Discriminant Analysis of Intracranial Volumetric Variables in Patients with Normal Pressure Hydrocephalus and Brain Atrophy
A method was developed for the computerized volumetric assessment of the intracranial cerebrospinal fluid (CSF) distribution. The study involved 62 patients differentiated into two groups: with CSF resorption disorders (normal pressure hydrocephalus – 30 patients) and without CSF resorption disorders (various types of brain atrophy – 32 patients). The goal of the study was to ascertain whether the assessment, depending on the linear discriminant analysis of volumetric brain features, could be an effective tool differentiating the two groups. Volumetric measurements were performed using VisNow software. For each patient, five features were determined and subjected to discriminant analysis: CSF volume in the subarachnoid space and basal cisterns (SV), CSF volume in the intracranial ventricular system (VV), brain volume (BV), total intracranial CSF volume (FV), and total intracranial volume (TV). Discriminant analysis enables the achievement of a high percentage of correct classification of patients to the appropriate group determined on the result of a lumbar infusion test. The discriminator, based on three features: BV, SV, and VV, showed a complete separation of the groups; irrespective of age. The squared Mahalanobis distance was 70.8. The results confirmed the applicability of the volumetric method. Discriminant analysis seems a useful tool leading to the acquisition of a computer-aided method for the differential diagnosis of CSF resorption disorders.
KeywordsComputer-aided diagnosis CSF resorption disorders Linear discriminant analysis Normal pressure hydrocephalus Normotensive hydrocephalus Volumetric assessment
Support in part by grant POIG.02.03.00-00-003/09 from the National Center for Research and Development in Poland.
Conflicts of Interest
The authors declare no competing interests in relation to this article.
- Anderson TW (1958) Introduction to multivariate statistical analysis. Wiley Publication in mathematical statistics. Wiley, New YorkGoogle Scholar
- Boon AJ, Tans JT, Delwel EJ, Egeler-Peerdeman SM, Hanlo PW, Wurzer HA, Avezaat CJ, de Jong DA, Gooskens RH, Hermans J (1997) Dutch normal-pressure hydrocephalus study: prediction of outcome after shunting by resistance to outflow of cerebrospinal fluid. J Neurosurg 87(5):687–693CrossRefPubMedGoogle Scholar
- Devijver PA, Kittler J (1980) Pattern recognition: a statistical approach. A very clear presentation of the mathematical foundations. Prentice-Hall International, Englewood Cliffs, New YorkGoogle Scholar
- Duda OR, Hart PE, Stork DG (1973) Pattern classification, 2nd edn. Wiley, New YorkGoogle Scholar
- Jóźwik A (1994) Pattern recognition method based on k-nearest neighbour rule. J Commun 45:27–29Google Scholar
- Jurkiewicz J, Costabile G, Czernicki Z, Hess K, Probst C (1991) Usefulness of somatosensory evoked potentials in the diagnosis of low-pressure hydrocephalus. J Neurol Neurosurg 5:559–566Google Scholar
- Mahalanobis PC (1936) On the generalised distance in statistics. Proc Nat Instit Sci India 2(1):49–55Google Scholar
- Marszałek P, Jurkiewicz J, Fersten E, Łuczywek E, Czernicki Z, Gielecki J, Bogucki J (1997) Multi-stage method for the diagnosis of low-pressure hydrocephalus. J Neurol Neurosurg 31(3):527–539Google Scholar
- Serulle Y, Rusinek H, Kirov II, Milch H, Fieremans E, Baxter AB, McMenamy J, Jain R, Wisoff J, Golomb J, Gonen O, George AE (2014) Differentiating shunt-responsive normal pressure hydrocephalus from Alzheimer disease and normal aging: pilot study using automated MRI brain tissue segmentation. J Neurol 261(10):1994–2002CrossRefPubMedGoogle Scholar
- Szczepek E, Czerwosz L, Nowiński K, Jurkiewicz J, Czernicki Z (2015) Evaluation of volumetric changes in differential diagnosis of brain atrophy and active hydrocephalus. Adv Exp Med Biol 9:59–67Google Scholar
- VisNow (2011) Visualization software developed at Laboratory of Visual Analysis at Interdisciplinary Centre of Mathematical and Computational Modelling. https://www.visnow.icm.edu.pl. Accessed on 18 Dec 2016