Non-rigid registration between histological and MR images of the prostate: A joint segmentation and registration framework

Yangming Ou, Dinggang Shen, Michael Feldman, John Tomaszewski, Christos Davatzikos

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

Abstract

This paper presents a 3D non-rigid registration algorithm between histological and MR images of the prostate with cancer. To compensate for the loss of 3D integrity in the histology sectioning process, series of 2D histological slices are first reconstructed into a 3D histological volume. After that, the 3D histology-MRI registration is obtained by maximizing a) landmark similarity and b) cancer region overlap between the two images. The former aims to capture distortions at prostate boundary and internal bloblike structures; and the latter aims to capture distortions specifically at cancer regions. In particular, landmark similarities, the former, is maximized by an annealing process, where correspondences between the automatically-detected boundary and internal landmarks are iteratively established in a fuzzy-to-deterministic fashion. Cancer region overlap, the latter, is maximized in a joint cancer segmentation and registration framework, where the two interleaved problems - segmentation and registration - inform each other in an iterative fashion. Registration accuracy is established by comparing against human-rater-defined landmarks and by comparing with other methods. The ultimate goal of this registration is to warp the histologically-defined cancer ground truth into MRI, for more thoroughly understanding MRI signal characteristics of the prostate cancerous tissue, which will promote the MRI-based prostate cancer diagnosis in the future studies.

Original languageEnglish (US)
Title of host publication2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009
Pages125-132
Number of pages8
DOIs
StatePublished - 2009
Externally publishedYes
Event2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009 - Miami, FL, United States
Duration: Jun 20 2009Jun 25 2009

Other

Other2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009
CountryUnited States
CityMiami, FL
Period6/20/096/25/09

Fingerprint

Magnetic resonance imaging
Histology
Annealing
Tissue

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Biomedical Engineering

Cite this

Ou, Y., Shen, D., Feldman, M., Tomaszewski, J., & Davatzikos, C. (2009). Non-rigid registration between histological and MR images of the prostate: A joint segmentation and registration framework. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009 (pp. 125-132). [5204347] https://doi.org/10.1109/CVPR.2009.5204347

Non-rigid registration between histological and MR images of the prostate : A joint segmentation and registration framework. / Ou, Yangming; Shen, Dinggang; Feldman, Michael; Tomaszewski, John; Davatzikos, Christos.

2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009. 2009. p. 125-132 5204347.

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

Ou, Y, Shen, D, Feldman, M, Tomaszewski, J & Davatzikos, C 2009, Non-rigid registration between histological and MR images of the prostate: A joint segmentation and registration framework. in 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009., 5204347, pp. 125-132, 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, Miami, FL, United States, 6/20/09. https://doi.org/10.1109/CVPR.2009.5204347
Ou Y, Shen D, Feldman M, Tomaszewski J, Davatzikos C. Non-rigid registration between histological and MR images of the prostate: A joint segmentation and registration framework. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009. 2009. p. 125-132. 5204347 https://doi.org/10.1109/CVPR.2009.5204347
Ou, Yangming ; Shen, Dinggang ; Feldman, Michael ; Tomaszewski, John ; Davatzikos, Christos. / Non-rigid registration between histological and MR images of the prostate : A joint segmentation and registration framework. 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009. 2009. pp. 125-132
@inproceedings{c200bd17c1cd486783945723cb211a40,
title = "Non-rigid registration between histological and MR images of the prostate: A joint segmentation and registration framework",
abstract = "This paper presents a 3D non-rigid registration algorithm between histological and MR images of the prostate with cancer. To compensate for the loss of 3D integrity in the histology sectioning process, series of 2D histological slices are first reconstructed into a 3D histological volume. After that, the 3D histology-MRI registration is obtained by maximizing a) landmark similarity and b) cancer region overlap between the two images. The former aims to capture distortions at prostate boundary and internal bloblike structures; and the latter aims to capture distortions specifically at cancer regions. In particular, landmark similarities, the former, is maximized by an annealing process, where correspondences between the automatically-detected boundary and internal landmarks are iteratively established in a fuzzy-to-deterministic fashion. Cancer region overlap, the latter, is maximized in a joint cancer segmentation and registration framework, where the two interleaved problems - segmentation and registration - inform each other in an iterative fashion. Registration accuracy is established by comparing against human-rater-defined landmarks and by comparing with other methods. The ultimate goal of this registration is to warp the histologically-defined cancer ground truth into MRI, for more thoroughly understanding MRI signal characteristics of the prostate cancerous tissue, which will promote the MRI-based prostate cancer diagnosis in the future studies.",
author = "Yangming Ou and Dinggang Shen and Michael Feldman and John Tomaszewski and Christos Davatzikos",
year = "2009",
doi = "10.1109/CVPR.2009.5204347",
language = "English (US)",
isbn = "9781424439911",
pages = "125--132",
booktitle = "2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009",

