HaraliCU: GPU-Powered Haralick Feature Extraction on Medical Images Exploiting the Full Dynamics of Gray-Scale Levels

  • Leonardo Rundo
  • Andrea Tangherloni
  • Simone Galimberti
  • Paolo Cazzaniga
  • Ramona Woitek
  • Evis Sala
  • Marco S. Nobile
  • Giancarlo MauriEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11657)


Image texture extraction and analysis are fundamental steps in Computer Vision. In particular, considering the biomedical field, quantitative imaging methods are increasingly gaining importance since they convey scientifically and clinically relevant information for prediction, prognosis, and treatment response assessment. In this context, radiomic approaches are fostering large-scale studies that can have a significant impact in the clinical practice. In this work, we focus on Haralick features, the most common and clinically relevant descriptors. These features are based on the Gray-Level Co-occurrence Matrix (GLCM), whose computation is considerably intensive on images characterized by a high bit-depth (e.g., 16 bits), as in the case of medical images that convey detailed visual information. We propose here HaraliCU, an efficient strategy for the computation of the GLCM and the extraction of an exhaustive set of the Haralick features. HaraliCU was conceived to exploit the parallel computation capabilities of modern Graphics Processing Units (GPUs), allowing us to achieve up to \(\sim \!20\times \) speed-up with respect to the corresponding C++ coded sequential version. Our GPU-powered solution highlights the promising capabilities of GPUs in the clinical research.


Haralick features GPU computing Full gray-scale range Medical imaging Radiomics CUDA 



This work was partially supported by The Mark Foundation for Cancer Research and Cancer Research UK Cambridge Centre [C9685/A25177]. Additional support has been provided by the National Institute of Health Research (NIHR) Cambridge Biomedical Research Centre. The views expressed are those of the authors and not necessarily those of the NHS, the NIHR or the Department of Health and Social Care.


