Literature DB >> 24321226

Molecular and metabolic pattern classification for detection of brain glioma progression.

Farzin Imani1, Fernando E Boada2, Frank S Lieberman3, Denise K Davis2, James M Mountz2.   

Abstract

OBJECTIVES: The ability to differentiate between brain tumor progression and radiation therapy induced necrosis is critical for appropriate patient management. In order to improve the differential diagnosis, we combined fluorine-18 2-fluoro-deoxyglucose positron emission tomography ((18)F-FDG PET), proton magnetic resonance spectroscopy ((1)H MRS) and histological data to develop a multi-parametric machine-learning model.
METHODS: We enrolled twelve post-therapy patients with grade 2 and 3 gliomas that were suspicious of tumor progression. All patients underwent (18)F-FDG PET and (1)H MRS. Maximal standardized uptake value (SUVmax) of the tumors and reference regions were obtained. Multiple 2D maps of choline (Cho), creatine (Cr), and N-acetylaspartate (NAA) of the tumors were generated. A support vector machine (SVM) learning model was established to take imaging biomarkers and histological data as input vectors. A combination of clinical follow-up and multiple sequential MRI studies served as the basis for assessing the clinical outcome. All vector combinations were evaluated for diagnostic accuracy and cross validation. The optimal cutoff value of individual parameters was calculated using Receiver operating characteristic (ROC) plots.
RESULTS: The SVM and ROC analyses both demonstrated that SUVmax of the lesion was the most significant single diagnostic parameter (75% accuracy) followed by Cho concentration (67% accuracy). SVM analysis of all paired parameters showed SUVmax and Cho concentration in combination could achieve 83% accuracy. SUVmax of the lesion paired with SUVmax of the white matter as well as the tumor Cho paired with the tumor Cr both showed 83% accuracy. These were the most significant paired diagnostic parameters of either modality. Combining all four parameters did not improve the results. However, addition of two more parameters, Cho and Cr of brain parenchyma contralateral to the tumor, increased the accuracy to 92%.
CONCLUSION: This study suggests that SVM models may improve detection of glioma progression more accurately than single parametric imaging methods. RESEARCH SUPPORT: National Cancer Institute, Cancer Center Support Grant Supplement Award, Imaging Response Assessment Teams.
Copyright © 2013 Elsevier Ireland Ltd. All rights reserved.

Entities:  

Keywords:  (1)H MRS; (18)F-FDG PET; Glioma; Support vector machine

Mesh:

Substances:

Year:  2013        PMID: 24321226      PMCID: PMC3923608          DOI: 10.1016/j.ejrad.2013.06.033

Source DB:  PubMed          Journal:  Eur J Radiol        ISSN: 0720-048X            Impact factor:   3.528


  18 in total

1.  On the origin of cancer cells.

Authors:  O WARBURG
Journal:  Science       Date:  1956-02-24       Impact factor: 47.728

2.  Cerebral astrocytomas: histopathologic correlation of MR and CT contrast enhancement with stereotactic biopsy.

Authors:  F Earnest; P J Kelly; B W Scheithauer; B A Kall; T L Cascino; R L Ehman; G S Forbes; P L Axley
Journal:  Radiology       Date:  1988-03       Impact factor: 11.105

Review 3.  Proton MR spectroscopy in neoplastic and non-neoplastic brain disorders.

Authors:  M Castillo; L Kwock; J Scatliff; S K Mukherji
Journal:  Magn Reson Imaging Clin N Am       Date:  1998-02       Impact factor: 2.266

4.  Absolute concentrations of metabolites in the adult human brain in vivo: quantification of localized proton MR spectra.

Authors:  T Michaelis; K D Merboldt; H Bruhn; W Hänicke; J Frahm
Journal:  Radiology       Date:  1993-04       Impact factor: 11.105

5.  Quantitative MR imaging and spectroscopy of brain tumours: a step forward?

Authors:  Dita Wagnerova; Vit Herynek; Alberto Malucelli; Monika Dezortova; Josef Vymazal; Dusan Urgosik; Martin Syrucek; Filip Jiru; Antonin Skoch; Robert Bartos; Martin Sames; Milan Hajek
Journal:  Eur Radiol       Date:  2012-06-12       Impact factor: 5.315

6.  Stereotactic histologic correlations of computed tomography- and magnetic resonance imaging-defined abnormalities in patients with glial neoplasms.

Authors:  P J Kelly; C Daumas-Duport; B W Scheithauer; B A Kall; D B Kispert
Journal:  Mayo Clin Proc       Date:  1987-06       Impact factor: 7.616

Review 7.  A review of chemical issues in 1H NMR spectroscopy: N-acetyl-L-aspartate, creatine and choline.

Authors:  B L Miller
Journal:  NMR Biomed       Date:  1991-04       Impact factor: 4.044

8.  FDG-PET on irradiated brain tumor: ten years' summary.

Authors:  S X Wang; J Boethius; K Ericson
Journal:  Acta Radiol       Date:  2006-02       Impact factor: 1.990

9.  Development of the human brain: in vivo quantification of metabolite and water content with proton magnetic resonance spectroscopy.

Authors:  R Kreis; T Ernst; B D Ross
Journal:  Magn Reson Med       Date:  1993-10       Impact factor: 4.668

10.  Increased choline levels coincide with enhanced proliferative activity of human neuroepithelial brain tumors.

Authors:  Sebastian Herminghaus; Ulrich Pilatus; Walter Möller-Hartmann; Peter Raab; Heinrich Lanfermann; Wolfgang Schlote; Friedhelm E Zanella
Journal:  NMR Biomed       Date:  2002-10       Impact factor: 4.044

View more
  11 in total

Review 1.  Machine learning studies on major brain diseases: 5-year trends of 2014-2018.

Authors:  Koji Sakai; Kei Yamada
Journal:  Jpn J Radiol       Date:  2018-11-29       Impact factor: 2.374

Review 2.  Positron emission tomography of high-grade gliomas.

Authors:  Guido Frosina
Journal:  J Neurooncol       Date:  2016-02-20       Impact factor: 4.130

Review 3.  Choline metabolism-based molecular diagnosis of cancer: an update.

Authors:  Kristine Glunde; Marie-France Penet; Lu Jiang; Michael A Jacobs; Zaver M Bhujwalla
Journal:  Expert Rev Mol Diagn       Date:  2015-04-28       Impact factor: 5.225

Review 4.  Neuro-Oncology Practice Clinical Debate: FDG PET to differentiate glioblastoma recurrence from treatment-related changes.

Authors:  Ephraim E Parent; Derek R Johnson; Tyler Gleason; Javier E Villanueva-Meyer
Journal:  Neurooncol Pract       Date:  2021-05-04

Review 5.  An Update on the Approach to the Imaging of Brain Tumors.

Authors:  Katherine M Mullen; Raymond Y Huang
Journal:  Curr Neurol Neurosci Rep       Date:  2017-07       Impact factor: 5.081

6.  2D-QSAR and 3D-QSAR Analyses for EGFR Inhibitors.

Authors:  Manman Zhao; Lin Wang; Linfeng Zheng; Mengying Zhang; Chun Qiu; Yuhui Zhang; Dongshu Du; Bing Niu
Journal:  Biomed Res Int       Date:  2017-05-29       Impact factor: 3.411

7.  Pseudoprogression of brain tumors.

Authors:  Stefanie C Thust; Martin J van den Bent; Marion Smits
Journal:  J Magn Reson Imaging       Date:  2018-05-07       Impact factor: 4.813

8.  Joint EANM/EANO/RANO practice guidelines/SNMMI procedure standards for imaging of gliomas using PET with radiolabelled amino acids and [18F]FDG: version 1.0.

Authors:  Ian Law; Nathalie L Albert; Javier Arbizu; Ronald Boellaard; Alexander Drzezga; Norbert Galldiks; Christian la Fougère; Karl-Josef Langen; Egesta Lopci; Val Lowe; Jonathan McConathy; Harald H Quick; Bernhard Sattler; David M Schuster; Jörg-Christian Tonn; Michael Weller
Journal:  Eur J Nucl Med Mol Imaging       Date:  2018-12-05       Impact factor: 9.236

9.  Multiparametric radiomic tissue signature and machine learning for distinguishing radiation necrosis from tumor progression after stereotactic radiosurgery.

Authors:  Xuguang Chen; Vishwa S Parekh; Luke Peng; Michael D Chan; Kristin J Redmond; Michael Soike; Emory McTyre; Doris Lin; Michael A Jacobs; Lawrence R Kleinberg
Journal:  Neurooncol Adv       Date:  2021-10-25

Review 10.  Big Data to Knowledge: Application of Machine Learning to Predictive Modeling of Therapeutic Response in Cancer.

Authors:  Sukanya Panja; Sarra Rahem; Cassandra J Chu; Antonina Mitrofanova
Journal:  Curr Genomics       Date:  2021-12-16       Impact factor: 2.689

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.