Literature DB >> 25923676

Machine learning methods for the classification of gliomas: Initial results using features extracted from MR spectroscopy.

G Ranjith1, R Parvathy2, V Vikas3, Kesavadas Chandrasekharan2, Suresh Nair2.   

Abstract

CONTEXT: With the advent of new imaging modalities, radiologists are faced with handling increasing volumes of data for diagnosis and treatment planning. The use of automated and intelligent systems is becoming essential in such a scenario. Machine learning, a branch of artificial intelligence, is increasingly being used in medical image analysis applications such as image segmentation, registration and computer-aided diagnosis and detection. Histopathological analysis is currently the gold standard for classification of brain tumors. The use of machine learning algorithms along with extraction of relevant features from magnetic resonance imaging (MRI) holds promise of replacing conventional invasive methods of tumor classification. AIMS: The aim of the study is to classify gliomas into benign and malignant types using MRI data. SETTINGS AND
DESIGN: Retrospective data from 28 patients who were diagnosed with glioma were used for the analysis. WHO Grade II (low-grade astrocytoma) was classified as benign while Grade III (anaplastic astrocytoma) and Grade IV (glioblastoma multiforme) were classified as malignant. METHODS AND MATERIALS: Features were extracted from MR spectroscopy. The classification was done using four machine learning algorithms: multilayer perceptrons, support vector machine, random forest and locally weighted learning.
RESULTS: Three of the four machine learning algorithms gave an area under ROC curve in excess of 0.80. Random forest gave the best performance in terms of AUC (0.911) while sensitivity was best for locally weighted learning (86.1%).
CONCLUSIONS: The performance of different machine learning algorithms in the classification of gliomas is promising. An even better performance may be expected by integrating features extracted from other MR sequences.
© The Author(s) 2015 Reprints and permissions: sagepub.co.uk/journalsPermissions.nav.

Entities:  

Keywords:  feature extraction; machine learning; magnetic resonance spectroscopy; multilayer perceptrons; random forest; support vector machine

Mesh:

Substances:

Year:  2015        PMID: 25923676      PMCID: PMC4757153          DOI: 10.1177/1971400915576637

Source DB:  PubMed          Journal:  Neuroradiol J        ISSN: 1971-4009


  15 in total

Review 1.  Magnetic resonance spectroscopy of the brain: review of metabolites and clinical applications.

Authors:  D P Soares; M Law
Journal:  Clin Radiol       Date:  2008-08-30       Impact factor: 2.350

2.  Advanced MR imaging techniques in the evaluation of nonenhancing gliomas: perfusion-weighted imaging compared with proton magnetic resonance spectroscopy and tumor grade.

Authors:  Neslin Sahin; Elias R Melhem; Sumei Wang; Jaroslaw Krejza; Harish Poptani; Sanjeev Chawla; Gaurav Verma
Journal:  Neuroradiol J       Date:  2013-11-07

3.  Computed tomographic virtual colonoscopy computer-aided polyp detection in a screening population.

Authors:  Ronald M Summers; Jianhua Yao; Perry J Pickhardt; Marek Franaszek; Ingmar Bitter; Daniel Brickman; Vamsi Krishna; J Richard Choi
Journal:  Gastroenterology       Date:  2005-12       Impact factor: 22.682

4.  Noninvasive evaluation of cerebral glioma grade by using multivoxel 3D proton MR spectroscopy.

Authors:  QingShi Zeng; HePeng Liu; Kai Zhang; ChuanFu Li; GengYin Zhou
Journal:  Magn Reson Imaging       Date:  2010-09-15       Impact factor: 2.546

5.  Investigating brain tumor differentiation with diffusion and perfusion metrics at 3T MRI using pattern recognition techniques.

Authors:  Patricia Svolos; Evangelia Tsolaki; Eftychia Kapsalaki; Kyriaki Theodorou; Kostas Fountas; Ioannis Fezoulidis; Ioannis Tsougos
Journal:  Magn Reson Imaging       Date:  2013-07-30       Impact factor: 2.546

6.  Correlation between choline level measured by proton MR spectroscopy and Ki-67 labeling index in gliomas.

Authors:  H Shimizu; T Kumabe; R Shirane; T Yoshimoto
Journal:  AJNR Am J Neuroradiol       Date:  2000-04       Impact factor: 3.825

7.  Specific expression of N-acetylaspartate in neurons, oligodendrocyte-type-2 astrocyte progenitors, and immature oligodendrocytes in vitro.

