Mouse lung volume reconstruction from efficient groupwise registration of individual histological slices with natural gradient@case.edu

Haibo Wang, Mirabela Rusu, Thea Golden, Andrew Gow, Anant Madabhushi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Mouse lung models facilitate the study of the pathogenesis of various pulmonary diseases such as infections and inflammatory diseases. The co-registration of ex vivo histological data and pre-excised magnetic resonance imaging (MRI) in preclinical mouse models would allow for determination and validation of imaging signatures for different pathobiologies within the lung. While slice-based co-registration could be used, this approach assumes that (a) slice correspondences between the two different modalities exist, and (b) finding slice correspondences often requires the intervention of an expert and is time consuming. A more practical approach is to first reconstruct the 3D histological volume from individual slices, then perform 3D registration with the MR volume. Before the histological reconstruction, image registration is required to compensate for geometric differences between slices. Pairwise algorithms work by registering pairs of successive slices. However, even if successive slices are registered reasonably well, the propagation of registration errors over slices can yield a distorted volumetric reconstruction significantly different in shape from the shape of the true specimen. Groupwise registration can reduce the error propagation by considering more than two successive images during the registration, but existing algorithms are computationally expensive. In this paper, we present an efficient groupwise registration approach, which yields consistent volumetric reconstruction and yet runs equally fast as pairwise registration. The improvements are based on 1) natural gradient which speeds up the transform warping procedure and 2) efficient optimization of the cost function of our groupwise registration. The strength of the natural gradient technique is that it could help mitigate the impact of the uncertainties of the gradient direction across multiple template slices. Experiments on two mouse lung datasets show that compared to pairwise registration, our groupwise approach runs faster in terms of registration convergence, and yields globally more consistent reconstruction.

Original languageEnglish
Title of host publicationMedical Imaging 2013: Image Processing
Volume8669
DOIs
Publication statusPublished - 2013
Externally publishedYes
EventMedical Imaging 2013: Image Processing - Lake Buena Vista, FL, United States
Duration: 10 Feb 201312 Feb 2013

Conference

ConferenceMedical Imaging 2013: Image Processing
CountryUnited States
CityLake Buena Vista, FL
Period10.2.1312.2.13

Fingerprint

lungs
mice
Imaging techniques
Lung
gradients
Pulmonary diseases
Image registration
Magnetic resonance
Cost functions
pathogenesis
Computer-Assisted Image Processing
propagation
infectious diseases
image reconstruction
Lung Diseases
Uncertainty
magnetic resonance
templates
Magnetic Resonance Imaging
signatures

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Wang, H., Rusu, M., Golden, T., Gow, A., & Madabhushi, A. (2013). Mouse lung volume reconstruction from efficient groupwise registration of individual histological slices with natural gradient@case.edu. In Medical Imaging 2013: Image Processing (Vol. 8669). [866914] https://doi.org/10.1117/12.2006860

Mouse lung volume reconstruction from efficient groupwise registration of individual histological slices with natural gradient@case.edu. / Wang, Haibo; Rusu, Mirabela; Golden, Thea; Gow, Andrew; Madabhushi, Anant.

Medical Imaging 2013: Image Processing. Vol. 8669 2013. 866914.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wang, H, Rusu, M, Golden, T, Gow, A & Madabhushi, A 2013, Mouse lung volume reconstruction from efficient groupwise registration of individual histological slices with natural gradient@case.edu. in Medical Imaging 2013: Image Processing. vol. 8669, 866914, Medical Imaging 2013: Image Processing, Lake Buena Vista, FL, United States, 10.2.13. https://doi.org/10.1117/12.2006860
Wang H, Rusu M, Golden T, Gow A, Madabhushi A. Mouse lung volume reconstruction from efficient groupwise registration of individual histological slices with natural gradient@case.edu. In Medical Imaging 2013: Image Processing. Vol. 8669. 2013. 866914 https://doi.org/10.1117/12.2006860
Wang, Haibo ; Rusu, Mirabela ; Golden, Thea ; Gow, Andrew ; Madabhushi, Anant. / Mouse lung volume reconstruction from efficient groupwise registration of individual histological slices with natural gradient@case.edu. Medical Imaging 2013: Image Processing. Vol. 8669 2013.
@inproceedings{b013584446094e038e3af5f838ad2384,
title = "Mouse lung volume reconstruction from efficient groupwise registration of individual histological slices with natural gradient@case.edu",
abstract = "Mouse lung models facilitate the study of the pathogenesis of various pulmonary diseases such as infections and inflammatory diseases. The co-registration of ex vivo histological data and pre-excised magnetic resonance imaging (MRI) in preclinical mouse models would allow for determination and validation of imaging signatures for different pathobiologies within the lung. While slice-based co-registration could be used, this approach assumes that (a) slice correspondences between the two different modalities exist, and (b) finding slice correspondences often requires the intervention of an expert and is time consuming. A more practical approach is to first reconstruct the 3D histological volume from individual slices, then perform 3D registration with the MR volume. Before the histological reconstruction, image registration is required to compensate for geometric differences between slices. Pairwise algorithms work by registering pairs of successive slices. However, even if successive slices are registered reasonably well, the propagation of registration errors over slices can yield a distorted volumetric reconstruction significantly different in shape from the shape of the true specimen. Groupwise registration can reduce the error propagation by considering more than two successive images during the registration, but existing algorithms are computationally expensive. In this paper, we present an efficient groupwise registration approach, which yields consistent volumetric reconstruction and yet runs equally fast as pairwise registration. The improvements are based on 1) natural gradient which speeds up the transform warping procedure and 2) efficient optimization of the cost function of our groupwise registration. The strength of the natural gradient technique is that it could help mitigate the impact of the uncertainties of the gradient direction across multiple template slices. Experiments on two mouse lung datasets show that compared to pairwise registration, our groupwise approach runs faster in terms of registration convergence, and yields globally more consistent reconstruction.",
author = "Haibo Wang and Mirabela Rusu and Thea Golden and Andrew Gow and Anant Madabhushi",
year = "2013",
doi = "10.1117/12.2006860",
language = "English",
isbn = "9780819494436",
volume = "8669",
booktitle = "Medical Imaging 2013: Image Processing",

