PORTR

Pre-operative and post-recurrence brain tumor registration

Dongjin Kwon, Marc Niethammer, Hamed Akbari, Michel Bilello, Christos Davatzikos, Kilian M. Pohl

Research output: Contribution to journalArticle

Abstract

We propose a new method for deformable registration of pre-operative and post-recurrence brain MR scans of glioma patients. Performing this type of intra-subject registration is challenging as tumor, resection, recurrence, and edema cause large deformations, missing correspondences, and inconsistent intensity profiles between the scans. To address this challenging task, our method, called PORTR, explicitly accounts for pathological information. It segments tumor, resection cavity, and recurrence based on models specific to each scan. PORTR then uses the resulting maps to exclude pathological regions from the image-based correspondence term while simultaneously measuring the overlap between the aligned tumor and resection cavity. Embedded into a symmetric registration framework, we determine the optimal solution by taking advantage of both discrete and continuous search methods. We apply our method to scans of 24 glioma patients. Both quantitative and qualitative analysis of the results clearly show that our method is superior to other state-of-the-art approaches.

Original languageEnglish (US)
Article number6678314
Pages (from-to)651-667
Number of pages17
JournalIEEE Transactions on Medical Imaging
Volume33
Issue number3
DOIs
StatePublished - 2014
Externally publishedYes

Fingerprint

Brain Neoplasms
Tumors
Brain
Recurrence
Glioma
Neoplasms
Edema

Keywords

  • Brain tumor magnetic resonance imaging (MRI)
  • Deformable registration
  • Discrete-continuous optimization
  • Tumor growth model
  • Tumor segmentation

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Radiological and Ultrasound Technology
  • Software

Cite this

Kwon, D., Niethammer, M., Akbari, H., Bilello, M., Davatzikos, C., & Pohl, K. M. (2014). PORTR: Pre-operative and post-recurrence brain tumor registration. IEEE Transactions on Medical Imaging, 33(3), 651-667. [6678314]. https://doi.org/10.1109/TMI.2013.2293478

PORTR : Pre-operative and post-recurrence brain tumor registration. / Kwon, Dongjin; Niethammer, Marc; Akbari, Hamed; Bilello, Michel; Davatzikos, Christos; Pohl, Kilian M.

In: IEEE Transactions on Medical Imaging, Vol. 33, No. 3, 6678314, 2014, p. 651-667.

Research output: Contribution to journalArticle

Kwon, D, Niethammer, M, Akbari, H, Bilello, M, Davatzikos, C & Pohl, KM 2014, 'PORTR: Pre-operative and post-recurrence brain tumor registration', IEEE Transactions on Medical Imaging, vol. 33, no. 3, 6678314, pp. 651-667. https://doi.org/10.1109/TMI.2013.2293478
Kwon D, Niethammer M, Akbari H, Bilello M, Davatzikos C, Pohl KM. PORTR: Pre-operative and post-recurrence brain tumor registration. IEEE Transactions on Medical Imaging. 2014;33(3):651-667. 6678314. https://doi.org/10.1109/TMI.2013.2293478
Kwon, Dongjin ; Niethammer, Marc ; Akbari, Hamed ; Bilello, Michel ; Davatzikos, Christos ; Pohl, Kilian M. / PORTR : Pre-operative and post-recurrence brain tumor registration. In: IEEE Transactions on Medical Imaging. 2014 ; Vol. 33, No. 3. pp. 651-667.
@article{7b6f1ca891df45e4af61ccedb9d8afb5,
title = "PORTR: Pre-operative and post-recurrence brain tumor registration",
abstract = "We propose a new method for deformable registration of pre-operative and post-recurrence brain MR scans of glioma patients. Performing this type of intra-subject registration is challenging as tumor, resection, recurrence, and edema cause large deformations, missing correspondences, and inconsistent intensity profiles between the scans. To address this challenging task, our method, called PORTR, explicitly accounts for pathological information. It segments tumor, resection cavity, and recurrence based on models specific to each scan. PORTR then uses the resulting maps to exclude pathological regions from the image-based correspondence term while simultaneously measuring the overlap between the aligned tumor and resection cavity. Embedded into a symmetric registration framework, we determine the optimal solution by taking advantage of both discrete and continuous search methods. We apply our method to scans of 24 glioma patients. Both quantitative and qualitative analysis of the results clearly show that our method is superior to other state-of-the-art approaches.",
keywords = "Brain tumor magnetic resonance imaging (MRI), Deformable registration, Discrete-continuous optimization, Tumor growth model, Tumor segmentation",
author = "Dongjin Kwon and Marc Niethammer and Hamed Akbari and Michel Bilello and Christos Davatzikos and Pohl, {Kilian M.}",
year = "2014",
doi = "10.1109/TMI.2013.2293478",
language = "English (US)",
volume = "33",
pages = "651--667",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - PORTR

T2 - Pre-operative and post-recurrence brain tumor registration

AU - Kwon, Dongjin

AU - Niethammer, Marc

AU - Akbari, Hamed

AU - Bilello, Michel

AU - Davatzikos, Christos

AU - Pohl, Kilian M.

PY - 2014

Y1 - 2014

N2 - We propose a new method for deformable registration of pre-operative and post-recurrence brain MR scans of glioma patients. Performing this type of intra-subject registration is challenging as tumor, resection, recurrence, and edema cause large deformations, missing correspondences, and inconsistent intensity profiles between the scans. To address this challenging task, our method, called PORTR, explicitly accounts for pathological information. It segments tumor, resection cavity, and recurrence based on models specific to each scan. PORTR then uses the resulting maps to exclude pathological regions from the image-based correspondence term while simultaneously measuring the overlap between the aligned tumor and resection cavity. Embedded into a symmetric registration framework, we determine the optimal solution by taking advantage of both discrete and continuous search methods. We apply our method to scans of 24 glioma patients. Both quantitative and qualitative analysis of the results clearly show that our method is superior to other state-of-the-art approaches.

AB - We propose a new method for deformable registration of pre-operative and post-recurrence brain MR scans of glioma patients. Performing this type of intra-subject registration is challenging as tumor, resection, recurrence, and edema cause large deformations, missing correspondences, and inconsistent intensity profiles between the scans. To address this challenging task, our method, called PORTR, explicitly accounts for pathological information. It segments tumor, resection cavity, and recurrence based on models specific to each scan. PORTR then uses the resulting maps to exclude pathological regions from the image-based correspondence term while simultaneously measuring the overlap between the aligned tumor and resection cavity. Embedded into a symmetric registration framework, we determine the optimal solution by taking advantage of both discrete and continuous search methods. We apply our method to scans of 24 glioma patients. Both quantitative and qualitative analysis of the results clearly show that our method is superior to other state-of-the-art approaches.

KW - Brain tumor magnetic resonance imaging (MRI)

KW - Deformable registration

KW - Discrete-continuous optimization

KW - Tumor growth model

KW - Tumor segmentation

UR - http://www.scopus.com/inward/record.url?scp=84896305853&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896305853&partnerID=8YFLogxK

U2 - 10.1109/TMI.2013.2293478

DO - 10.1109/TMI.2013.2293478

M3 - Article

VL - 33

SP - 651

EP - 667

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 3

M1 - 6678314

ER -