  1. 1.
    Trivedi, M.M., Harlow, C.A., Conners, R.W., Goh, S.: Object detection based on gray level cooccurrence. Comput. Vis. Graph. Image Process. 28(2), 199–219 (1984)CrossRefGoogle Scholar
  2. 2.
    Soh, L.K., Tsatsoulis, C.: Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices. IEEE Trans. Geosci. Remote Sens. 37(2), 780–795 (1999)CrossRefGoogle Scholar
  3. 3.
    Torheim, T., et al.: Classification of dynamic contrast enhanced MR images of cervical cancers using texture analysis and support vector machines. IEEE Trans. Med. Imaging 33(8), 1648–1656 (2014)CrossRefGoogle Scholar
  4. 4.
    Yankeelov, T.E., et al.: Quantitative imaging in cancer clinical trials. Clin. Cancer Res. 22(2), 284–290 (2016)CrossRefGoogle Scholar
  5. 5.
    Lambin, P., et al.: Radiomics: extracting more information from medical images using advanced feature analysis. Eur. J. Cancer 48(4), 441–446 (2012)CrossRefGoogle Scholar
  6. 6.
    Lambin, P., et al.: Radiomics: the bridge between medical imaging and personalized medicine. Nat. Rev. Clin. Oncol. 14(12), 749 (2017)CrossRefGoogle Scholar
  7. 7.
    Yip, S.S., Aerts, H.J.: Applications and limitations of radiomics. Phys. Med. Biol. 61(13), R150 (2016)CrossRefGoogle Scholar
  8. 8.
    Stoyanova, R., et al.: Prostate cancer radiomics and the promise of radiogenomics. Transl. Cancer Res. 5(4), 432 (2016)CrossRefGoogle Scholar
  9. 9.
    Chen, C.C., DaPonte, J.S., Fox, M.D.: Fractal feature analysis and classification in medical imaging. IEEE Trans. Med. Imaging 8(2), 133–142 (1989)CrossRefGoogle Scholar
  10. 10.
    Galloway, M.M.: Texture analysis using gray level run lengths. Comput. Graph. Image Process. 4(2), 172–179 (1975)CrossRefGoogle Scholar
  11. 11.
    Thibault, G., et al.: Shape and texture indexes application to cell nuclei classification. Int. J. Pattern Recognit. Artif. Intell. 27(01), 1357002 (2013)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Zhu, H., et al.: A new local multiscale Fourier analysis for medical imaging. Med. Phys. 30(6), 1134–1141 (2003)CrossRefGoogle Scholar
  13. 13.
    Arivazhagan, S., Ganesan, L.: Texture classification using wavelet transform. Pattern Recognit. Lett. 24(9–10), 1513–1521 (2003)zbMATHCrossRefGoogle Scholar
  14. 14.
    Haralick, R.M., Shanmugam, K., Dinstein, I.: Textural features for image classification. IEEE Trans. Syst. Man Cybern. SMC 3(6), 610–621 (1973)CrossRefGoogle Scholar
  15. 15.
    Haralick, R.M.: Statistical and structural approaches to texture. Proc. IEEE 67(5), 786–804 (1979)CrossRefGoogle Scholar
  16. 16.
    Brynolfsson, P., et al.: Haralick texture features from apparent diffusion coefficient (ADC) MRI images depend on imaging and pre-processing parameters. Sci. Rep. 7(1), 4041 (2017)CrossRefGoogle Scholar
  17. 17.
    Gómez, W., Pereira, W., Infantosi, A.F.C.: Analysis of co-occurrence texture statistics as a function of gray-level quantization for classifying breast ultrasound. IEEE Trans. Med. Imaging 31(10), 1889–1899 (2012)CrossRefGoogle Scholar
  18. 18.
    Ortiz, A., Górriz, J., Ramírez, J., Salas-Gonzalez, D., Llamas-Elvira, J.M.: Two fully-unsupervised methods for MR brain image segmentation using SOM-based strategies. Appl. Soft Comput. 13(5), 2668–2682 (2013)CrossRefGoogle Scholar
  19. 19.
    Park, S., Kim, B., Lee, J., Goo, J.M., Shin, Y.G.: GGO nodule volume-preserving nonrigid lung registration using GLCM texture analysis. IEEE Trans. Biomed. Eng. 58(10), 2885–2894 (2011)CrossRefGoogle Scholar
  20. 20.
    Rundo, L., et al.: MedGA: a novel evolutionary method for image enhancement in medical imaging systems. Expert Syst. Appl. 119, 387–399 (2019)CrossRefGoogle Scholar
  21. 21.
    Dercle, L., et al.: Limits of radiomic-based entropy as a surrogate of tumor heterogeneity: ROI-area, acquisition protocol and tissue site exert substantial influence. Sci. Rep. 7(1), 7952 (2017)CrossRefGoogle Scholar
  22. 22.
    Gipp, M., et al.: Haralick’s texture features computation accelerated by GPUs for biological applications. In: Bock, H., Hoang, X., Rannacher, R., Schlöder, J. (eds.) Modeling, Simulation and Optimization of Complex Processes, pp. 127–137. Springer, Heidelberg (2012). Scholar
  23. 23.
    Leijenaar, R.T., et al.: The effect of SUV discretization in quantitative FDG-PET radiomics: the need for standardized methodology in tumor texture analysis. Sci. Rep. 5, 11075 (2015)CrossRefGoogle Scholar
  24. 24.
    Orlhac, F., Soussan, M., Chouahnia, K., Martinod, E., Buvat, I.: 18F-FDG PET-derived textural indices reflect tissue-specific uptake pattern in non-small cell lung cancer. PLoS One 10(12), e0145063 (2015)CrossRefGoogle Scholar