Authors:  J Urenjak; S R Williams; D G Gadian; M Noble
Journal:  J Neurochem       Date:  1992-07       Impact factor: 5.372

8.  Screening for lung cancer with low-dose spiral computed tomography.

Authors:  Stephen J Swensen; James R Jett; Jeff A Sloan; David E Midthun; Thomas E Hartman; Anne-Marie Sykes; Gregory L Aughenbaugh; Frank E Zink; Shauna L Hillman; Gayle R Noetzel; Randolph S Marks; Amy C Clayton; Peter C Pairolero
Journal:  Am J Respir Crit Care Med       Date:  2002-02-15       Impact factor: 21.405

9.  Proton magnetic resonance spectroscopic imaging in children with recurrent primary brain tumors.

Authors:  K E Warren; J A Frank; J L Black; R S Hill; J H Duyn; A A Aikin; B K Lewis; P C Adamson; F M Balis
Journal:  J Clin Oncol       Date:  2000-03       Impact factor: 44.544

10.  Peripheral lung cancer: screening and detection with low-dose spiral CT versus radiography.

Authors:  M Kaneko; K Eguchi; H Ohmatsu; R Kakinuma; T Naruke; K Suemasu; N Moriyama
Journal:  Radiology       Date:  1996-12       Impact factor: 11.105

View more
  12 in total

Review 1.  Precision Digital Oncology: Emerging Role of Radiomics-based Biomarkers and Artificial Intelligence for Advanced Imaging and Characterization of Brain Tumors.

Authors:  Reza Forghani
Journal:  Radiol Imaging Cancer       Date:  2020-07-31

Review 2.  Can artificial intelligence overtake human intelligence on the bumpy road towards glioma therapy?

Authors:  Precilla S Daisy; T S Anitha
Journal:  Med Oncol       Date:  2021-04-03       Impact factor: 3.064

3.  Changes in metabolites in the brain of patients with fibromyalgia after treatment with an NMDA receptor antagonist.

Authors:  Nicolas Fayed; Barbara Oliván; Yolanda Lopez Del Hoyo; Eva Andrés; Mari Cruz Perez-Yus; Alicia Fayed; Luisa F Angel; Antoni Serrano-Blanco; Miquel Roca; Javier Garcia Campayo
Journal:  Neuroradiol J       Date:  2019-06-19

4.  Malignancy probability map as a novel imaging biomarker to predict malignancy distribution: employing MRS in GBM patients.

Authors:  Manijeh Beigi; Kevan Ghasemi; Parvin Mirzaghavami; Mohammadreza Khanmohammadi; Hamidreza SalighehRad
Journal:  J Neurooncol       Date:  2018-03-14       Impact factor: 4.130

5.  Machine learning: a useful radiological adjunct in determination of a newly diagnosed glioma's grade and IDH status.

Authors:  Céline De Looze; Alan Beausang; Jane Cryan; Teresa Loftus; Patrick G Buckley; Michael Farrell; Seamus Looby; Richard Reilly; Francesca Brett; Hugh Kearney
Journal:  J Neurooncol       Date:  2018-05-16       Impact factor: 4.130

6.  Multivariable non-invasive association of isocitrate dehydrogenase mutational status in World Health Organization grade II and III gliomas with advanced magnetic resonance imaging T2 mapping techniques.

Authors:  Maike Kern; Timo A Auer; Uli Fehrenbach; Yasemin Tanyildizi; Thomas Picht; Martin Misch; Edzard Wiener
Journal:  Neuroradiol J       Date:  2020-01-19

Review 7.  Optimal differentiation of high- and low-grade glioma and metastasis: a meta-analysis of perfusion, diffusion, and spectroscopy metrics.

Authors:  Jurgita Usinskiene; Agne Ulyte; Atle Bjørnerud; Jonas Venius; Vasileios K Katsaros; Ryte Rynkeviciene; Simona Letautiene; Darius Norkus; Kestutis Suziedelis; Saulius Rocka; Andrius Usinskas; Eduardas Aleknavicius
Journal:  Neuroradiology       Date:  2016-01-15       Impact factor: 2.804

8.  Multimodal MRI features predict isocitrate dehydrogenase genotype in high-grade gliomas.

Authors:  Biqi Zhang; Ken Chang; Shakti Ramkissoon; Shyam Tanguturi; Wenya Linda Bi; David A Reardon; Keith L Ligon; Brian M Alexander; Patrick Y Wen; Raymond Y Huang
Journal:  Neuro Oncol       Date:  2016-06-26       Impact factor: 13.029

9.  Machine Learning Versus Logistic Regression Methods for 2-Year Mortality Prognostication in a Small, Heterogeneous Glioma Database.

Authors:  Sandip S Panesar; Rhett N D'Souza; Fang-Cheng Yeh; Juan C Fernandez-Miranda
Journal:  World Neurosurg X       Date:  2019-01-24

10.  Spatial habitats from multiparametric MR imaging are associated with signaling pathway activities and survival in glioblastoma.

Authors:  Katherine Dextraze; Abhijoy Saha; Donnie Kim; Shivali Narang; Michael Lehrer; Anita Rao; Saphal Narang; Dinesh Rao; Salmaan Ahmed; Venkatesh Madhugiri; Clifton David Fuller; Michelle M Kim; Sunil Krishnan; Ganesh Rao; Arvind Rao
Journal:  Oncotarget       Date:  2017-12-05
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.