DEMANS ÖZELLİKLERİNİN BELİRLENMESİ İÇİN FİLTRE ÖZNİTELİK SEÇİM ANALİZİ

Demans hastalıkları nöropsikiyatrik bozukluklar olarak tanımlanır. Yaşlandıkça bir demans hastalığına yakalanma şansı da artış göstermektedir. Manyetik rezonans görüntüleme teknikleri ile iki boyutlu dilimlenmiş beyin taramaları oluşturulabilir. Bu taramalar üzerinden bölgelerin üç boyutlu ölçümlerine ulaşılabilir. ADNI veri setindeki örnekler için, beyin özellikleri Freesurfer beyin analiz aracı kullanılarak çıkarılmaktadır. Bu özelliklerin ve demografik verinin öğrenme algoritmalarında parametreler olarak yer almasıyla, bilinmeyen bir örnek, sağlıklı veya demans olarak etiketlenebilir. Öte yandan, tüm özellik setindeki bazı öznitelikler diğerlerine göre daha az yararlı veya direkt etkisiz olabilir. Bu araştırmanın amacı, en belirgin demans özelliklerini belirlemek adına ilk adım olarak öznitelik sayısını azaltmaktır. Bu amaçla, toplam 2264 numune (471 AH, 428 gHBB, 669 eHBB, 696 sağlıklı kontrol), % 65 eğitim seti (1464 numune) ve % 35 test seti (800 numune) olmak üzere iki gruba ayrılmaktadır. Çeşitli filtre öznitelik seçim algoritmaları, Bayes tabanlı ve ağaç tabanlı sınıflandırıcılarla birlikte farklı parametreler üzerinden test edilmektedir. % 76,50'ye varan test performans doğruluğu oranları ayrıntılı olarak analiz edilmektedir. Öznitelik setinin tamamını işlemek yerine, doğru şekilde daha az öznitelik alındığında genel performans artış eğilimindedir.

Anahtar Kelimeler:

Alzheimer hastalığı, Demans, Filtre öznitelik seçimi, ADNI, Freesurfer

FILTER FEATURE SELECTION ANALYSIS TO DETERMINE THE CHARACTERISTICS OF DEMENTIA

Dementias are known as neuropsychiatric disorders. As getting old, the chance of coming down with a dementia disease increases. Two-dimensional sliced brain scans can be generated via magnetic resonance imaging. Three-dimensional measurements of regions can be reached from those scans. For the samples in the ADNI dataset, the brain features are extracted through operating the Freesurfer brain analyzing tool. Parametrizing those features and demographic information in learning algorithms can label an unknown sample as healthy or dementia. On the other hand, some of the features in the initial set may be less practical than others. In this research, the aim is to decrease the feature-size, not the feature-dimension, as a first step to determine the most distinctive dementia characteristics. To that end, a total of 2264 samples (471 AD, 428 lMCI, 669 eMCI, 696 healthy controls) are divided into two sets: 65% training set (1464 samples) and 35% test set (800 samples). Various filter feature selection algorithms are tested over different parameters together with multiple Bayesian-based and tree-based classifiers. Test performance accuracy rates up to 76.50% are analyzed in detail. Instead of processing the whole feature set, the overall performance tends to increase with correctly fewer attributes taken.

Keywords:

