Advertisement

An improved random forests approach for interactive lobar segmentation on emphysema detection

  • Qiang Li
  • Lei Chen
  • Xiangju Li
  • Shuyue Xia
  • Yan KangEmail author
Original Paper
First Online:
  • 48 Downloads

Abstract

Emphysema is one of the most widespread diseases in chronic diseases. Early diagnosis is crucial in slowing down the decline in the lung function of patients. Nowadays, it mainly relies on the pulmonary function test, which suffers from two drawbacks: the pulmonary function test cannot reflect the severity of patients with heterogeneous emphysema accurately and diagnose dyspnea patients. Hence, we propose an approach to analyze emphysema based on computed tomography (CT) images, which can detect the location of emphysema on each lung lobe. For the cases that cannot be automatically segmented, a random forests-based multi-task learning method with granular computing perspective is designed for interactive lobar segmentation. The effectiveness of the proposed emphysema detection method is demonstrated with the CT dataset from 93 patients with chronic obstructive pulmonary diseases. The accuracy of the presented lobar segmentation technique is proved on the CT images that cannot segment lobes. The experimental results show that the proposed interactive lobar segmentation method on locate emphysema about lobes could detect early symptoms of emphysema and reduce \(17.2\%\) of missing diagnosis.

Keywords

Random forests Lobar segmentation Chronic obstructive pulmonary disease Pulmonary function test Emphysema Granular computing 
This is a preview of subscription content, log in to check access.

Notes

Acknowledgements

The authors acknowledge support for the research reported in this paper through the research development fund at the Project (2017YFC0114200) of National Key Technology R&D Program of the Ministry of Science and Technology and the Project (2018YFC1311900) of National Key R&D Program of China. The authors sincerely thank Prof.Shuyue Xia at the Central Hospital Affiliated to Shenyang Medical College for providing image data.

References

  1. Amit Y, Geman D (1997) Shape quantization and recognition with randomized trees. MIT Press 9(7):1545–1588Google Scholar
  2. Atanassov KT (1986) Intuitionistic fuzzy sets. Fuzzy Sets Syst 20(1):87–96MathSciNetzbMATHCrossRefGoogle Scholar
  3. Bağcı U, Bray M, Caban J, Yao J, Mollura DJ (2012) Computer-assisted detection of infectious lung diseases: a review. Computer Med Imag Graph 36(1):72–84CrossRefGoogle Scholar
  4. Barinova O, Shapovalov R, Sudakov S, Velizhev A (2012) Online random forest for interactive image segmentation. Exp Econ Machine Learn 12(2):1Google Scholar
  5. Birant D, Kut A (2007) Stdbscan: an algorithm for clustering spatialtemporal data. Data Knowl Eng 60(1):208–221CrossRefGoogle Scholar
  6. Bosch A, Zisserman A, Munoz X (2007) Image classification using random forests and ferns. IEEE Int Conf Comput Vis 613(2):1–8Google Scholar
  7. Boueiz A, Chang Y, Cho MH, Washko GR, Estépar RSJ, Bowler RP, Crapo JD, DeMeo DL, Dy JG, Silverman EK et al (2017) Lobar emphysema distribution is associated with 5-year radiologic disease progression. Chest 153(1):65–76CrossRefGoogle Scholar
  8. Bragman FJ, McClelland JR, Jacob J, Hurst JR, Hawkes DJ (2017) Pulmonary lobe segmentation with probabilistic segmentation of the fissures and a groupwise fissure prior. IEEE Trans Med Imag 36(8):1650–1663CrossRefGoogle Scholar
  9. Breiman L (2001) Random forests. Mach Learn 45(1):5–32zbMATHCrossRefGoogle Scholar
  10. Buist AS, McBurnie MA, Vollmer WM, Gillespie S, Burney P, Mannino DM, Menezes AM, Sullivan SD, Lee TA, Weiss KB et al (2007) International variation in the prevalence of copd(the bolp study): a population-based prevalence stydy. Lancet 370(9589):741–750CrossRefGoogle Scholar
  11. Chen SM, Chang CH (2015) A novel similarity measure between atanassov’s intuitionistic fuzzy sets based on transformation techniques with applications to pattern recognition. Inf Sci 291(p):96–114CrossRefGoogle Scholar
  12. Chen SM, Chang YC (2011) Weighted fuzzy rule interpolation based on ga-based weight-learning techniques. IEEE Trans Fuzzy Syst 19(4):729–744MathSciNetCrossRefGoogle Scholar
  13. Chen SM, Huang CM (2003) Generating weighted fuzzy rules from relational database systems for estimating null values using genetic algorithms. IEEE Trans Fuzzy Syst 11(4):495–506CrossRefGoogle Scholar
  14. Chen SM, Cheng SH, Chiou CH (2016) Fuzzy multiattribute group decision making based on intuitionistic fuzzy sets and evidential reasoning methodology. Inf Fusion 27(p):215–227CrossRefGoogle Scholar
  15. Cheng SH, Chen SM, Jian WS (2016) Fuzzy time series forecasting based on fuzzy logical relationships and similarity measures. Inf Sci 327(p):272–287MathSciNetzbMATHCrossRefGoogle Scholar
  16. Cheng Y (1995) Mean shift, mode seeking, and clustering. IEEE Trans Pat Anal Mach Intell 17(8):790–799CrossRefGoogle Scholar
  17. Chu C, Bai J, Liu L, Wu X, Zheng G (2014) Fully automatic segmentation of hip ct images via random forest regression-based atlas selection and optimal graph search-based surface detection. In: Asian Conference on Computer Vision, Springer, pp 640–654Google Scholar
  18. Criminisi A, Shotton J, Konukoglu E (2011) Decision forests for classification, regression, density estimation, manifold learning and semi-supervised learning. Microsoft Research technical report TR-2011-114 5(1):12Google Scholar
  19. Cuingnet R, Prevost R, Lesage D, Cohen LD, Mory B, Ardon R (2012) Automatic detection and segmentation of kidneys in 3d ct images using random forests. Springer 132(11):66–74Google Scholar
  20. Culver BH, Graham BL, Coates AL, Wanger J, Berry CE, Clarke PK, Hallstrand TS, Hankinson JL, Kaminsky DA, MacIntyre NR, et al. (2017) Recommendations for a standardized pulmonary function report. In: An official american thoracic society technical statement. American Journal of Respiratory and Critical Care Medicine 196(11):1463Google Scholar
  21. Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. IEEE Comput Soc Conf Comput Vis Pat Recogn 1:886–893Google Scholar
  22. Emam M, De La Faverie JR, Gharbi N, El-Gohary M (2010) Characterization of lung’s emphysema distribution: Numerical assessment of disease development. In: International Conference on New Trends in Information Science and Service Science, pp 464–469Google Scholar
  23. Ester M, Kriegel HP, Sander J, Xu X et al (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. Proc Sec Int Conf Knowl Discov Data Min 96(34):226–331Google Scholar
  24. Fukunaga K, Hostetler L (1975) The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Trans Inf Theory 21(1):32–40MathSciNetzbMATHCrossRefGoogle Scholar
  25. Geurts P, Ernst D, Wehenkel L (2006) Extremely randomized trees. Mach Learn 63(1):3–42zbMATHCrossRefGoogle Scholar
  26. Giuliani N, Payer C, Pienn M, Olschewski H, Urschler M (2018) Pulmonary lobe segmentation in ct images using alpha-expansion. Imag Computer Graph Theory Appl 23(6):387–394Google Scholar
  27. Grady L (2006) Random walks for image segmentation. IEEE Trans Pat Anal Mach Intell 28(11):1768–1783CrossRefGoogle Scholar
  28. Greenspan H, Pinhas AT (2007) Medical image categorization and retrieval for pacs using the gmmkl framework. IEEE Trans Inf Technol Biomed 11(2):190–202CrossRefGoogle Scholar
  29. Group NETTR (2001) Patients at high risk of death after lung-volume reduction surgery. N Engl J Med 345(15):1075–1083CrossRefGoogle Scholar
  30. Häme Y, Angelini ED, Hoffman EA, Barr RG, Laine AF (2013) Robust quantification of pulmonary emphysema with a hidden markov measure field model. In: IEEE International Symposium on Biomedical Imaging, pp 382–385Google Scholar
  31. Hu H, Shi Z (2009) Machine learning as granular computing. In: 2009 IEEE International Conference on Granular Computing, pp 229–234Google Scholar
  32. Karri SPK, Sheet D, Mazumder AG, Ghosh S, Chakraborty D, Chatterjee J, Ray AK (2014) Deep learnt random forests for segmentation of retinal layers in optical coherence tomography images. ISBI2014 121(1):162–172Google Scholar
  33. Kim N, Seo JB, Lee Y, Lee JG, Kim SS, Kang SH (2009) Development of an automatic classification system for differentiation of obstructive lung disease using hrct. J Digit Imag 22(2):136–148CrossRefGoogle Scholar
  34. Kontschieder P, Fiterau M, Criminisi A, Rota Bulo S (2015) Deep neural decision forests. In: Proceedings of the IEEE international conference on computer vision, pp 1467–1475Google Scholar
  35. Kurumalla S, Rao PS (2016) K-nearest neighbor based dbscan clustering algorithm for image segmentation. J Theor Appl Inf Technol 92(2):395–402Google Scholar
  36. Lassen B, van Rikxoort EM, Schmidt M, Kerkstra S, van Ginneken B, Kuhnigk JM (2013) Automatic segmentation of the pulmonary lobes from chest ct scans based on fissures, vessels, and bronchi. IEEE Trans Med Imag 32(2):210–222CrossRefGoogle Scholar
  37. Lee LW, Chen SM (2008) Fuzzy risk analysis based on fuzzy numbers with different shapes and different deviations. Expert Syst Appl 34(4):2763–2771CrossRefGoogle Scholar
  38. Lee SM, Seo JB, Kim N, Oh SY, Oh YM (2016) Optimal threshold of subtraction method for quantification of air-trapping on coregistered ct in copd patients. Eur Radiol 26(7):2184–2192CrossRefGoogle Scholar
  39. Leistner C, Saffari A, Santner J, Bischof H (2009) Semi-supervised random forests. In: 2009 IEEE International Conference on Computer Vision, pp 506–513Google Scholar
  40. Lim HJ, Weinheimer O, Wielpütz MO, Dinkel J, Hielscher T, Gompelmann D, Kauczor HU, Heussel CP (2016) Fully automated pulmonary lobar segmentation: influence of different prototype software programs onto quantitative evaluation of chronic obstructive lung disease. PloS One 11(3):e0151498CrossRefGoogle Scholar
  41. LindaA MEMS (2014) Segmentation of pulmonary lobes using marker based watershed algorithm. Int J Eng Res Appl 9005(3):71–75Google Scholar
  42. Liu H, Cocea M (2017a) Granular computing-based approach for classification towards reduction of bias in ensemble learning. Granul Comput 2(3):131–139CrossRefGoogle Scholar
  43. Liu H, Cocea M (2017b) Granular computing based machine learning: a big data processing approach. Studies in big data, vol 35. SpringerGoogle Scholar
  44. Liu H, Cocea M (2018) Nature-inspired framework of ensemble learning for collaborative classification in granular computing context. Granul Comput 5:1–10Google Scholar
  45. Liu H, Cocea M, Ding W (2018) Multi-task learning for intelligent data processing in granular computing context. Granul Comput 3(3):257–273CrossRefGoogle Scholar
  46. Liu P, Chen SM (2017) Group decision making based on heronian aggregation operators of intuitionistic fuzzy numbers. IEEE Trans Cybern 47(9):2514–2530CrossRefGoogle Scholar
  47. Liu P, Chen SM, Liu J (2017) Multiple attribute group decision making based on intuitionistic fuzzy interaction partitioned bonferroni mean operators. Inf Sci 411((p)):98–121MathSciNetCrossRefGoogle Scholar
