Skip to main content

Advertisement

SpringerLink
Log in

Automated liver lesion detection in CT images based on multi-level geometric features

  • Original Article
  • Published:
International Journal of Computer Assisted Radiology and Surgery Aims and scope Submit manuscript

Abstract

Purpose

Due to the increasing number of liver cancer cases in clinical practice, there is a significant need for efficient tools for computer-assisted liver lesion analysis. A wide range of clinical applications, such as lesion characterization, quantification and follow-up, can be facilitated by automated liver lesion detection. Liver lesions vary significantly in size, shape, density and heterogeneity, which make them difficult to detect automatically. The goal of this work was to develop a method that can detect all types of liver lesions with high sensitivity and low false positive rate within a short run time.

Methods

The proposed method identifies abnormal regions in liver CT images based on their intensity using a multi-level segmentation approach. The abnormal regions are analyzed from the inside-out using basic geometric features (such as asymmetry, compactness or volume). Using this multi-level shape characterization, the abnormal regions are classified into lesions and other region types (including vessel, liver boundary). The proposed analysis also allows defining the contour of each finding. The method was trained on a set of 55 cases involving 120 lesions and evaluated on a set of 30 images involving 59 (various types of) lesions, which were manually contoured by a physician.

Results

The proposed algorithm demonstrated a high detection rate (92 %) at a low (1.7) false positive per case (precision 51 %), when the method was started from a manually contoured liver. The same level of false positive per case (1.6) and precision (51 %) was achieved at a somewhat lower detection rate (85 %), when the volume of interest was defined by a fully automated liver segmentation.

Conclusions

The proposed method can efficiently detect liver lesions irrespective of their size, shape, density and heterogeneity within half a minute. According to the evaluation, its accuracy is competitive with the actual state-of-the-art approaches, and the contour of the detected findings is acceptable in most of the cases. Future work shall focus on more precise lesion contouring so that the proposed method can be a solid basis for fully automated liver tumour burden estimation.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

References

  1. Doi K (2007) Computer-aided diagnosis in medical imaging: historical review, current status and future potential. Comput Med Imaging Graph 31(4–5):198–211

    Article  PubMed Central  PubMed  Google Scholar 

  2. van Leeuwen MS, Noordzij J, Feldberg MA, Hennipman AH, Doornewaard H (1996) Focal liver lesions: characterization with triphasic spiral CT. Radiology 201:327–336

    PubMed  Google Scholar 

  3. Corso JJ, Yuille A, Sicotte NL, Toga A (2007) Detection and segmentation of pathological structures by the extended graph-shifts algorithm. In: Medical image computing and computer-assisted intervention—MICCAI 2007, Lecturer Notes in Computer Science, vol 4791, pp 985–993

  4. Nie J, Xue Z, Liu T, Young GS, Setayesh K, Guo L, Wong STC (2009) Automated brain tumor segmentation using spatial accuracy-weighted hidden Markov random field. Comput Med Imaging Graph 33(6):431–441

    Article  PubMed Central  PubMed  Google Scholar 

  5. Kitasaka T, Tsujimura Y, Nakamura Y, Mori K, Suenaga Y, Ito M, Nawano S (2007) Automated extraction of lymph nodes from 3-d abdominal CT images using 3-d minimum directional difference filter. In: Medical image computing and computer-assisted intervention—MICCAI 2007, Lecturer Notes Computer Science, vol 4792, pp 336–343

  6. Bilello M, Gokturk SB, Desser T, Napel S, Jeffrey RB Jr, Beaulieu CF (2004) Automatic detection and classification of hypodense hepatic lesions on contrast-enhanced venous-phase CT. Med Phys 31(9):2584–2593

    Article  PubMed  Google Scholar 

  7. Duda D, Kretowsky M, Bezy-Wendling J (2006) Texture characterization for hepatic tumor recognition in multiphase CT. Biocybern Biomed Eng 26(4):15–24

    Google Scholar 

  8. Huang YL, Chen JH, Shen WC (2006) Diagnosis of hepatic tumors with texture analysis in nonenhanced computed tomography images. Acad Radiol 13(6):713–720

    Article  PubMed  Google Scholar 

  9. Mougiakakou SG, Valavanis IK, Nikita A, Nikita KS (2007) Differential diagnosis of CT focal liver lesions using texture features, feature selection and ensemble driven classifiers. Artif Intell Med 41(1):25–37

    Article  PubMed  Google Scholar 

  10. Tajima T, Zhang X, Kitagawa T, Kanematsu M, Zhou X, Hara T, Fujita H, Yokoyama R, Kondo H, Hoshi H, Nawano S, Shinozaki K (2007) Computer-aided detection (CAD) of hepatocellular carcinoma on multiphase CT images. Proc SPIE 6514:65142Q

    Article  Google Scholar 

  11. Kumar SS, Moni RS (2010) Diagnosis of liver tumor from CT images using fast discrete curvelet transform. Int J Comput Sci Eng 2(4):1173–1178

    Google Scholar 

  12. Safdari M, Pasari R, Rubin D, Greenspan H (2013) Image patch-based method for automated classification and detection of focal liver lesions on CT. In: Proceedings of SPIE 8670, medical imaging 2013: computer-aided diagnosis, 86700Y

  13. Quatrehomme A, Millet I, Hoa D, Subsol G, Puech W (2013) Assessing the classification of liver focal lesions by using multi-phase computer tomography scans. In: Greenspan H, Müller H, Syeda-Mahmood T (eds). Lecture notes in computer science: medical content-based retrieval for clinical decision support, vol 7723, pp 80–91

  14. Shimizu A, Narihira T, Furukawa D, Kobatake H, Nawano S, Shinozaki K (2008) Ensemble segmentation using AdaBoost with application to liver lesion extraction from a CT volume. In: Workshop on 3D segmentation in the clinic: a grand challenge II, MICCAI. http://grand-challenge2008.bigr.nl/proceedings/pdfs/lts08/06_LC%20Taker.pdf

  15. Pescia D, Paragios N, Chemouny S (2008) Automatic detection of liver tumors. In: Proceedings of the 2008 IEEE international symposium on biomedical imaging, pp 672–675

  16. Massoptier L, Casciaro S (2008) A new fully automatic and robust algorithm for fast segmentation of liver tissue and tumors from CT scans. Eur Radiol 18(8):1658–1665

    Article  PubMed  Google Scholar 

  17. Moltz JH, Bornemann L, Kuhnigk JM, Dicken V, Peitgen E, Meier S, Bolte H, Fabel M, Bauknecht HC, Hittinger M, Kiessling A, Pusken M, Peitgen HO (2009) Advanced segmentation techniques for lung nodules, liver metastases, and enlarged lymph nodes in CT scans. IEEE J Sel Topics Signal Process 3(1):122–134

    Article  Google Scholar 

  18. Abdel-massieh NH, Hadhoud MM, Amin KM (2010) A novel fully automatic technique for liver tumor segmentation from CT scans with knowledge-based constraints. In: Proceedings of 2010 10th international conference on intelligent systems design and applications, pp 1253–1258

  19. Militzer A, Hager T, Jäger F, Tietjen C, Hornegger J (2010) Automatic detection and segmentation of focal liver lesions in contrast enhanced CT images. In: 2010 20th international conference on, pattern recognition, pp 2524–2527

  20. Masuda Y, Foruzan AH, Tateyama T, Chen YW (2010) Automatic liver tumor detection using EM/MPM algorithm and shape information. Softw Eng Data Mining, pp 692–695

  21. Casciaro S, Franchini R, Massoptier L, Casciaro E, Conversano F, Malvasi A, Lay-Ekuakille A (2012) Fully automatic segmentations of liver and hepatic tumors from 3-d computed tomography abdominal images: comparative evaluation of two automatic methods. IEEE Sens J 12(3):464–473

    Article  Google Scholar 

  22. Linguraru MG, Richbourg WJ, Liu J, Watt JM, Pamulapati V, Wang S, Summers RM (2012) Tumor burden analysis on computed tomography by automated liver and tumor segmentation. IEEE Trans Med Imaging 31(10):1965–1976

    Article  PubMed Central  PubMed  Google Scholar 

  23. Wu D, Liu D, Suehling M, Tietjen C, Soza G, Zhou KS (2012) Automatic detection of liver lesion from 3d computed tomography images. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp 31–37

  24. Chi Y, Zhou J, Venkatesh SK, Huang S, Tian Q, Hennedige T, Liu L (2013) Computer-aided focal liver lesion detection. Int J Comput Assist Radiol Surg 8(4):511–525

    Google Scholar 

  25. Schwier M, Moltz JH, Peitgen HO (2011) Object-based analysis of CT images for automatic detection and segmentation of hypodense liver lesions. Int J Comput Assist Radiol.Surg 6(6):737–747

    Article  PubMed  Google Scholar 

  26. Folio LR, Choi MM, Solomon JM, Schaub NP (2013) Automated registration, segmentation, and measurement of metastatic melanoma tumors in serial CT scans. Acad Radiol 20(5):604–613

    Article  PubMed  Google Scholar 

  27. Deng X, Du G (eds) (2008) Workshop on 3D segmentation in the clinic: a grand challenge II, MICCAI. http://www.grand-challenge2008.bigr.nl/proceedings/liver/articles.html

  28. Sethian JA (1999) Level set methods and fast marching methods. Cambridge University Press, Cambridge

    Google Scholar 

  29. Heimann T, Styner M, van Ginneken B (eds) (2007) Workshop on 3D segmentation in the clinic: a grand challenge, MICCAI. http://mbi.dkfz-heidelberg.de/grand-challenge2007/sites/proceed.htm

  30. Ruskó L, Bekes G (2010) Liver segmentation for contrast-enhanced MR images using partitioned probabilistic model. Int J Comput Assist Radiol Surg 6(1):13–20

    Article  PubMed  Google Scholar 

  31. Metz CE (2006) Receiver operating characteristic analysis: a tool for the quantitative evaluation of observer performance and imaging systems. J Am Coll Radiol 3(6):413–422

    Article  PubMed  Google Scholar 

Download references

Acknowledgments

This work was supported by the research and development fund GOP-1.1.1-08/1-2008-0037 of the National Development Agency of Hungary. Hereby, the authors would like to thank Dr. Zsolt Berényi MD and Prof. Dr. András Palkó MD from the Radiology Department, Faculty of Medicine, University of Szeged for their feedback about clinical liver lesion assessment.

Conflict of interest

Authors, László Ruskó and Ádám Perényi declare that they have no conflict of interest. Co-author, Dr. Ádám Perényi, as well as her institution, University of Szeged, Department of Radiology was financially supported by GE Hungary Healthcare division within the framework of the research and development tender GOP-1.1.1-08/1-2008-0037 of the National Development Agency of Hungary.

Author information

Authors and Affiliations

  1. GE Hungary Healthcare Division, Petőfi Sándor sgt. 10, 6722 , Szeged, Hungary

    László Ruskó

  2. Department of Radiology, University of Szeged, Semmelweis utca 6., 6725 , Szeged, Hungary

    Ádám Perényi

Authors
  1. László Ruskó
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ádám Perényi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to László Ruskó.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Ruskó, L., Perényi, Á. Automated liver lesion detection in CT images based on multi-level geometric features. Int J CARS 9, 577–593 (2014). https://doi.org/10.1007/s11548-013-0949-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11548-013-0949-9

Keywords

Search

Navigation