Alzheimer’s disease, Dementia, Filter feature selection, ADNI, Freesurfer,

PDF

___

Alam, S., Kwon, G. R., & Initi, A. s. D. N. (2017). Alzheimer disease classification using KPCA, LDA, and multi-kernel learning SVM. International Journal of Imaging Systems and Technology, 27(2), 133-143. doi: http://dx.doi.org/10.1002/ima.22217
Aldous, D. (1991). The continuum random tree. I. The Annals of Probability, 1-28.
Bhargava, N., Sharma, G., Bhargava, R., & Mathuria, M. (2013). Decision tree analysis on j48 algorithm for data mining. Proceedings of International Journal of Advanced Research in Computer Science and Software Engineering, 3(6).
Delgado, J., Moure, J. C., Vives-Gilabert, Y., Delfino, M., Espinosa, A., & Gomez-Anson, B. (2014). Improving the Execution Performance of FreeSurfer. Neuroinformatics, 12(3), 413-421. doi: http://dx.doi.org/10.1007/s12021-013-9214-1
Dimitriadis, S. I., Liparas, D., & Initi, A. s. D. N. (2018). How random is the random forest ? Random forest algorithm on the service of structural imaging biomarkers for Alzheimer’s disease: from Alzheimer’s disease neuroimaging initiative (ADNI) database. Neural Regeneration Research, 13(6), 962-970. doi: http://dx.doi.org/10.4103/1673-5374.233433
Dimitriadis, S. I., Liparas, D., Tsolaki, M. N., & Initia, A. D. N. (2018). Random forest feature selection, fusion and ensemble strategy: Combining multiple morphological MRI measures to discriminate among healhy elderly, MCI, cMCI and alzheimer’s disease patients: From the alzheimer’s disease neuroimaging initiative (ADNI) database. Journal of Neuroscience Methods, 302, 14-23. doi: http://dx.doi.org/10.1016/j.jneumeth.2017.12.010
Doan, N. T., Engvig, A., Zaske, K., Persson, K., Lund, M. J., Kaufmann, T., . . . Initi, A. s. D. N. (2017). Distinguishing early and late brain aging from the Alzheimer’s disease spectrum: consistent morphological patterns across independent samples. Neuroimage, 158, 282-295. doi: http://dx.doi.org/10.1016/j.neuroimage.2017.06.070
Fischl, B. (2012). FreeSurfer. Neuroimage, 62(2), 774-781. doi: http://dx.doi.org/10.1016/j.neuroimage.2012.01.021
Hall, M. A., & Smith, L. A. (1998). Feature subset selection: A correlation based filter approach. Progress in Connectionist-Based Information Systems, Vols 1 and 2, 855-858.
Lama, R. K., Gwak, J., Park, J. S., & Lee, S. W. (2017). Diagnosis of Alzheimer’s Disease Based on Structural MRI Images Using a Regularized Extreme Learning Machine and PCA Features. Journal of Healthcare Engineering. doi: http://dx.doi.org/10.1155/2017/5485080
Moradi, E., Pepe, A., Gaser, C., Huttunen, H., Tohka, J., & Initi, A. s. D. N. (2015). Machine learning framework for early MRI-based Alzheimer’s conversion prediction in MCI subjects. Neuroimage, 104, 398-412. doi: http://dx.doi.org/10.1016/j.neuroimage.2014.10.002
Murphy, K. P. (2001). Active learning of causal Bayes net structure.
Okyay, S., & Adar, N. (2018). Parallel 3D brain modeling & feature extraction: ADNI dataset case study. Paper presented at the 2018 14th International Conference on Advanced Trends in Radioelecrtronics, Telecommunications and Computer Engineering (TCSET), Lviv-Slavske, Ukraine. doi: http://dx.doi.org/10.1109/TCSET.2018.8336172
Patil, T., & Sherekar, S. (2013). Performance Analysis of Naive Bayes and J48 Classification Algorithm for Data Classification. International Journal Of Computer Science And Applications, ISSN: 0974, 1011.
Ramirez, J., Gorriz, J. M., Ortiz, A., Martinez-Murcia, F. J., Segovia, F., Salas-Gonzalez, D., . . . Initia, A. D. N. (2018). Ensemble of random forests One vs. Rest classifiers for MCI and AD prediction using ANOVA cortical and subcortical feature selection and partial least squares. Journal of Neuroscience Methods, 302, 47-57. doi: http://dx.doi.org/10.1016/j.jneumeth.2017.12.005
Reuter, M., Schmansky, N. J., Rosas, H. D., & Fischl, B. (2012). Within-subject template estimation for unbiased longitudinal image analysis. Neuroimage, 61(4), 1402-1418. doi: http://dx.doi.org/10.1016/j.neuroimage.2012.02.084
Rish, I. (2001). An empirical study of the naive Bayes classifier. Paper presented at the IJCAI 2001 workshop on empirical methods in artificial intelligence.
Sharma, A. K., & Sahni, S. (2011). A comparative study of classification algorithms for spam email data analysis. International Journal on Computer Science and Engineering, 3(5), 1890-1895.
Sorensen, L., Igel, C., Pai, A., Balas, I., Anker, C., Lillholm, M., . . . Init, A. s. D. N. (2017). Differential diagnosis of mild cognitive impairment and Alzheimer’s disease using structural MRI cortical thickness, hippocampal shape, hippocampal texture, and volumetry. Neuroimage-Clinical, 13, 470-482. doi: http://dx.doi.org/10.1016/j.nicl.2016.11.025
Web, U. (2017). Access Data and Samples. Retrieved from http://adni.loni.usc.edu/data-samples/access-data/ [Access Date: Jan 9, 2020]
Yao, D. R., Calhoun, V. D., Fu, Z. N., Du, Y. H., & Sui, J. (2018). An ensemble learning system for a 4-way classification of Alzheimer’s disease and mild cognitive impairment. Journal of Neuroscience Methods, 302, 75-81. doi: http://dx.doi.org/10.1016/j.jneumeth.2018.03.008