Registering Histologic and MR Images of Prostate for Image-based Cancer Detection

Yiqiang Zhan, Yangming Ou, Michael Feldman, John Tomaszeweski, Christos Davatzikos, Dinggang Shen

Research output: Contribution to journalArticle

Abstract

Rationale and Objectives: Needle biopsy is currently the only way to confirm prostate cancer. To increase prostate cancer diagnostic rate, needles are expected to be deployed at suspicious cancer locations. High-contrast magnetic resonance (MR) imaging provides a powerful tool for detecting suspicious cancerous tissues. To do this, MR appearances of cancerous tissue should be characterized and learned from a sufficient number of prostate MR images with known cancer information. However, ground-truth cancer information is only available in histologic images. Therefore it is necessary to warp ground-truth cancerous regions in histological images to MR images by a registration procedure. The objective of this article is to develop a registration technique for aligning histological and MR images of the same prostate. Material and Methods: Five pairs of histological and T2-weighted MR images of radical prostatectomy specimens are collected. For each pair, registration is guided by two sets of correspondences that can be reliably established on prostate boundaries and internal salient bloblike structures of histologic and MR images. Results: Our developed registration method can accurately register histologic and MR images. It yields results comparable to manual registration, in terms of landmark distance and volume overlap. It also outperforms both affine registration and boundary-guided registration methods. Conclusions: We have developed a novel method for deformable registration of histologic and MR images of the same prostate. Besides the collection of ground-truth cancer information in MR images, the method has other potential applications. An automatic, accurate registration of histologic and MR images actually builds a bridge between in vivo anatomical information and ex vivo pathologic information, which is valuable for various clinical studies.

Original languageEnglish (US)
Pages (from-to)1367-1381
Number of pages15
JournalAcademic Radiology
Volume14
Issue number11
DOIs
StatePublished - Nov 2007
Externally publishedYes

Fingerprint

Prostate
Magnetic Resonance Spectroscopy
Neoplasms
Prostatic Neoplasms
Histological Techniques
Needle Biopsy
Prostatectomy
Needles
Magnetic Resonance Imaging

Keywords

  • biopsy
  • deformable registration
  • histologic image
  • MR image
  • Prostate cancer

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Zhan, Y., Ou, Y., Feldman, M., Tomaszeweski, J., Davatzikos, C., & Shen, D. (2007). Registering Histologic and MR Images of Prostate for Image-based Cancer Detection. Academic Radiology, 14(11), 1367-1381. https://doi.org/10.1016/j.acra.2007.07.018

Registering Histologic and MR Images of Prostate for Image-based Cancer Detection. / Zhan, Yiqiang; Ou, Yangming; Feldman, Michael; Tomaszeweski, John; Davatzikos, Christos; Shen, Dinggang.

In: Academic Radiology, Vol. 14, No. 11, 11.2007, p. 1367-1381.

Research output: Contribution to journalArticle

Zhan, Y, Ou, Y, Feldman, M, Tomaszeweski, J, Davatzikos, C & Shen, D 2007, 'Registering Histologic and MR Images of Prostate for Image-based Cancer Detection', Academic Radiology, vol. 14, no. 11, pp. 1367-1381. https://doi.org/10.1016/j.acra.2007.07.018
Zhan Y, Ou Y, Feldman M, Tomaszeweski J, Davatzikos C, Shen D. Registering Histologic and MR Images of Prostate for Image-based Cancer Detection. Academic Radiology. 2007 Nov;14(11):1367-1381. https://doi.org/10.1016/j.acra.2007.07.018
Zhan, Yiqiang ; Ou, Yangming ; Feldman, Michael ; Tomaszeweski, John ; Davatzikos, Christos ; Shen, Dinggang. / Registering Histologic and MR Images of Prostate for Image-based Cancer Detection. In: Academic Radiology. 2007 ; Vol. 14, No. 11. pp. 1367-1381.
@article{4c332ad3cc85410a862b21bcf7378289,
title = "Registering Histologic and MR Images of Prostate for Image-based Cancer Detection",
abstract = "Rationale and Objectives: Needle biopsy is currently the only way to confirm prostate cancer. To increase prostate cancer diagnostic rate, needles are expected to be deployed at suspicious cancer locations. High-contrast magnetic resonance (MR) imaging provides a powerful tool for detecting suspicious cancerous tissues. To do this, MR appearances of cancerous tissue should be characterized and learned from a sufficient number of prostate MR images with known cancer information. However, ground-truth cancer information is only available in histologic images. Therefore it is necessary to warp ground-truth cancerous regions in histological images to MR images by a registration procedure. The objective of this article is to develop a registration technique for aligning histological and MR images of the same prostate. Material and Methods: Five pairs of histological and T2-weighted MR images of radical prostatectomy specimens are collected. For each pair, registration is guided by two sets of correspondences that can be reliably established on prostate boundaries and internal salient bloblike structures of histologic and MR images. Results: Our developed registration method can accurately register histologic and MR images. It yields results comparable to manual registration, in terms of landmark distance and volume overlap. It also outperforms both affine registration and boundary-guided registration methods. Conclusions: We have developed a novel method for deformable registration of histologic and MR images of the same prostate. Besides the collection of ground-truth cancer information in MR images, the method has other potential applications. An automatic, accurate registration of histologic and MR images actually builds a bridge between in vivo anatomical information and ex vivo pathologic information, which is valuable for various clinical studies.",
keywords = "biopsy, deformable registration, histologic image, MR image, Prostate cancer",
author = "Yiqiang Zhan and Yangming Ou and Michael Feldman and John Tomaszeweski and Christos Davatzikos and Dinggang Shen",
year = "2007",
month = "11",
doi = "10.1016/j.acra.2007.07.018",
language = "English (US)",
volume = "14",
pages = "1367--1381",
journal = "Academic Radiology",
issn = "1076-6332",
publisher = "Elsevier USA",
number = "11",

