2D and 3D texture analysis to differentiate brain metastases on MR images: proceed with caution
To find structural differences between brain metastases of lung and breast cancer, computing their heterogeneity parameters by means of both 2D and 3D texture analysis (TA).
Materials and methods
Patients with 58 brain metastases from breast (26) and lung cancer (32) were examined by MR imaging. Brain lesions were manually delineated by 2D ROIs on the slices of contrast-enhanced T1-weighted (CET1) images, and local binary patterns (LBP) maps were created from each region. Histogram-based (minimum, maximum, mean, standard deviation, and variance), and co-occurrence matrix-based (contrast, correlation, energy, entropy, and homogeneity) 2D, weighted average of the 2D slices, and true 3D TA were obtained on the CET1 images and LBP maps.
For LBP maps and 2D TA contrast, correlation, energy, and homogeneity were identified as statistically different heterogeneity parameters (SDHPs) between lung and breast metastasis. The weighted 3D TA identified entropy as an additional SDHP. Only two texture indexes (TI) were significantly different with true 3D TA: entropy and energy. All these TIs discriminated between the two tumor types significantly by ROC analysis. For the CET1 images there was no SDHP at all by 3D TA.
Our results indicate that the used textural analysis methods may help with discriminating between brain metastases of different primary tumors.
KeywordsComputer-assisted Image processing Texture analysis Magnetic resonance imaging Brain neoplasms Metastasis Breast cancer Lung cancer
This work was supported in part by the Spanish Ministerio de Economía y Competitividad (MINECO) and FEDER funds under Grant BFU2015-64380-C2-2-R, by the “Richter Gedeon Talentum Alapítvány” and by the Campus Hungary Mobility Program. Andrés Larroza was funded by the Spanish Ministerio de Educación, Cultura y Deporte (MECD) under Grant FPU12/01140. The authors also thank to the continuous help of Dr. Joaquin Gavila from Fundación IVO.
Protocol/project development: David Moratal, Estanislao Arana, Monika Béresová. Data collection or management: David Moratal, Estanislao Arana, László Balkay. Andrés Larroza, Monika Béresová. Data analysis: David Moratal, Estanislao Arana, Balkay László, József Varga, Monika Béresová.
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.
All exams came from individuals who gave informed consent at admission for research and follow-up, in accordance with Institutional Board Review (IBR) approval.
- 4.Kumar V, Abbas AK, Aster JC (2014) Robbins and cotran pathologic basis of disease, 9th edn. Elsevier, PhiladelphiaGoogle Scholar
- 26.Suoranta S, Holli-Helenius K, Koskenkorva P, Niskanen E, Könönen M, Äikiä M, Eskola H, Kälviäinen R, Vanninen R (2013) 3D Texture analysis reveals imperceptible MRI textural alterations in the thalamus and putamen in progressive myoclonic epilepsy type 1, EPM1. PLoS One. doi: 10.1371/journal.pone.0069905 PubMedPubMedCentralGoogle Scholar
- 27.Allin Christe S, Vasantha Kumari B, Kandaswamy A (2012) Experimental study for 3D statistical property based intracranial brain tumor classification. J Sci Ind Res 71(1):36–44Google Scholar
- 30.Ben Sassi O, Sellami L, Ben Slima M, Chtourou K, Ben Hamida A (2013) Improved spatial gray level dependence matrices for texture analysis. Int J Comput Sci Inf Technol 4(6):209Google Scholar
- 31.Carl P, Daniel L (2008) Matlab function—cooc3d.m, available at https://www.mathworks.com/matlabcentral/fileexchange/19058-cooc3d
- 33.Wibmer A, Hricak H, Gondo T, Matsumoto K, Veeraraghavan H, Fehr D, Zheng J, Goldman D, Moskowitz C, Fine SW, Reuter VE, Eastham J, Sala E, Vargas HA (2015) Haralick texture analysis of prostate MRI: utility for differentiating non-cancerous prostate from prostate cancer and differentiating prostate cancers with different Gleason scores. Eur Radiol 25(10):2840–2850CrossRefPubMedPubMedCentralGoogle Scholar
- 36.Sikio M, Holli-Helenius KK, Ryymin P, Dastida P, Eskola H, Harrison L (2015) The effect of region of interest size on textural parameters: 9th International Symposium on Image and Signal Processing and Analysis (2015) IEEE, pp:149–153Google Scholar