item
Provide Feedback