}

TY - GEN

T1 - Non-rigid registration between histological and MR images of the prostate

T2 - A joint segmentation and registration framework

AU - Ou, Yangming

AU - Shen, Dinggang

AU - Feldman, Michael

AU - Tomaszewski, John

AU - Davatzikos, Christos

PY - 2009

Y1 - 2009

N2 - This paper presents a 3D non-rigid registration algorithm between histological and MR images of the prostate with cancer. To compensate for the loss of 3D integrity in the histology sectioning process, series of 2D histological slices are first reconstructed into a 3D histological volume. After that, the 3D histology-MRI registration is obtained by maximizing a) landmark similarity and b) cancer region overlap between the two images. The former aims to capture distortions at prostate boundary and internal bloblike structures; and the latter aims to capture distortions specifically at cancer regions. In particular, landmark similarities, the former, is maximized by an annealing process, where correspondences between the automatically-detected boundary and internal landmarks are iteratively established in a fuzzy-to-deterministic fashion. Cancer region overlap, the latter, is maximized in a joint cancer segmentation and registration framework, where the two interleaved problems - segmentation and registration - inform each other in an iterative fashion. Registration accuracy is established by comparing against human-rater-defined landmarks and by comparing with other methods. The ultimate goal of this registration is to warp the histologically-defined cancer ground truth into MRI, for more thoroughly understanding MRI signal characteristics of the prostate cancerous tissue, which will promote the MRI-based prostate cancer diagnosis in the future studies.

AB - This paper presents a 3D non-rigid registration algorithm between histological and MR images of the prostate with cancer. To compensate for the loss of 3D integrity in the histology sectioning process, series of 2D histological slices are first reconstructed into a 3D histological volume. After that, the 3D histology-MRI registration is obtained by maximizing a) landmark similarity and b) cancer region overlap between the two images. The former aims to capture distortions at prostate boundary and internal bloblike structures; and the latter aims to capture distortions specifically at cancer regions. In particular, landmark similarities, the former, is maximized by an annealing process, where correspondences between the automatically-detected boundary and internal landmarks are iteratively established in a fuzzy-to-deterministic fashion. Cancer region overlap, the latter, is maximized in a joint cancer segmentation and registration framework, where the two interleaved problems - segmentation and registration - inform each other in an iterative fashion. Registration accuracy is established by comparing against human-rater-defined landmarks and by comparing with other methods. The ultimate goal of this registration is to warp the histologically-defined cancer ground truth into MRI, for more thoroughly understanding MRI signal characteristics of the prostate cancerous tissue, which will promote the MRI-based prostate cancer diagnosis in the future studies.

UR - http://www.scopus.com/inward/record.url?scp=70449560654&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449560654&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2009.5204347

DO - 10.1109/CVPR.2009.5204347

M3 - Conference contribution

AN - SCOPUS:70449560654

SN - 9781424439911

SP - 125

EP - 132

BT - 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009

ER -