Automated hemangioma detection using Otsu based binarized Kaze features

Abstract

This study aims to detect liver hemangioma on CT images by using hybrid image processing methods as well as binarized histogram of gradients based Kaze feature extraction. Using hybrid strategies, automatic hemangioma detector design is the state of art of this study. Our study helps doctors to detect the solid liver masses. Proposed algorithm includes detection of hemangioma using Otsu auto-threshold based Histogram of Gradients (HOG) and Kaze feature extraction implementation. 48 liver CT images, 28 of which are hemangiomas and 20 of which are healthy liver images, are used as the dataset. CT images are obtained by the Department of the Radiology at Fırat University. Presented work was implemented to 48-CT images and 91,66% accuracy was achieved for different shaped and sized hemangiomas. These results show that the developed algorithm could ease the process of detecting liver masses for radiologist and doctors could evaluate their findings easily.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

References

  1. 1.

    Abanovie E, Stankevieius G, Matuzevieius D (2018) Deep neural network-based feature descriptor for retinal image registration. In: 2018 IEEE 6th workshop on advances in information, Electronic and Electrical Engineering (AIEEE). IEEE, pp 1–4

  2. 2.

    Acharya UR, Koh JEW, Hagiwara Y, Tan JH, Gertych A, Vijayananthan A, Yaakup NA, Abdullah BJJ, Bin Mohd Fabell MK, Yeong CH (2018) Automated diagnosis of focal liver lesions using bidirectional empirical mode decomposition features. Comput Biol Med 94:11–18. https://doi.org/10.1016/J.COMPBIOMED.2017.12.024

    Article  Google Scholar 

  3. 3.

    Alcantarilla PF, Bartoli A, Davison AJ (2012) KAZE features. Springer, Berlin, Heidelberg, pp 214–227

    Google Scholar 

  4. 4.

    Bahirwani R, Reddy KR (2008) Review article: the evaluation of solitary liver masses. Aliment Pharmacol Ther 28:953–965. https://doi.org/10.1111/j.1365-2036.2008.03805.x

    Article  Google Scholar 

  5. 5.

    Balbin JR, Garcia RG, Fernandez KED, et al (2018) Crowd counting system by facial recognition using histogram of oriented gradients, completed local binary pattern, gray-level co-occurrence matrix and unmanned aerial vehicle. In: Jiang X, Chen G, Chen Z (eds), Third international workshop on pattern recognition. SPIE, p 58

  6. 6.

    Chan Y-K, Chang M-J, Hung Y-W, Wang CL, Hong CF, Tung KC, Yu SS (2018) Tissue section image-based liver scar detection. J Med Biol Eng 38:857–866. https://doi.org/10.1007/s40846-017-0352-z

    Article  Google Scholar 

  7. 7.

    D’Onofrio M, Crosara S, De Robertis R et al (2015) Contrast-enhanced ultrasound of focal liver lesions. Am J Roentgenol 205:W56–W66. https://doi.org/10.2214/AJR.14.14203

    Article  Google Scholar 

  8. 8.

    Dalal N, Triggs B (2005) Histograms of Oriented Gradients for Human Detection. In: 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05). IEEE, pp 886–893

  9. 9.

    Fan DP, Zhang S, Wu YH, et al (2019) Scoot: a perceptual metric for facial sketches. In: Proceedings of the IEEE International Conference on Computer Vision. Institute of Electrical and Electronics Engineers Inc., pp 5611–5621

  10. 10.

    Firuzi K, Vakilian M, Phung BT, Blackburn TR (2019) Partial discharges pattern recognition of transformer defect model by LBP & HOG features. IEEE Trans Power Deliv 34:542–550. https://doi.org/10.1109/TPWRD.2018.2872820

    Article  Google Scholar 

  11. 11.

    Gandolfi L, Leo P, Solmi L, Vitelli E, Verros G, Colecchia A (1991) Natural history of hepatic haemangiomas: clinical and ultrasound study. Gut 32:677–680

    Article  Google Scholar 

  12. 12.