  25. 25.
    Orlhac, F., Soussan, M., Maisonobe, J.A., Garcia, C.A., Vanderlinden, B., Buvat, I.: Tumor texture analysis in 18F-FDG PET: relationships between texture parameters, histogram indices, standardized uptake values, metabolic volumes, and total lesion glycolysis. J. Nucl. Med. 55(3), 414–422 (2014)CrossRefGoogle Scholar
  26. 26.
    Jen, C.C., Yu, S.S.: Automatic detection of abnormal mammograms in mammographic images. Expert Syst. Appl. 42(6), 3048–3055 (2015)CrossRefGoogle Scholar
  27. 27.
    Shafiq-ul Hassan, M., Latifi, K., Zhang, G., Ullah, G., Gillies, R., Moros, E.: Voxel size and gray level normalization of CT radiomic features in lung cancer. Sci. Rep. 8(1), 10545 (2018)CrossRefGoogle Scholar
  28. 28.
    Larue, R.T., et al.: Influence of gray level discretization on radiomic feature stability for different CT scanners, tube currents and slice thicknesses: a comprehensive phantom study. Acta Oncol. 56(11), 1544–1553 (2017)CrossRefGoogle Scholar
  29. 29.
    Luebke, D.: CUDA: scalable parallel programming for high-performance scientific computing. In: Proceedings 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro (ISBI), pp. 836–838. IEEE (2008)Google Scholar
  30. 30.
    Nobile, M.S., Cazzaniga, P., Tangherloni, A., Besozzi, D.: Graphics processing units in bioinformatics, computational biology and systems biology. Brief. Bioinform. 18(5), 870–885 (2016)Google Scholar
  31. 31.
    Eklund, A., Dufort, P., Forsberg, D., LaConte, S.M.: Medical image processing on the GPU-past, present and future. Med. Image Anal. 17(8), 1073–1094 (2013)CrossRefGoogle Scholar
  32. 32.
    Smistad, E., Falch, T.L., Bozorgi, M., Elster, A.C., Lindseth, F.: Medical image segmentation on GPUs-a comprehensive review. Med. Image Anal. 20(1), 1–18 (2015)CrossRefGoogle Scholar
  33. 33.
    Shen, D., Wu, G., Suk, H.I.: Deep learning in medical image analysis. Annu. Rev. Biomed. Eng. 19, 221–248 (2017)CrossRefGoogle Scholar
  34. 34.
    Tsai, H.Y., Zhang, H., Hung, C.L., Min, G.: GPU-accelerated features extraction from magnetic resonance images. IEEE Access 5, 22634–22646 (2017)CrossRefGoogle Scholar
  35. 35.
    Militello, C., et al.: Gamma Knife treatment planning: MR brain tumor segmentation and volume measurement based on unsupervised Fuzzy C-Means clustering. Int. J. Imaging Syst. Technol. 25(3), 213–225 (2015)CrossRefGoogle Scholar
  36. 36.
    Vargas, H.A., et al.: A novel representation of inter-site tumour heterogeneity from pre-treatment computed tomography textures classifies ovarian cancers by clinical outcome. Eur. Radiol. 27(9), 3991–4001 (2017)CrossRefGoogle Scholar
  37. 37.
    Rizzo, S., et al.: Radiomics of high-grade serous ovarian cancer: association between quantitative CT features, residual tumour and disease progression within 12 months. Eur. Radiol. 28, 4849–4859 (2018)CrossRefGoogle Scholar
  38. 38.
    Pinker, K., et al.: Background, current role, and potential applications of radiogenomics. J. Magn. Reson. Imaging 47(3), 604–620 (2018)CrossRefGoogle Scholar
  39. 39.
    Gupta, S., Xiang, P., Zhou, H.: Analyzing locality of memory references in GPU architectures. In: Proceedings ACM SIGPLAN Workshop on Memory Systems Performance and Correctness. ACM (2013). 12Google Scholar
  40. 40.
    Sala, E., et al.: Unravelling tumour heterogeneity using next-generation imaging: radiomics, radiogenomics, and habitat imaging. Clin. Radiol. 72(1), 3–10 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Leonardo Rundo
    • 1
    • 2
    • 3
  • Andrea Tangherloni
    • 3
    • 4
    • 5
    • 6
  • Simone Galimberti
    • 3
  • Paolo Cazzaniga
    • 7
    • 8
  • Ramona Woitek
    • 1
    • 2
    • 9
  • Evis Sala
    • 1
    • 2
  • Marco S. Nobile
    • 3
    • 8
  • Giancarlo Mauri
    • 3
    • 8
    Email author
  1. 1.Department of RadiologyUniversity of CambridgeCambridgeUK
  2. 2.Cancer Research UK Cambridge CentreCambridgeUK
  3. 3.Department of Informatics, Systems and CommunicationUniversity of Milano-BicoccaMilanItaly
  4. 4.Department of HaematologyUniversity of CambridgeCambridgeUK
  5. 5.Wellcome Trust Sanger InstituteHinxtonUK
  6. 6.Wellcome Trust – Medical Research Council Cambridge Stem Cell InstituteCambridgeUK
  7. 7.Department of Human and Social SciencesUniversity of BergamoBergamoItaly
  8. 8.SYSBIO.IT Centre of Systems BiologyMilanoItaly
  9. 9.Department of Biomedical Imaging and Image-guided TherapyMedical University ViennaViennaAustria

Personalised recommendations