Automatic pathology classification using a single feature machine learning support - Vector machines

Fernando Yepes-Calderon, Fabian Pedregosa, Bertrand Thirion, Yalin Wang, Natasha Lepore

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Magnetic Resonance Imaging (MRI) has been gaining popularity in the clinic in recent years as a safe in-vivo imaging technique. As a result, large troves of data are being gathered and stored daily that may be used as clinical training sets in hospitals. While numerous machine learning (ML) algorithms have been implemented for Alzheimera's disease classification, their outputs are usually difficult to interpret in the clinical setting. Here, we propose a simple method of rapid diagnostic classification for the clinic using Support Vector Machines (SVM)1 and easy to obtain geometrical measurements that, together with a cortical and sub-cortical brain parcellation, create a robust framework capable of automatic diagnosis with high accuracy. On a significantly large imaging dataset consisting of over 800 subjects taken from the Alzheimera's Disease Neuroimaging Initiative (ADNI) database, classification-success indexes of up to 99.2% are reached with a single measurement.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
PublisherSPIE
Volume9035
ISBN (Print)9780819498281
DOIs
StatePublished - 2014
EventMedical Imaging 2014: Computer-Aided Diagnosis - San Diego, CA, United States
Duration: Feb 18 2014Feb 20 2014

Other

OtherMedical Imaging 2014: Computer-Aided Diagnosis
CountryUnited States
CitySan Diego, CA
Period2/18/142/20/14

Fingerprint

machine learning
pathology
Pathology
Support vector machines
Learning systems
Neuroimaging
Imaging techniques
imaging techniques
Learning algorithms
brain
magnetic resonance
Brain
education
Magnetic Resonance Imaging
Databases
output
Support Vector Machine
Machine Learning

Keywords

  • Alzheimer's disease
  • Fast clinical diagnosis
  • Machine learning
  • Mild cognitive impairment
  • Support vector machines

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Yepes-Calderon, F., Pedregosa, F., Thirion, B., Wang, Y., & Lepore, N. (2014). Automatic pathology classification using a single feature machine learning support - Vector machines. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 9035). [903524] SPIE. https://doi.org/10.1117/12.2043943

Automatic pathology classification using a single feature machine learning support - Vector machines. / Yepes-Calderon, Fernando; Pedregosa, Fabian; Thirion, Bertrand; Wang, Yalin; Lepore, Natasha.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 9035 SPIE, 2014. 903524.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yepes-Calderon, F, Pedregosa, F, Thirion, B, Wang, Y & Lepore, N 2014, Automatic pathology classification using a single feature machine learning support - Vector machines. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 9035, 903524, SPIE, Medical Imaging 2014: Computer-Aided Diagnosis, San Diego, CA, United States, 2/18/14. https://doi.org/10.1117/12.2043943
Yepes-Calderon F, Pedregosa F, Thirion B, Wang Y, Lepore N. Automatic pathology classification using a single feature machine learning support - Vector machines. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 9035. SPIE. 2014. 903524 https://doi.org/10.1117/12.2043943
Yepes-Calderon, Fernando ; Pedregosa, Fabian ; Thirion, Bertrand ; Wang, Yalin ; Lepore, Natasha. / Automatic pathology classification using a single feature machine learning support - Vector machines. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 9035 SPIE, 2014.
@inproceedings{d0e13d67d9a340a1a593e98c974f4e6e,
title = "Automatic pathology classification using a single feature machine learning support - Vector machines",
abstract = "Magnetic Resonance Imaging (MRI) has been gaining popularity in the clinic in recent years as a safe in-vivo imaging technique. As a result, large troves of data are being gathered and stored daily that may be used as clinical training sets in hospitals. While numerous machine learning (ML) algorithms have been implemented for Alzheimera's disease classification, their outputs are usually difficult to interpret in the clinical setting. Here, we propose a simple method of rapid diagnostic classification for the clinic using Support Vector Machines (SVM)1 and easy to obtain geometrical measurements that, together with a cortical and sub-cortical brain parcellation, create a robust framework capable of automatic diagnosis with high accuracy. On a significantly large imaging dataset consisting of over 800 subjects taken from the Alzheimera's Disease Neuroimaging Initiative (ADNI) database, classification-success indexes of up to 99.2{\%} are reached with a single measurement.",
keywords = "Alzheimer's disease, Fast clinical diagnosis, Machine learning, Mild cognitive impairment, Support vector machines",
author = "Fernando Yepes-Calderon and Fabian Pedregosa and Bertrand Thirion and Yalin Wang and Natasha Lepore",
year = "2014",
doi = "10.1117/12.2043943",
language = "English (US)",
isbn = "9780819498281",
volume = "9035",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
publisher = "SPIE",

}

TY - GEN

T1 - Automatic pathology classification using a single feature machine learning support - Vector machines

AU - Yepes-Calderon, Fernando

AU - Pedregosa, Fabian

AU - Thirion, Bertrand

AU - Wang, Yalin

AU - Lepore, Natasha

PY - 2014

Y1 - 2014

N2 - Magnetic Resonance Imaging (MRI) has been gaining popularity in the clinic in recent years as a safe in-vivo imaging technique. As a result, large troves of data are being gathered and stored daily that may be used as clinical training sets in hospitals. While numerous machine learning (ML) algorithms have been implemented for Alzheimera's disease classification, their outputs are usually difficult to interpret in the clinical setting. Here, we propose a simple method of rapid diagnostic classification for the clinic using Support Vector Machines (SVM)1 and easy to obtain geometrical measurements that, together with a cortical and sub-cortical brain parcellation, create a robust framework capable of automatic diagnosis with high accuracy. On a significantly large imaging dataset consisting of over 800 subjects taken from the Alzheimera's Disease Neuroimaging Initiative (ADNI) database, classification-success indexes of up to 99.2% are reached with a single measurement.

AB - Magnetic Resonance Imaging (MRI) has been gaining popularity in the clinic in recent years as a safe in-vivo imaging technique. As a result, large troves of data are being gathered and stored daily that may be used as clinical training sets in hospitals. While numerous machine learning (ML) algorithms have been implemented for Alzheimera's disease classification, their outputs are usually difficult to interpret in the clinical setting. Here, we propose a simple method of rapid diagnostic classification for the clinic using Support Vector Machines (SVM)1 and easy to obtain geometrical measurements that, together with a cortical and sub-cortical brain parcellation, create a robust framework capable of automatic diagnosis with high accuracy. On a significantly large imaging dataset consisting of over 800 subjects taken from the Alzheimera's Disease Neuroimaging Initiative (ADNI) database, classification-success indexes of up to 99.2% are reached with a single measurement.

KW - Alzheimer's disease

KW - Fast clinical diagnosis

KW - Machine learning

KW - Mild cognitive impairment

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=84902105317&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902105317&partnerID=8YFLogxK

U2 - 10.1117/12.2043943

DO - 10.1117/12.2043943

M3 - Conference contribution

AN - SCOPUS:84902105317

SN - 9780819498281

VL - 9035

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

PB - SPIE

ER -