    Getzin T, Gueler F, Hartleben B, Gutberlet M, Thorenz A, Chen R, Meier M, Bräsen JH, Derlin T, Hartung D, Lang HAS, Haller H, Wacker F, Rong S, Hueper K (2018) Gd-EOB-DTPA-enhanced MRI for quantitative assessment of liver organ damage after partial hepatic ischaemia reperfusion injury: correlation with histology and serum biomarkers of liver cell injury. Eur Radiol 28:4455–4464. https://doi.org/10.1007/s00330-018-5380-8

    Article  Google Scholar 

  13. 13.

    Huang Z, Wang R, Shan S, van Gool L, Chen X (2018) Cross Euclidean-to-Riemannian metric learning with application to face recognition from video. IEEE Trans Pattern Anal Mach Intell 40:2827–2840. https://doi.org/10.1109/TPAMI.2017.2776154

    Article  Google Scholar 

  14. 14.

    Jain N, Kumar V (2016) IFCM based segmentation method for liver ultrasound images. J Med Syst 40:249. https://doi.org/10.1007/s10916-016-0623-1

    Article  Google Scholar 

  15. 15.

    Koc M, Serhatlioglu S (2017) The investigation of incidence and radiological findings of gastrointestinal stromal tumor as a rare cause of abdominal mass. J Turgut Ozal Med Cent 24(3):301–304. https://doi.org/10.5455/jtomc.2017.04.058

    Article  Google Scholar 

  16. 16.

    Lee W-L (2013) An ensemble-based data fusion approach for characterizing ultrasonic liver tissue. Appl Soft Comput 13:3683–3692. https://doi.org/10.1016/J.ASOC.2013.03.009

    Article  Google Scholar 

  17. 17.

    Lee KL, Mokji MM (2014) Automatic target detection in GPR images using histogram of oriented gradients (HOG). In: 2014 2nd international conference on electronic design (ICED). IEEE, pp 181–186

  18. 18.

    Li J, Yang Y (2019) Clinical study of diffusion-weighted imaging in the diagnosis of liver focal lesion. J Med Syst 43:43. https://doi.org/10.1007/s10916-019-1164-1

    Article  Google Scholar 

  19. 19.

    Li X, Wen M, Su L et al (2018) Local suture ligation-assisted percutaneous sclerotherapy for Kasabach-Merritt phenomenon-associated kaposiform haemangioendothelioma. Oncol Lett 17:981–989. https://doi.org/10.3892/ol.2018.9661

    Article  Google Scholar 

  20. 20.

    Liu L, Fieguth P, Guo Y, Wang X, Pietikäinen M (2017) Local binary features for texture classification: taxonomy and experimental study. Pattern Recogn 62:135–160. https://doi.org/10.1016/J.PATCOG.2016.08.032

    Article  Google Scholar 

  21. 21.

    Liu Y, Cheng M-M, Fan D-P, et al (2018) Semantic edge detection with diverse deep supervision

  22. 22.

    Mehta N, Liu K, Alibhai AY, Gendelman I, Braun PX, Ishibazawa A, Sorour O, Duker JS, Waheed NK (2019) Impact of Binarization Thresholding and brightness/contrast adjustment methodology on optical coherence tomography angiography image quantification. Am J Ophthalmol 205:54–65. https://doi.org/10.1016/J.AJO.2019.03.008

    Article  Google Scholar 

  23. 23.

    Navale P, Habib M, Stueck A, Fiel MI (2018) Hepatic Sclerosing Hemangioma simulating gallbladder carcinoma: a rare case. J Clin Exp Hepatol 8:474–477. https://doi.org/10.1016/j.jceh.2018.07.003

    Article  Google Scholar 

  24. 24.

    Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9:62–66. https://doi.org/10.1109/TSMC.1979.4310076

    Article  Google Scholar 

  25. 25.

    Pournik O, Alavian SM, Ghalichi L, Seifizarei B, Mehrnoush L, Aslani A, Anjarani S, Eslami S (2014) Inter-observer and intra-observer agreement in pathological evaluation of non-alcoholic fatty liver disease suspected liver biopsies. Hepat Mon 14:e15167. https://doi.org/10.5812/hepatmon.15167

    Article  Google Scholar 

  26. 26.