  48. MacQueen J et al (1967) Some methods for classification and analysis of multivariate observations. Proc Berkel Symp Math Stat Probab 1(14):281–297MathSciNetzbMATHGoogle Scholar
  49. Nishio M, Tanaka Y (2018) Heterogeneity in pulmonary emphysema: analysis of ct attenuation using gaussian mixture model. PloS One 13(2):e0192892CrossRefGoogle Scholar
  50. Pena IP, Cheplygina V, Paschaloudi S, Vuust M, Carl J, Weinreich UM, Østergaard LR, de Bruijne M (2018) Automatic emphysema detection using weakly labeled hrct lung images. PloS One 13(10):e0205397CrossRefGoogle Scholar
  51. Rabe KF, Hurd S, Anzueto A, Barnes PJ, Buist SA, Calverley P, Fukuchi Y, Jenkins C, Rodriguez-Roisin R, Van Weel C et al (2007) Global strategy for the diagnosis, management, and prevention of chronic obstructive pulmonary disease: gold executive summary. Am J Respirat Crit Care Med 176(6):532–555CrossRefGoogle Scholar
  52. Rogez G, Rihan J, Ramalingam S, Orrite C, Torr ea (2008) Randomized trees for human pose detection. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp 1–8Google Scholar
  53. Gea Scheuch (2003) Deposition of monodisperse aerosols in patients with hereditary \(\alpha 1\)-antitrypsin deficiency and lung emphysema. Atemwegs Lungenkrankheiten 29(7):317–323Google Scholar
  54. Schubert E, Sander J, Ester M, Kriegel HP, Xu X (2017) Dbscan revisited, revisited: why and how you should (still) use dbscan. Acm Trans Datab Syst 42(3):19MathSciNetGoogle Scholar
  55. Stavngaard T, Shaker S, Bach K, Stoel B, Dirksen A (2006) Quantitative assessment of regional emphysema distribution in patients with chronic obstructive pulmonary disease (copd). Acta Radiol 47(9):914–921CrossRefGoogle Scholar
  56. Sverzellati N, Calabrò E, Randi G, La Vecchia C, Marchianò A, Kuhnigk JM, Zompatori M, Spagnolo P, Pastorino U (2009) Sex differences in emphysema phenotype in smokers without airflow obstruction. Eur Respir J 33(6):1320–1328CrossRefGoogle Scholar
  57. Tu Z, Bai X (2010) Auto-context and its application to high-level vision tasks and 3d brain image segmentation. IEEE Trans Pattern Anal Mach Intell 32(10):1744–1757CrossRefGoogle Scholar
  58. Van Rikxoort E, Van Ginneken B (2011) Automatic segmentation of the lungs and lobes from thoracic ct scans. Int Workshop Pulm Image Anal 13(10):261–268Google Scholar
  59. Vestbo J, Hurd SS, Agustí AG, Jones PW, Vogelmeier C, Anzueto A, Barnes PJ, Fabbri LM, Martinez FJ, Nishimura M et al (2013) Global strategy for the diagnosis, management and prevention of chronic obstructive pulmonary disease(copd). Global Initiative Chronic Obstruct Lung Dis 187(4):347–365Google Scholar
  60. Vogelmeier CF, Criner GJ, Martinez FJ, Anzueto A, Barnes PJ, Bourbeau J, Celli BR, Chen R, Decramer M, Fabbri LM et al (2017) Global strategy for the diagnosis, management and prevention of chronic obstructive pulmonary disease(copd). Am J Respirat Crit Care Med 195(5):557–582CrossRefGoogle Scholar
  61. Wang C, Xu J, Yang L, Xu Y, Zhang X, Bai C, Kang J, Ran P, Shen H, Wen F et al (2018) Prevalence and risk factors of chronic obstructive pulmonary disease in china (the china pulmonary health [cph] study): a national cross-sectional study. Lancet 391(10131):1706–1717CrossRefGoogle Scholar
  62. Wang Z, Gu S, Leader JK, Kundu S, Tedrow JR, Sciurba FC, Gur D, Siegfried JM, Pu J (2013) Optimal threshold in ct quantification of emphysema. Eur Radiol 23(4):975–984CrossRefGoogle Scholar
  63. Yin D, Pan J, Chen P, Zhang R (2008) Medical image categorization based on gaussian mixture model. Int Conf Biomed Eng Inf 2:128–131Google Scholar
  64. Zadeh LA (1965) Fuzzy sets. Inf Control 8(3):338–353zbMATHCrossRefGoogle Scholar
  65. Zhou M, Wang H, Zhu J, Chen W, Wang L, Liu S, Li Y, Wang L, Liu Y, Yin P et al (2016) Cause-specific mortality for 240 causes in china during 1990–2013 a systematic subnational analysis for the global burden of disease study \(2013\). Lancet 387(10015):251–272CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Qiang Li
    • 1
  • Lei Chen
    • 2
  • Xiangju Li
    • 3
  • Shuyue Xia
    • 4
  • Yan Kang
    • 1
    • 5
    Email author
  1. 1.Sino-dutch Biomedical and Information Engineering SchoolNortheastern UniversityShenyangChina
  2. 2.Neusoft Medical Systems Ltd.ShenyangChina
  3. 3.School of Computer Science and EngineeringNortheastern UniversityShenyangChina
  4. 4.The Central Hospital Affiliated to Shenyang Medical CollegeShenyangChina
  5. 5.Neusoft Intelligent Medical Research InstituteShenyangChina

Personalised recommendations

Cite article

Buy options