Literature DB >> 30277270

Machine learning improves classification of preclinical models of pancreatic cancer with chemical exchange saturation transfer MRI.

Joshua M Goldenberg1,2, Julio Cárdenas-Rodríguez3, Mark D Pagel2.   

Abstract

PURPOSE: We sought to assess whether machine learning-based classification approaches can improve the classification of pancreatic tumor models relative to more simplistic analysis methods, using T1 relaxation, CEST, and DCE MRI.
METHODS: The T1 relaxation time constants, % CEST at five saturation frequencies, and vascular permeability constants from DCE MRI were measured from Hs 766 T, MIA PaCa-2, and SU.86.86 pancreatic tumor models. We used each of these measurements as predictors for machine learning classifier algorithms. We also used principal component analysis to reduce the dimensionality of entire CEST spectra and DCE signal evolutions, which were then analyzed using classification methods.
RESULTS: The T1 relaxation time constants, % CEST amplitudes at specific saturation frequencies, and the relative Ktrans and kep values from DCE MRI could not classify all three tumor types. However, the area under the curve from DCE signal evolutions could classify each tumor type. Principal component analysis was used to analyze the entire CEST spectrum and DCE signal evolutions, which predicted the correct tumor model with 87.5% and 85.1% accuracy, respectively.
CONCLUSIONS: Machine learning applied to the entire CEST spectrum improved the classification of the three tumor models, relative to classifications that used % CEST values at single saturation frequencies. A similar improvement was not attained with machine learning applied to T1 relaxation times or DCE signal evolutions, relative to more simplistic analysis methods.
© 2018 International Society for Magnetic Resonance in Medicine.

Entities:  

Keywords:  CEST; DCE. machine learning; MRI; PCA; pancreatic cancer imaging

Mesh:

Year:  2018        PMID: 30277270      PMCID: PMC6258293          DOI: 10.1002/mrm.27439

Source DB:  PubMed          Journal:  Magn Reson Med        ISSN: 0740-3194            Impact factor:   4.668


  26 in total

Review 1.  Machine learning for detection and diagnosis of disease.

Authors:  Paul Sajda
Journal:  Annu Rev Biomed Eng       Date:  2006       Impact factor: 9.590

2.  Optimizing the precision in T1 relaxation estimation using limited flip angles.

Authors:  H Z Wang; S J Riederer; J N Lee
Journal:  Magn Reson Med       Date:  1987-11       Impact factor: 4.668

3.  A comparison of one-shot and recovery methods in T1 imaging.

Authors:  A P Crawley; R M Henkelman
Journal:  Magn Reson Med       Date:  1988-05       Impact factor: 4.668

4.  Machine Learning in Medical Imaging.

Authors:  Miles N Wernick; Yongyi Yang; Jovan G Brankov; Grigori Yourganov; Stephen C Strother
Journal:  IEEE Signal Process Mag       Date:  2010-07       Impact factor: 12.551

5.  Multi-echo length and offset VARied saturation (MeLOVARS) method for improved CEST imaging.

Authors:  Xiaolei Song; Jiadi Xu; Shuli Xia; Nirbhay N Yadav; Bachchu Lal; John Laterra; Jeff W M Bulte; Peter C M van Zijl; Michael T McMahon
Journal:  Magn Reson Med       Date:  2014-12-16       Impact factor: 4.668

Review 6.  Phenotype and genotype of pancreatic cancer cell lines.

Authors:  Emily L Deer; Jessica González-Hernández; Jill D Coursen; Jill E Shea; Josephat Ngatia; Courtney L Scaife; Matthew A Firpo; Sean J Mulvihill
Journal:  Pancreas       Date:  2010-05       Impact factor: 3.327

7.  A linear algorithm of the reference region model for DCE-MRI is robust and relaxes requirements for temporal resolution.

Authors:  Julio Cárdenas-Rodríguez; Christine M Howison; Mark D Pagel
Journal:  Magn Reson Imaging       Date:  2012-12-08       Impact factor: 2.546

8.  Dynamic Contrast Enhanced Magnetic Resonance Imaging in Oncology: Theory, Data Acquisition, Analysis, and Examples.

Authors:  Thomas E Yankeelov; John C Gore
Journal:  Curr Med Imaging Rev       Date:  2009-05-01

Review 9.  Nuts and bolts of chemical exchange saturation transfer MRI.

Authors:  Guanshu Liu; Xiaolei Song; Kannie W Y Chan; Michael T McMahon
Journal:  NMR Biomed       Date:  2013-01-10       Impact factor: 4.044

10.  Downfield-NOE-suppressed amide-CEST-MRI at 7 Tesla provides a unique contrast in human glioblastoma.

Authors:  Moritz Zaiss; Johannes Windschuh; Steffen Goerke; Daniel Paech; Jan-Eric Meissner; Sina Burth; Philipp Kickingereder; Wolfgang Wick; Martin Bendszus; Heinz-Peter Schlemmer; Mark E Ladd; Peter Bachert; Alexander Radbruch
Journal:  Magn Reson Med       Date:  2016-01-27       Impact factor: 4.668

View more
  2 in total

1.  Deep learning-based classification of preclinical breast cancer tumor models using chemical exchange saturation transfer magnetic resonance imaging.

Authors:  Chongxue Bie; Yuguo Li; Yang Zhou; Zaver M Bhujwalla; Xiaolei Song; Guanshu Liu; Peter C M van Zijl; Nirbhay N Yadav
Journal:  NMR Biomed       Date:  2021-10-19       Impact factor: 4.044

2.  Learning-based analysis of amide proton transfer-weighted MRI to identify true progression in glioma patients.

Authors:  Pengfei Guo; Mathias Unberath; Hye-Young Heo; Charles G Eberhart; Michael Lim; Jaishri O Blakeley; Shanshan Jiang
Journal:  Neuroimage Clin       Date:  2022-07-18       Impact factor: 4.891

  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.