Deformable registration for quantifying longitudinal tumor changes during neoadjuvant chemotherapy

Yangming Ou, Susan P. Weinstein, Emily F. Conant, Sarah Englander, Xiao Da, Bilwaj Gaonkar, Meng Kang Hsieh, Mark Rosen, Angela Demichele, Christos Davatzikos, Despina Kontos

Research output: Contribution to journalArticle

Abstract

Purpose To evaluate DRAMMS, an attribute-based deformable registration algorithm, compared to other intensity-based algorithms, for longitudinal breast MRI registration, and to show its applicability in quantifying tumor changes over the course of neoadjuvant chemotherapy. Methods Breast magnetic resonance images from 14 women undergoing neoadjuvant chemotherapy were analyzed. The accuracy of DRAMMS versus five intensity-based deformable registration methods was evaluated based on 2,380 landmarks independently annotated by two experts, for the entire image volume, different image subregions, and patient subgroups. The registration method with the smallest landmark error was used to quantify tumor changes, by calculating the Jacobian determinant maps of the registration deformation. Results DRAMMS had the smallest landmark errors (6.05±4.86 mm), followed by the intensity-based methods CC-FFD (8.07±3.86 mm), NMI-FFD (8.21±3.81 mm), SSD-FFD (9.46±4.55 mm), Demons (10.76±6.01 mm), and Diffeomorphic Demons (10.82±6.11 mm). Results show that registration accuracy also depends on tumor versus normal tissue regions and different patient subgroups. Conclusions The DRAMMS deformable registration method, driven by attribute-matching and mutual-saliency, can register longitudinal breast magnetic resonance images with a higher accuracy than several intensity-matching methods included in this article. As such, it could be valuable for more accurately quantifying heterogeneous tumor changes as a marker of response to treatment. Magn Reson Med 73:2343-2356, 2015.

Original languageEnglish (US)
Pages (from-to)2343-2356
Number of pages14
JournalMagnetic Resonance in Medicine
Volume73
Issue number6
DOIs
StatePublished - Jun 1 2015
Externally publishedYes

Fingerprint

Drug Therapy
Neoplasms
Breast
Magnetic Resonance Spectroscopy
Silver Sulfadiazine
Therapeutics

Keywords

  • breast cancer
  • deformable image registration
  • evaluation
  • longitudinal breast MRI
  • treatment
  • tumor changes

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Medicine(all)

Cite this

Ou, Y., Weinstein, S. P., Conant, E. F., Englander, S., Da, X., Gaonkar, B., ... Kontos, D. (2015). Deformable registration for quantifying longitudinal tumor changes during neoadjuvant chemotherapy. Magnetic Resonance in Medicine, 73(6), 2343-2356. https://doi.org/10.1002/mrm.25368

Deformable registration for quantifying longitudinal tumor changes during neoadjuvant chemotherapy. / Ou, Yangming; Weinstein, Susan P.; Conant, Emily F.; Englander, Sarah; Da, Xiao; Gaonkar, Bilwaj; Hsieh, Meng Kang; Rosen, Mark; Demichele, Angela; Davatzikos, Christos; Kontos, Despina.

In: Magnetic Resonance in Medicine, Vol. 73, No. 6, 01.06.2015, p. 2343-2356.

Research output: Contribution to journalArticle

Ou, Y, Weinstein, SP, Conant, EF, Englander, S, Da, X, Gaonkar, B, Hsieh, MK, Rosen, M, Demichele, A, Davatzikos, C & Kontos, D 2015, 'Deformable registration for quantifying longitudinal tumor changes during neoadjuvant chemotherapy', Magnetic Resonance in Medicine, vol. 73, no. 6, pp. 2343-2356. https://doi.org/10.1002/mrm.25368
Ou, Yangming ; Weinstein, Susan P. ; Conant, Emily F. ; Englander, Sarah ; Da, Xiao ; Gaonkar, Bilwaj ; Hsieh, Meng Kang ; Rosen, Mark ; Demichele, Angela ; Davatzikos, Christos ; Kontos, Despina. / Deformable registration for quantifying longitudinal tumor changes during neoadjuvant chemotherapy. In: Magnetic Resonance in Medicine. 2015 ; Vol. 73, No. 6. pp. 2343-2356.
@article{731747a081e94a12bdeabf87d4b4e9a6,
title = "Deformable registration for quantifying longitudinal tumor changes during neoadjuvant chemotherapy",
abstract = "Purpose To evaluate DRAMMS, an attribute-based deformable registration algorithm, compared to other intensity-based algorithms, for longitudinal breast MRI registration, and to show its applicability in quantifying tumor changes over the course of neoadjuvant chemotherapy. Methods Breast magnetic resonance images from 14 women undergoing neoadjuvant chemotherapy were analyzed. The accuracy of DRAMMS versus five intensity-based deformable registration methods was evaluated based on 2,380 landmarks independently annotated by two experts, for the entire image volume, different image subregions, and patient subgroups. The registration method with the smallest landmark error was used to quantify tumor changes, by calculating the Jacobian determinant maps of the registration deformation. Results DRAMMS had the smallest landmark errors (6.05±4.86 mm), followed by the intensity-based methods CC-FFD (8.07±3.86 mm), NMI-FFD (8.21±3.81 mm), SSD-FFD (9.46±4.55 mm), Demons (10.76±6.01 mm), and Diffeomorphic Demons (10.82±6.11 mm). Results show that registration accuracy also depends on tumor versus normal tissue regions and different patient subgroups. Conclusions The DRAMMS deformable registration method, driven by attribute-matching and mutual-saliency, can register longitudinal breast magnetic resonance images with a higher accuracy than several intensity-matching methods included in this article. As such, it could be valuable for more accurately quantifying heterogeneous tumor changes as a marker of response to treatment. Magn Reson Med 73:2343-2356, 2015.",
keywords = "breast cancer, deformable image registration, evaluation, longitudinal breast MRI, treatment, tumor changes",
author = "Yangming Ou and Weinstein, {Susan P.} and Conant, {Emily F.} and Sarah Englander and Xiao Da and Bilwaj Gaonkar and Hsieh, {Meng Kang} and Mark Rosen and Angela Demichele and Christos Davatzikos and Despina Kontos",
year = "2015",
month = "6",
day = "1",
doi = "10.1002/mrm.25368",
language = "English (US)",
volume = "73",
pages = "2343--2356",
journal = "Magnetic Resonance in Medicine",
issn = "0740-3194",
publisher = "John Wiley and Sons Inc.",
number = "6",

