Scientific article

Classification of magnetic resonance images from rabbit renal perfusion

Published inChemometrics and intelligent laboratory systems, vol. 98, no. 2, p. 173-181
Publication date2009-10-15

The feasibility of using chemometric techniques for the automatic detection of whether a rabbit kidney is pathological or not is studied. Sequential images of the kidney are acquired using Dynamic Contrast-Enhanced Magnetic Resonance Imaging with contrast agent injection. A segmentation approach based upon principal component analysis (PCA) is used to separate out the cortex from the rest of the kidney including the medulla, the renal pelvic, and the background. Two classifiers (Soft Independent Method of Class Analogy, SIMCA; Partial Least Squares Discriminant Analysis, PLS-DA) are tested for various types of data pre-treatment including segmentation, feature extraction, centering, autoscaling, standard normal variate transformation, Savitsky-Golay smoothing, and normalization. It is shown that (i) the renal cortex contains more discriminating information on kidney perfusion changes than the whole kidney, and (ii) the PLS-DA classifiers outperform the SIMCA classifiers. PLS-DA, preceded by an automated PCA-based segmentation of kidney anatomical regions, correctly classified all kidneys and constitutes a classification tool of the renal function that can be useful for the clinical diagnosis of renovascular diseases.

  • Kidney
  • Contrast-enhanced MRI
  • Renal perfusion
  • PCA
  • Segmentation
Citation (ISO format)
GUJRAL, Paman et al. Classification of magnetic resonance images from rabbit renal perfusion. In: Chemometrics and intelligent laboratory systems, 2009, vol. 98, n° 2, p. 173–181. doi: 10.1016/j.chemolab.2009.06.004
Main files (1)
Article (Published version)
ISSN of the journal0169-7439

Technical informations

Creation11/29/2022 9:25:59 AM
First validation05/03/2023 8:54:36 AM
Update time05/03/2023 8:54:36 AM
Status update05/03/2023 8:54:36 AM
Last indexation05/06/2024 3:48:10 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack