PLOSL: Population learning followed by one shot learning pulmonary image registration using tissue volume preserving and vesselness constraints

•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....

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Medical image analysis Ročník 79; s. 102434
Hlavní autoři: Wang, Di, Pan, Yue, Durumeric, Oguz C., Reinhardt, Joseph M., Hoffman, Eric A., Schroeder, Joyce D., Christensen, Gary E.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Netherlands Elsevier B.V 01.07.2022
Elsevier BV
Témata:
Algorithms
Coders
Computed tomography
Convolutional encoder-decoder network
Datasets
Deep learning
Encoders-Decoders
Expiration
Humans
Image Processing, Computer-Assisted - methods
Image registration
Inspiration
Learning
Lipodystrophy
Lung - diagnostic imaging
Machine learning
Medical imaging
Osteochondrodysplasias
Registration
Subacute Sclerosing Panencephalitis
Tissues
Tomography, X-Ray Computed
Topology
Training
Transfer learning
Deep learning
Image registration
Transfer learning
Convolutional encoder-decoder network
ISSN:1361-8415, 1361-8423, 1361-8423
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•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.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1361-8415
1361-8423
1361-8423
DOI:10.1016/j.media.2022.102434