A Statistical Framework for Brain MRI Diagnostic Classification and Evaluation in Medical Image Processing

The proposed work introduces the statistical framework of quantitative analysis and image processing methods for detecting structural brain changes and classifying the severity of dementia cases using cross-sectional database. From cases, only individuals were included in a filtered analysis sample. Patients were divided into two groups according to CDR score. Cognitively Normal ( ) and Demented ( ). Continuous variables were tested for normal distribution using the Anderson-Darling test, followed by parametric (two-sample t-test) and non-parametric (Mann-Whitney U test) comparison between the groups. Further, a multivariable binary logistic regression model was developed based on structural MRI biomarkers of brain volume changes. Normalised Whole Brain Volume ( ), Estimated Total Intracranial Volume ( ), and Atlas Scaling Factor ( ) were investigated. Other continuous covariates such as score and and a dichotomous gender covariate were created. Empirical results showed that score ( , ) and ( ) were independent, statistically significant covariates associated with dementia risk. Therefore, progressive cerebral atrophy and cognitive dysfunction are the main predictors of impairment. Other covariates ( , , ) turned out to be non-significant in the multivariable model, since their influence is incorporated in structural brain volume changes and cognitive function test scores. The constructed logistic regression model had good performance in terms of calibration and fit ( , Hosmer-Lemeshow ). Evaluation of model classification performance revealed high accuracy of prediction of dementia presence with Area Under the ROC Curve ( ) of ( CI: ]) and concordance index of . Overall, a combination of quantitative biomarkers and standard cognitive tests provides an efficient diagnostic framework for making clinical decisions in Alzheimer’s disease and other forms of dementia.

I. Altman, D. G. (1990). Practical statistics for medical research. CRC Press.
II. Barnett, A. S., Irfanoglu, M. O., Landman, B., Rogers, B., & Pierpaoli, C. (2021). Mapping gradient nonlinearity and miscalibration using diffusion‐weighted MR images of a uniform isotropic phantom. Magnetic Resonance in Medicine, 86(6), 3259–3273.
III. Bethea, R. M. (1995). Statistical methods for engineers and scientists (Vol. 144). CRC Press.
IV. Buckner, R. L., Head, D., Parker, J., Fotenos, A. F., Marcus, D., Morris, J. C., & Snyder, A. Z. (2004). A unified approach for morphometric and functional data analysis in young, old, and demented adults using automated atlas-based head size normalisation: reliability and validation against manual measurement of total intracranial volume. Neuroimage, 23(2), 724–738.
V. Cohen, J. (1988). Statistical Power Analysis for the Behavioral Sciences. 2nd edn Lawrence Erlbaum: Hillsdale. NJ.
VI. Cuingnet, R., Gerardin, E., Tessieras, J., Auzias, G., Lehéricy, S., Habert, M.-O., Chupin, M., Benali, H., Colliot, O., & Initiative, A. D. N. (2011). Automatic classification of patients with Alzheimer’s disease from structural MRI: a comparison of ten methods using the ADNI database. Neuroimage, 56(2), 766–781.
VII. Fawcett, T. (2006). An introduction to ROC analysis. Pattern Recognition Letters, 27(8), 861–874.
VIII. Fischl, B. (2012). FreeSurfer. Neuroimage, 62(2), 774–781.
IX. Folstein, M. F., Folstein, S. E., & McHugh, P. R. (1975). “Mini-mental state”: a practical method for grading the cognitive state of patients for the clinician. Journal of Psychiatric Research, 12(3), 189–198.
X. Hastie, T., Tibshirani, R., Friedman, J. H., & Friedman, J. H. (2009). The elements of statistical learning: data mining, inference, and prediction (Vol. 2). Springer.
XI. Hosmer, D. W., Lemeshow, S., & Sturdivant, R. X. (2000). Applied logistic regression (Vol. 2). wiley New York.
XII. Klöppel, S., Stonnington, C. M., Chu, C., Draganski, B., Scahill, R. I., Rohrer, J. D., Fox, N. C., Jack Jr, C. R., Ashburner, J., & Frackowiak, R. S. J. (2008). Automatic classification of MR scans in Alzheimer’s disease. Brain, 131(3), 681–689.
XIII. Little, R. J. A., & Rubin, D. B. (2019). Statistical analysis with missing data. John Wiley & Sons.
XIV. Marcus, D. S., Wang, T. H., Parker, J., Csernansky, J. G., Morris, J. C., & Buckner, R. L. (2007). Open Access Series of Imaging Studies (OASIS): cross-sectional MRI data in young, middle aged, nondemented, and demented older adults. Journal of Cognitive Neuroscience, 19(9), 1498–1507.
XV. Mathews, P. G. (2004). Design of Experiments with MINITAB. Quality press.
XVI. Montgomery, D. C., Runger, G. C., & Hubele, N. F. (2007). Engineering statistics. John Wiley & Sons. Inc: Hoboken, NJ, USA.
XVII. Morris, J. C. (1993). The Clinical Dementia Rating (CDR) current version and scoring rules. Neurology, 43(11), 2412.
XVIII. Navidi, W. C. (2008). Statistics for engineers and scientists (Vol. 20). McGraw-Hill Higher Education New York.
XIX. Risan, H. K., Al-Azzawi, A. A., & Al-Zwainy, F. M. S. (2024). Statistical Analysis for Civil Engineers. Elsevier.
XX. Sled, J. G., Zijdenbos, A. P., & Evans, A. C. (1998). A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Transactions on Medical Imaging, 17(1), 87–97.
XXI. Stephens, M. A. (1974). EDF statistics for goodness of fit and some comparisons. Journal of the American Statistical Association, 69(347), 730–737.
XXII. Suk, H.-I., Lee, S.-W., Shen, D., & Initiative, A. D. N. (2014). Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis. NeuroImage, 101, 569–582.

"An Interdisciplinary Peer Reviewed Quaterly Published International Journal"

A Statistical Framework for Brain MRI Diagnostic Classification and Evaluation in Medical Image Processing

Authors:

DOI:

Abstract:

Keywords:

Refference: