Quantification of local metabolic tumor volume changes by registering blended PET-CT images for prediction of pathologic tumor response Conference Paper

  


Authors: Riyahi, S.; Choi, W.; Liu, C. J.; Nadeem, S.; Tan, S.; Zhong, H.; Chen, W.; Wu, A. J.; Mechalakos, J. G.; Deasy, J. O.; Lu, W.
Editors: Melbourne, A.; Licandro, R.; DiFranco, M.; Rota, P.; Gau, M.; Kampel, M.; Aughwane, R.; Moeskops, P.; Schwartz, E.; Robinson, E.; Makropoulos, A.
Title: Quantification of local metabolic tumor volume changes by registering blended PET-CT images for prediction of pathologic tumor response
Conference Title: 1st International Workshop on Data Driven Treatment Response Assessment (DATRA 2018) held in conjunction with the 21st International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)
Abstract: Quantification of local metabolic tumor volume (MTV) changes after Chemo-radiotherapy would allow accurate tumor response evaluation. Currently, local MTV changes in esophageal (soft-tissue) cancer are measured by registering follow-up PET to baseline PET using the same transformation obtained by deformable registration of follow-up CT to baseline CT. Such approach is suboptimal because PET and CT capture fundamentally different properties (metabolic vs. anatomy) of a tumor. In this work we combined PET and CT images into a single blended PET-CT image and registered follow-up blended PET-CT image to baseline blended PET-CT image. B-spline regularized diffeomorphic registration was used to characterize the large MTV shrinkage. Jacobian of the resulting transformation was computed to measure the local MTV changes. Radiomic features (intensity and texture) were then extracted from the Jacobian map to predict pathologic tumor response. Local MTV changes calculated using blended PET-CT registration achieved the highest correlation with ground truth segmentation (R = 0.88) compared to PET-PET (R = 0.80) and CT-CT (R = 0.67) registrations. Moreover, using blended PET-CT registration, the multivariate prediction model achieved the highest accuracy with only one Jacobian co-occurrence texture feature (accuracy = 82.3%). This novel framework can replace the conventional approach that applies CT-CT transformation to the PET data for longitudinal evaluation of tumor response. © Springer Nature Switzerland AG 2018.
Keywords: metabolism; image analysis; pathology; computerized tomography; medical imaging; tumors; forecasting; texture features; pediatrics; tumor response; deformable registration; prediction model; conventional approach; metadata; metabolic tumor volumes; computer aided analysis; co-occurrence; diffeomorphic registrations
Journal Title Lecture Notes in Computer Science
Volume: 11076
Conference Dates: 2018 Sep 16
Conference Location: Granada, Spain
ISBN: 0302-9743
Publisher: Springer  
Location: Cham, Switzerland
Date Published: 2018-01-01
Start Page: 31
End Page: 41
Language: English
DOI: 10.1007/978-3-030-00807-9_4
PROVIDER: scopus
DOI/URL:

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85054861153&doi=10.1007%2f978-3-030-00807-9_4&partnerID=40&md5=2578d4c03b9cf02ddbc2ace875a4eaac
Notes: Conference Paper -- Export Date: 1 November 2018 -- Source: Scopus
Altmetric
What is Altmetric?
Citation Impact
What is Dimensions Citation Badge?
MSK Authors
  1. Abraham Jing-Ching Wu
    347 Wu
  2. James G Mechalakos
    156 Mechalakos
  3. Joseph Owen Deasy
    471 Deasy
  4. Wei Lu
    59 Lu
  5. Wookjin Choi
    18 Choi
  6. Mohamad Sadegh Riyahi Alam
    46 Riyahi Alam
  7. Chia-Ju Liu
    8 Liu
  8. Saad Nadeem
    42 Nadeem
Related MSK Work