Effects of MRI image normalization techniques in prostate cancer radiomics. (March 2020)

• Record Type: Journal Article
• Authors: Isaksson, Lars J.; Raimondi, Sara; Botta, Francesca; Pepa, Matteo; Gugliandolo, Simone G.; De Angelis, Simone P.; Marvaso, Giulia; Petralia, Giuseppe; De Cobelli, Ottavio; Gandini, Sara; Cremonesi, Marta; Cattani, Federica; Summers, Paul; Jereczek-Fossa, Barbara A.
• Is Part Of: Physica medica. Volume 71(2020)
• Page Start: 7
• Page End: 13
• Publication Date: 2020-03
• Subjects: Image normalization -- Prostate cancer -- MRI -- Radiomics; Medical physics -- Periodicals; Biophysics -- Periodicals; Biophysics -- Periodicals; Imagerie médicale -- Périodiques; Radiothérapie -- Périodiques; Rayons X -- Sécurité -- Mesures -- Périodiques; Physique -- Périodiques; Médecine -- Périodiques; 610.153
• DOI: 10.1016/j.ejmp.2020.02.007
• Languages: English
• ISSNs: 1120-1797

Abstract

Highlights: Normalizing images with respect to healthy prostate tissue is optimal. Histogram-based normalization should be used otherwise. Over 87% of radiomic features drastically change after normalization. Improper normalization is worse than no normalization. Abstract: The variance in intensities of MRI scans is a fundamental impediment for quantitative MRI analysis. Intensity values are not only highly dependent on acquisition parameters, but also on the subject and body region being scanned. This warrants the need for image normalization techniques to ensure that intensity values are consistent within tissues across different subjects and visits. Many intensity normalization methods have been developed and proven successful for the analysis of brain pathologies, but evaluation of these methods for images of the prostate region is lagging. In this paper, we compare four different normalization methods on 49 T2-w scans of prostate cancer patients: 1) the well-established histogram normalization, 2) the generalized scale normalization, 3) an extension of generalized scale normalization called generalized ball-scale normalization, and 4) a custom normalization based on healthy prostate tissue intensities. The methods are compared qualitatively and quantitatively in terms of behaviors of intensity distributions as well as impact on radiomic features. Our findings suggest that normalization based on prior knowledge of the healthy prostate tissue intensities may be the most effective way of acquiring the desired properties of normalized images. In addition, the histogram normalization method outperform the generalized scale and generalized ball-scale methods which have proven superior for other body regions.