}

TY - GEN

T1 - Mouse lung volume reconstruction from efficient groupwise registration of individual histological slices with natural gradient@case.edu

AU - Wang, Haibo

AU - Rusu, Mirabela

AU - Golden, Thea

AU - Gow, Andrew

AU - Madabhushi, Anant

PY - 2013

Y1 - 2013

N2 - Mouse lung models facilitate the study of the pathogenesis of various pulmonary diseases such as infections and inflammatory diseases. The co-registration of ex vivo histological data and pre-excised magnetic resonance imaging (MRI) in preclinical mouse models would allow for determination and validation of imaging signatures for different pathobiologies within the lung. While slice-based co-registration could be used, this approach assumes that (a) slice correspondences between the two different modalities exist, and (b) finding slice correspondences often requires the intervention of an expert and is time consuming. A more practical approach is to first reconstruct the 3D histological volume from individual slices, then perform 3D registration with the MR volume. Before the histological reconstruction, image registration is required to compensate for geometric differences between slices. Pairwise algorithms work by registering pairs of successive slices. However, even if successive slices are registered reasonably well, the propagation of registration errors over slices can yield a distorted volumetric reconstruction significantly different in shape from the shape of the true specimen. Groupwise registration can reduce the error propagation by considering more than two successive images during the registration, but existing algorithms are computationally expensive. In this paper, we present an efficient groupwise registration approach, which yields consistent volumetric reconstruction and yet runs equally fast as pairwise registration. The improvements are based on 1) natural gradient which speeds up the transform warping procedure and 2) efficient optimization of the cost function of our groupwise registration. The strength of the natural gradient technique is that it could help mitigate the impact of the uncertainties of the gradient direction across multiple template slices. Experiments on two mouse lung datasets show that compared to pairwise registration, our groupwise approach runs faster in terms of registration convergence, and yields globally more consistent reconstruction.

AB - Mouse lung models facilitate the study of the pathogenesis of various pulmonary diseases such as infections and inflammatory diseases. The co-registration of ex vivo histological data and pre-excised magnetic resonance imaging (MRI) in preclinical mouse models would allow for determination and validation of imaging signatures for different pathobiologies within the lung. While slice-based co-registration could be used, this approach assumes that (a) slice correspondences between the two different modalities exist, and (b) finding slice correspondences often requires the intervention of an expert and is time consuming. A more practical approach is to first reconstruct the 3D histological volume from individual slices, then perform 3D registration with the MR volume. Before the histological reconstruction, image registration is required to compensate for geometric differences between slices. Pairwise algorithms work by registering pairs of successive slices. However, even if successive slices are registered reasonably well, the propagation of registration errors over slices can yield a distorted volumetric reconstruction significantly different in shape from the shape of the true specimen. Groupwise registration can reduce the error propagation by considering more than two successive images during the registration, but existing algorithms are computationally expensive. In this paper, we present an efficient groupwise registration approach, which yields consistent volumetric reconstruction and yet runs equally fast as pairwise registration. The improvements are based on 1) natural gradient which speeds up the transform warping procedure and 2) efficient optimization of the cost function of our groupwise registration. The strength of the natural gradient technique is that it could help mitigate the impact of the uncertainties of the gradient direction across multiple template slices. Experiments on two mouse lung datasets show that compared to pairwise registration, our groupwise approach runs faster in terms of registration convergence, and yields globally more consistent reconstruction.

UR - http://www.scopus.com/inward/record.url?scp=84878322934&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878322934&partnerID=8YFLogxK

U2 - 10.1117/12.2006860

DO - 10.1117/12.2006860

M3 - Conference contribution

SN - 9780819494436

VL - 8669

BT - Medical Imaging 2013: Image Processing

ER -