    Sanchez-Morillo D, González J, García-Rojo M, Ortega J (2018) Classification of breast Cancer Histopathological images using KAZE features. Springer, Cham, pp 276–286

    Google Scholar 

  27. 27.

    Siegel RL, Miller KD, Jemal A (2017) Cancer statistics, 2017. CA Cancer J Clin 67:7–30. https://doi.org/10.3322/caac.21387

    Article  Google Scholar 

  28. 28.

    Su T-Y, Yang W-T, Cheng T-C, et al (2019) Computer-aided liver cirrhosis diagnosis via automatic liver segmentation and machine learning algorithm. In: Fujita H, Lin F, Kim JH (eds), International forum on medical imaging in Asia 2019. SPIE, p 54

  29. 29.

    Sugo H, Sekine Y, Miyano S, Watanobe I, Machida M, Kojima K, Okubo H, Ura A, Ogura K, Matsumoto T (2018) Hepatic Sclerosing Hemangioma with predominance of the Sclerosed area mimicking a biliary Cystadenocarcinoma. Case Rep Hepatol 2018:1–6. https://doi.org/10.1155/2018/7353170

    Article  Google Scholar 

  30. 30.

    Tait N, Richardson AJ, Muguti G, Little JM (1992) Hepatic cavernous haemangioma: a 10 year review. Aust N Z J Surg 62:521–524

    Article  Google Scholar 

  31. 31.

    Virmani J, Kumar V, Kalra N, Khandelwal N (2014) Neural network ensemble based CAD system for focal liver lesions from B-mode ultrasound. J Digit Imaging 27:520–537. https://doi.org/10.1007/s10278-014-9685-0

    Article  Google Scholar 

  32. 32.

    Wang X, Wang J, Yang F, Zeng G (2018) Target detection in colorful imaging sonar based on HOG. In: 2018 IEEE international conference on signal processing, Communications and Computing (ICSPCC). IEEE, pp 1–5

  33. 33.

    Wu H, Liang Y, Jiang X, Wei X, Liu Y, Liu W, Guo Y, Tang W (2018) Meta-analysis of intravoxel incoherent motion magnetic resonance imaging in differentiating focal lesions of the liver. Medicine (Baltimore) 97:e12071. https://doi.org/10.1097/MD.0000000000012071

    Article  Google Scholar 

  34. 34.

    Xu Q, Li M, Li M, Liu S (2018) Energy Spectrum CT image detection based dimensionality reduction with phase congruency. J Med Syst 42:49. https://doi.org/10.1007/s10916-018-0904-y

    Article  Google Scholar 

  35. 35.

    Yuan XC, Wu LS, Peng Q (2015) An improved Otsu method using the weighted object variance for defect detection. Appl Surf Sci 349:472–484. https://doi.org/10.1016/j.apsusc.2015.05.033

    Article  Google Scholar 

  36. 36.

    Zhu H, Zhuang Z, Zhou J, Zhang F, Wang X, Wu Y (2017) Segmentation of liver cyst in ultrasound image based on adaptive threshold algorithm and particle swarm optimization. Multimed Tools Appl 76:8951–8968. https://doi.org/10.1007/s11042-016-3486-z

    Article  Google Scholar 

Download references

Acknowledgements

This computer based study was performed at Gazi University, Engineering Faculty, Electrical & Electronics Engineering Department. I would also like to thank to Prof. Dr. Selami SERHATLIOĞLU and Asst. Prof. Dr. Mustafa KOÇ for sharing CT images without personal data and contributing their valuable comments.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Uğurhan Kutbay.

Ethics declarations

Conflict of interest

The author declares that he have no conflicts of interests.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Kutbay, U. Automated hemangioma detection using Otsu based binarized Kaze features. Multimed Tools Appl (2020). https://doi.org/10.1007/s11042-020-09156-2

Download citation

Keywords

  • Hemangioma
  • CT
  • Otsu
  • Histogram of gradients
  • Kaze features
  • Diagnosis system
  • Biomedical image processing