Multimodal Learning for Lung Segmentation: Enhancing UTE MRI Segmentation with CT Datasets

Partho Ghosh; Keegan R. Staab; Jonathan L. Percy; Abhilash Kizhakke Puliyakote; Marrissa McIntosh; Andrew Hahn; Sean B. Fain; Sarah E. Gerard

doi:10.1109/ISBI60581.2025.10980692

Conference proceeding

Multimodal Learning for Lung Segmentation: Enhancing UTE MRI Segmentation with CT Datasets

Partho Ghosh, Keegan R. Staab, Jonathan L. Percy, Abhilash Kizhakke Puliyakote, Marrissa McIntosh, Andrew Hahn, Sean B. Fain and Sarah E. Gerard

Proceedings (International Symposium on Biomedical Imaging), pp.1-5

04/14/2025

DOI: 10.1109/ISBI60581.2025.10980692

View Online

Abstract

Ultrashort echo time (UTE) magnetic resonance imaging (MRI) produces high-resolution structural images of the lungs without the ionizing radiation risks associated with computed tomography (CT) imaging. Lung segmentation in UTE is a necessary precursor to biomarker analysis, however, there are challenges associated with limited labeled training data, intensity inhomogeneity, noise, and image gradients. In this work, CT datasets are leveraged to improve the robustness of UTE lung segmentation, given limited labeled training data in the UTE domain. A novel joint training framework is proposed to simultaneously learn structural patterns important for multimodal lung segmentation. Additionally, a learnable downsample layer is proposed to enable training on full 3D CT and MRI images, while maintaining network complexity. Lastly, a false positive penalization loss is proposed to decrease erroneous segmentations associated with noise and gradients in UTE MRI. An ablation study evaluates each component's contribution, with the proposed approach achieving a Dice coefficient of 0.97 and a surface distance of 1.05 mm.

Computed Tomography

Magnetic Resonance Imaging

Noise

Biomedical imaging

Deep Learning

Image resolution

Image segmentation

Lungs

Multimodal

Pulmonary

Segmentation

Training

Training data

Transfer learning

UTE MRI

Details

Title: Subtitle: Multimodal Learning for Lung Segmentation: Enhancing UTE MRI Segmentation with CT Datasets
Creators: Partho Ghosh - University of Iowa
Keegan R. Staab - University of Iowa
Jonathan L. Percy - University of Iowa
Abhilash Kizhakke Puliyakote - University of Iowa, Radiology
Marrissa McIntosh - University of Iowa
Andrew Hahn - University of Iowa
Sean B. Fain - University of Iowa
Sarah E. Gerard - University of Iowa
Resource Type: Conference proceeding
Publication Details: Proceedings (International Symposium on Biomedical Imaging), pp.1-5
Publisher: IEEE
DOI: 10.1109/ISBI60581.2025.10980692
ISSN: 1945-7928
eISSN: 1945-8452
Number of pages: 5
Language: English
Date published: 04/14/2025
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Radiology; Electrical and Computer Engineering; Health and Human Physiology
Record Identifier: 9984825528202771

Metrics

1 Record Views