}

TY - JOUR

T1 - Registering Histologic and MR Images of Prostate for Image-based Cancer Detection

AU - Zhan, Yiqiang

AU - Ou, Yangming

AU - Feldman, Michael

AU - Tomaszeweski, John

AU - Davatzikos, Christos

AU - Shen, Dinggang

PY - 2007/11

Y1 - 2007/11

N2 - Rationale and Objectives: Needle biopsy is currently the only way to confirm prostate cancer. To increase prostate cancer diagnostic rate, needles are expected to be deployed at suspicious cancer locations. High-contrast magnetic resonance (MR) imaging provides a powerful tool for detecting suspicious cancerous tissues. To do this, MR appearances of cancerous tissue should be characterized and learned from a sufficient number of prostate MR images with known cancer information. However, ground-truth cancer information is only available in histologic images. Therefore it is necessary to warp ground-truth cancerous regions in histological images to MR images by a registration procedure. The objective of this article is to develop a registration technique for aligning histological and MR images of the same prostate. Material and Methods: Five pairs of histological and T2-weighted MR images of radical prostatectomy specimens are collected. For each pair, registration is guided by two sets of correspondences that can be reliably established on prostate boundaries and internal salient bloblike structures of histologic and MR images. Results: Our developed registration method can accurately register histologic and MR images. It yields results comparable to manual registration, in terms of landmark distance and volume overlap. It also outperforms both affine registration and boundary-guided registration methods. Conclusions: We have developed a novel method for deformable registration of histologic and MR images of the same prostate. Besides the collection of ground-truth cancer information in MR images, the method has other potential applications. An automatic, accurate registration of histologic and MR images actually builds a bridge between in vivo anatomical information and ex vivo pathologic information, which is valuable for various clinical studies.

AB - Rationale and Objectives: Needle biopsy is currently the only way to confirm prostate cancer. To increase prostate cancer diagnostic rate, needles are expected to be deployed at suspicious cancer locations. High-contrast magnetic resonance (MR) imaging provides a powerful tool for detecting suspicious cancerous tissues. To do this, MR appearances of cancerous tissue should be characterized and learned from a sufficient number of prostate MR images with known cancer information. However, ground-truth cancer information is only available in histologic images. Therefore it is necessary to warp ground-truth cancerous regions in histological images to MR images by a registration procedure. The objective of this article is to develop a registration technique for aligning histological and MR images of the same prostate. Material and Methods: Five pairs of histological and T2-weighted MR images of radical prostatectomy specimens are collected. For each pair, registration is guided by two sets of correspondences that can be reliably established on prostate boundaries and internal salient bloblike structures of histologic and MR images. Results: Our developed registration method can accurately register histologic and MR images. It yields results comparable to manual registration, in terms of landmark distance and volume overlap. It also outperforms both affine registration and boundary-guided registration methods. Conclusions: We have developed a novel method for deformable registration of histologic and MR images of the same prostate. Besides the collection of ground-truth cancer information in MR images, the method has other potential applications. An automatic, accurate registration of histologic and MR images actually builds a bridge between in vivo anatomical information and ex vivo pathologic information, which is valuable for various clinical studies.

KW - biopsy

KW - deformable registration

KW - histologic image

KW - MR image

KW - Prostate cancer

UR - http://www.scopus.com/inward/record.url?scp=35349013507&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35349013507&partnerID=8YFLogxK

U2 - 10.1016/j.acra.2007.07.018

DO - 10.1016/j.acra.2007.07.018

M3 - Article

VL - 14

SP - 1367

EP - 1381

JO - Academic Radiology

JF - Academic Radiology

SN - 1076-6332

IS - 11

ER -