PLOSL: Population Learning Followed by One Shot Learning Pulmonary Image Registration Using Tissue Volume Preserving and Vesselness Constraints

Di Wang; Yue Pan; Oguz C Durumeric; Joseph M Reinhardt; Eric A Hoffman; Joyce D Schroeder; Gary E Christensen

doi:10.1016/j.media.2022.102434

Back

PLOSL: Population Learning Followed by One Shot Learning Pulmonary Image Registration Using Tissue Volume Preserving and Vesselness Constraints

Journal article

Open access

Peer reviewed

PLOSL: Population Learning Followed by One Shot Learning Pulmonary Image Registration Using Tissue Volume Preserving and Vesselness Constraints

Di Wang, Yue Pan, Oguz C Durumeric, Joseph M Reinhardt, Eric A Hoffman, Joyce D Schroeder and Gary E Christensen

Medical image analysis, Vol.79, pp.102434-102434

04/01/2022

DOI: 10.1016/j.media.2022.102434

PMID: 35430476

Files and links (1)

url

https://doi.org/10.1016/j.media.2022.102434View

Published (Version of record) Open Access

Abstract

•The proposed method was designed for pulmonary CT image registration•Adding one-shot learning improves population learning image registration•Intensity changes between inspiration-expiration lung CT images are accommodated•The vesselness constraint improves pulmonary image registration accuracy•The proposed method achieved sub-voxel accuracy on DIR-LAB and SPIROMICS data sets [Display omitted] This paper presents the Population Learning followed by One Shot Learning (PLOSL) pulmonary image registration method. PLOSL is a fast unsupervised learning-based framework for 3D-CT pulmonary image registration algorithm based on combining population learning (PL) and one-shot learning (OSL). The PLOSL image registration has the advantages of the PL and OSL approaches while reducing their respective drawbacks. The advantages of PLOSL include improved performance over PL, substantially reducing OSL training time and reducing the likelihood of OSL getting stuck in local minima. PLOSL pulmonary image registration uses tissue volume preserving and vesselness constraints for registration of inspiration-to-expiration and expiration-to-inspiration pulmonary CT images. A coarse-to-fine convolution encoder-decoder CNN architecture is used to register large and small shape features. During training, the sum of squared tissue volume difference (SSTVD) compensates for intensity differences between inspiration and expiration computed tomography (CT) images and the sum of squared vesselness measure difference (SSVMD) helps match the lung vessel tree. Results show that the PLOSL (SSTVD+SSVMD) algorithm achieved subvoxel landmark error while preserving pulmonary topology on the SPIROMICS data set, the public DIR-LAB COPDGene and 4DCT data sets.

Convolutional encoder-decoder network

Deep learning

Image Registration

Transfer learning

Details

Title: Subtitle: PLOSL: Population Learning Followed by One Shot Learning Pulmonary Image Registration Using Tissue Volume Preserving and Vesselness Constraints
Creators: Di Wang - University of Iowa
Yue Pan - Elekta (United Kingdom)
Oguz C Durumeric - University of Iowa
Joseph M Reinhardt - University of Iowa
Eric A Hoffman - University of Iowa
Joyce D Schroeder - University of Utah
Gary E Christensen - University of Iowa
Resource Type: Journal article
Publication Details: Medical image analysis, Vol.79, pp.102434-102434
DOI: 10.1016/j.media.2022.102434
PMID: 35430476
NLM abbreviation: Med Image Anal
ISSN: 1361-8415
eISSN: 1361-8423
Publisher: Elsevier B.V
Language: English
Date published: 04/01/2022
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Radiology; Electrical and Computer Engineering; Iowa Technology Institute; Radiation Oncology; Radiation Research Laboratory; The Iowa Institute for Biomedical Imaging; Mathematics; Advanced Pulmonary Physiomic Imaging Laboratory; Holden Comprehensive Cancer Center; Internal Medicine
Record Identifier: 9984243957102771

Metrics

18 Record Views

14 Times Cited - Web of Science