}

TY - JOUR

T1 - Deformable registration for quantifying longitudinal tumor changes during neoadjuvant chemotherapy

AU - Ou, Yangming

AU - Weinstein, Susan P.

AU - Conant, Emily F.

AU - Englander, Sarah

AU - Da, Xiao

AU - Gaonkar, Bilwaj

AU - Hsieh, Meng Kang

AU - Rosen, Mark

AU - Demichele, Angela

AU - Davatzikos, Christos

AU - Kontos, Despina

PY - 2015/6/1

Y1 - 2015/6/1

N2 - Purpose To evaluate DRAMMS, an attribute-based deformable registration algorithm, compared to other intensity-based algorithms, for longitudinal breast MRI registration, and to show its applicability in quantifying tumor changes over the course of neoadjuvant chemotherapy. Methods Breast magnetic resonance images from 14 women undergoing neoadjuvant chemotherapy were analyzed. The accuracy of DRAMMS versus five intensity-based deformable registration methods was evaluated based on 2,380 landmarks independently annotated by two experts, for the entire image volume, different image subregions, and patient subgroups. The registration method with the smallest landmark error was used to quantify tumor changes, by calculating the Jacobian determinant maps of the registration deformation. Results DRAMMS had the smallest landmark errors (6.05±4.86 mm), followed by the intensity-based methods CC-FFD (8.07±3.86 mm), NMI-FFD (8.21±3.81 mm), SSD-FFD (9.46±4.55 mm), Demons (10.76±6.01 mm), and Diffeomorphic Demons (10.82±6.11 mm). Results show that registration accuracy also depends on tumor versus normal tissue regions and different patient subgroups. Conclusions The DRAMMS deformable registration method, driven by attribute-matching and mutual-saliency, can register longitudinal breast magnetic resonance images with a higher accuracy than several intensity-matching methods included in this article. As such, it could be valuable for more accurately quantifying heterogeneous tumor changes as a marker of response to treatment. Magn Reson Med 73:2343-2356, 2015.

AB - Purpose To evaluate DRAMMS, an attribute-based deformable registration algorithm, compared to other intensity-based algorithms, for longitudinal breast MRI registration, and to show its applicability in quantifying tumor changes over the course of neoadjuvant chemotherapy. Methods Breast magnetic resonance images from 14 women undergoing neoadjuvant chemotherapy were analyzed. The accuracy of DRAMMS versus five intensity-based deformable registration methods was evaluated based on 2,380 landmarks independently annotated by two experts, for the entire image volume, different image subregions, and patient subgroups. The registration method with the smallest landmark error was used to quantify tumor changes, by calculating the Jacobian determinant maps of the registration deformation. Results DRAMMS had the smallest landmark errors (6.05±4.86 mm), followed by the intensity-based methods CC-FFD (8.07±3.86 mm), NMI-FFD (8.21±3.81 mm), SSD-FFD (9.46±4.55 mm), Demons (10.76±6.01 mm), and Diffeomorphic Demons (10.82±6.11 mm). Results show that registration accuracy also depends on tumor versus normal tissue regions and different patient subgroups. Conclusions The DRAMMS deformable registration method, driven by attribute-matching and mutual-saliency, can register longitudinal breast magnetic resonance images with a higher accuracy than several intensity-matching methods included in this article. As such, it could be valuable for more accurately quantifying heterogeneous tumor changes as a marker of response to treatment. Magn Reson Med 73:2343-2356, 2015.

KW - breast cancer

KW - deformable image registration

KW - evaluation

KW - longitudinal breast MRI

KW - treatment

KW - tumor changes

UR - http://www.scopus.com/inward/record.url?scp=84929653305&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929653305&partnerID=8YFLogxK

U2 - 10.1002/mrm.25368

DO - 10.1002/mrm.25368

M3 - Article

VL - 73

SP - 2343

EP - 2356

JO - Magnetic Resonance in Medicine

JF - Magnetic Resonance in Medicine

SN - 0740-3194

IS - 6

ER -