access icon openaccess New approach for automatic classification of Alzheimer's disease, mild cognitive impairment and healthy brain magnetic resonance images

Explored is the utility of modelling brain magnetic resonance images as a fractal object for the classification of healthy brain images against those with Alzheimer's disease (AD) or mild cognitive impairment (MCI). More precisely, fractal multi-scale analysis is used to build feature vectors from the derived Hurst's exponents. These are then classified by support vector machines (SVMs). Three experiments were conducted: in the first the SVM was trained to classify AD against healthy images. In the second experiment, the SVM was trained to classify AD against MCI and, in the third experiment, a multiclass SVM was trained to classify all three types of images. The experimental results, using the 10-fold cross-validation technique, indicate that the SVM achieved 97.08% ± 0.05 correct classification rate, 98.09% ± 0.04 sensitivity and 96.07% ± 0.07 specificity for the classification of healthy against MCI images, thus outperforming recent works found in the literature. For the classification of MCI against AD, the SVM achieved 97.5% ± 0.04 correct classification rate, 100% sensitivity and 94.93% ± 0.08 specificity. The third experiment also showed that the multiclass SVM provided highly accurate classification results. The processing time for a given image was 25 s. These findings suggest that this approach is efficient and may be promising for clinical applications.

Inspec keywords: medical image processing; diseases; cognition; image classification; biomedical MRI; support vector machines

Other keywords: cross-validation technique; Hurst exponents; healthy brain image classification; mild cognitive impairment; fractal multiscale analysis; MCI; Alzheimer disease; clinical applications; fractal object; support vector machines; healthy brain magnetic resonance images; SVM; AD classification

Subjects: Image recognition; Biomedical magnetic resonance imaging and spectroscopy; Biology and medical computing; Medical magnetic resonance imaging and spectroscopy; Computer vision and image processing techniques; Patient diagnostic methods and instrumentation; Knowledge engineering techniques

References

    1. 1)
      • 7. Vapnik, V.: ‘The nature of statistical learning theory’ (Springer, Berlin, 1995).
    2. 2)
      • 14. www.mathworks.com (consulted in 18 March 2014).
    3. 3)
      • 12. http://adni.loni.ucla.edu (consulted in 18 March 2014).
    4. 4)
    5. 5)
      • 11. http://www.med.harvard.edu/aanlib/ (consulted in 18 March 2014).
    6. 6)
    7. 7)
      • 13. http://www.oasis-brains.org/ (consulted in 18 March 2014).
    8. 8)
    9. 9)
    10. 10)
    11. 11)
      • 8. Lahmiri, S., Boukadoum, M.: ‘Alzheimer disease detection in brain magnetic resonance images using multi-scale fractal analysis’, ISRN Radiol., 2013, Article ID 627303, doi: 10.5402/2013/627303.
    12. 12)
    13. 13)
      • 15. Rees, D.G.: ‘Essential statistics’ (Chapman & Hall/CRC, 2001, 4th edn.).
    14. 14)
    15. 15)
    16. 16)
    17. 17)
http://iet.metastore.ingenta.com/content/journals/10.1049/htl.2013.0022
Loading

Related content

content/journals/10.1049/htl.2013.0022
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading