Computational Intelligent Image Analysis for Assisting Radiation Oncologists’ Decision Making in Radiation Treatment Planning

  • Hidetaka Arimura
  • Taiki Magome
  • Genyu Kakiuchi
  • Jumpei Kuwazuru
  • Asumi Mizoguchi


This chapter describes the computational image analysis for assisting radiation oncologists’ decision making in radiation treatment planning for high precision radiation therapy. The radiation therapy consists of five steps, i.e., diagnosis, treatment planning, patient setup, treatment, and follow-up, in which computational intelligent image analysis and pattern recognition methods play important roles in improving the accuracy of radiation therapy and assisting radiation oncologists’ or medical physicists’ decision making. In particular, the treatment planning step is substantially important and indispensable, because the subsequent steps must be performed according to the treatment plan. This chapter introduces a number of studies on computational intelligent image analysis used for the computer-aided decision making in radiation treatment planning. Moreover, the authors also explore computer-aided treatment planning methods including automated beam arrangement based on similar cases, computerized contouring of lung tumor regions using a support vector machine (SVM) classifier, and a computerized method for determination of robust beam directions against patient setup errors in particle therapy.


Support Vector Machine Standardize Uptake Value Positron Emission Tomography Image Planning Target Volume Stereotactic Body Radiation Therapy 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



The authors are grateful to all members of the Arimura Laboratory (, whose comments made an enormous contribution to this chapter. This research was partially supported by the Ministry of Education, Culture, Sports Science, and Technology (MEXT), Grant-in-Aid for Scientific Research (C), 22611011, 2011to 2012, and Grant-in-Aid for Scientific Research on Innovative Areas, 24103707, 2012.


  1. 1.
    National Cancer Center (2010) Cancer statistics in Japan
  2. 2.
    Dawson LA, Sharpe MB (2006) Image-guided radiotherapy: rationale, benefits, and limitations. The Lancet Oncol 7(10):848–858CrossRefGoogle Scholar
  3. 3.
    Evans PM (2008) Anatomical imaging for radiotherapy. Phys Med Biol 53(12):R151–R191CrossRefGoogle Scholar
  4. 4.
    ICRU (1999) ICRU report 62, Prescribing, recording and reporting photon beam therapy. (supplement to ICRU report 50)Google Scholar
  5. 5.
    Onishi H et al (2011) Stereotactic body radiotherapy (SBRT) for operable stage I non-small-cell lung cancer: can SBRT be comparable to surgery? Int J Radiat Oncol Biol Phys 81:1352–1358CrossRefGoogle Scholar
  6. 6.
    Ploquin N, Rangel A, Dunscombe P (2008) Phantom evaluation of a commercially available three modality image guided radiation therapy system. Med Phys 35(12):5303–5311CrossRefGoogle Scholar
  7. 7.
    Wang Z, Nelson JW, Yoo S et al (2009) Refinement of treatment setup and target localization accuracy using three-dimensional cone-beam computed tomography for stereotactic body radiotherapy. Int J Radiat Oncol Biol Phys 73(2):571–577CrossRefGoogle Scholar
  8. 8.
    Shirato H, Shimizu S, Kitamura K et al (2000) Four-dimensional treatment planning and fluoroscopic real-time tumor tracking radiotherapy for moving tumor. Int J Radiat Oncol Biol Phys 48:435–442CrossRefGoogle Scholar
  9. 9.
    Su M, Miften M, Whiddon C, Sun X, Light K, Marks L (2005) An artificial neural network for predicting the incidence of radiation pneumonitis. Med Phys 32(2):318–325CrossRefGoogle Scholar
  10. 10.
    Kakar M, Seierstad T, Røe K, Olsen DR (2009) Artificial neural networks for prediction of response to chemoradiation in HT29 xenografts. Int J Radiat Oncol Biol Phys 75(2):506–511CrossRefGoogle Scholar
  11. 11.
    El Naqa I, Bradley JD, Lindsay PE, Hope AJ, Deasy JO (2009) Predicting radiotherapy outcomes using statistical learning techniques. Phys Med Biol 54(18):S9–S30CrossRefGoogle Scholar
  12. 12.
    Jayasurya K, Fung G, Yu S, Dehing-Oberije C, De Ruysscher D, Hope A, De Neve W, Lievens Y, Lambin P, Dekker AL (2010) Comparison of Bayesian network and support vector machine models for two-year survival prediction in lung cancer patients treated with radiotherapy. Med Phys 37(4):1401–1407CrossRefGoogle Scholar
  13. 13.
    Atsumi K, Shioyama Y, Arimura H, Terashima K, Matsuki T, Ohga S, Yoshitake T, Nonoshita T, Tsurumaru D, Ohnishi K, Asai K, Matsumoto K, Nakamura K, Honda H (2012) Esophageal stenosis associated with tumor regression in radiation therapy for esophageal cancer: frequency and prediction. Int J Radiat Oncol Biol Phys 82(5):1973–1980CrossRefGoogle Scholar
  14. 14.
    Nagata Y, Wulf J, Lax I, Timmerman R, Zimmermann F, Stojkovski I, Jeremic B (2011) Stereotactic radiotherapy of primary lung cancer and other targets: results of consultant meeting of the international atomic energy agency. Int J Radiat Oncol Biol Phys 79:660–669CrossRefGoogle Scholar
  15. 15.
    Takayama K, Nagata Y, Negoro Y, Mizowaki T, Sakamoto T, Sakamoto M, Aoki T, Yano S, Koga S, Hiraoka M (2005) Treatment planning of stereotactic radiotherapy for solitary lung tumor. Int J Radiat Oncol Biol Phys 61:1565–1571CrossRefGoogle Scholar
  16. 16.
    Meyer J, Hummel SM, Cho PS, Austin-Seymour MM, Phillips MH (2005) Automatic selection of non-coplanar beam directions for three-dimensional conformal radiotherapy. Br J Radiol 78:316–327CrossRefGoogle Scholar
  17. 17.
    dePooter JA, Méndez Romero A, Wunderink W et al (2008) Automated non-coplanar beam direction optimization improves IMRT in SBRT of liver metastasis. Radiother Oncol 88:376–381CrossRefGoogle Scholar
  18. 18.
    Aisen AM, Broderick LS, Winer-Muram H, Brodley CE, Kak AC, Pavlopoulou C, Dy J, Shyu CR, Marchiori A (2003) Automated storage and retrieval of thin-section CT images to assist diagnosis. System description and preliminary assessment. Radiology 228:265–270CrossRefGoogle Scholar
  19. 19.
    Li Q, Li F, Shiraishi J, Katsuragawa S, Sone S, Doi K (2003) Investigation of new psychophysical measures for evaluation of similar images on thoracic CT for distinction between benign and malignant nodules. Med Phys 30:2584–2593CrossRefGoogle Scholar
  20. 20.
    Kumazawa S, Muramatsu C, Li Q, Li F, Shiraishi J, Caligiuri P, Schmidt RA, MacMahon H, Doi K (2008) An investigation of radiologists’ perception of lesion similarity: observations with paired breast masses on mammograms and paired lung nodules on CT images. Acad Radiol 15:887–894CrossRefGoogle Scholar
  21. 21.
    Muramatsu C, Li Q, Suzuki K, Schmidt RA, Shiraishi J, Newstead GM, Doi K (2005) Investigation of psychophysical measure for evaluation of similar images for mammographic masses: preliminary results. Med Phys 32:2295–2304CrossRefGoogle Scholar
  22. 22.
    Muramatsu C, Li Q, Schmidt RA, Shiraishi J, Doi K (2009) Determination of similarity measures for pairs of mass lesions on mammograms by use of BI-RADS lesion descriptors and image features. Acad Radiol 16:443–449CrossRefGoogle Scholar
  23. 23.
    Muramatsu C, Schmidt RA, Shiraishi J, Li Q, Doi K (2010) Presentation of similar images as a reference for distinction between benign and malignant masses on mammograms: analysis of initial observer study. J Digit Imaging 23:592–602CrossRefGoogle Scholar
  24. 24.
    Burger W, Burge MJ (2007) Digital image processing: an algorithmic introduction using java, 1st edn. Springer, New YorkGoogle Scholar
  25. 25.
    Steene JV et al (2002) Definition of gross tumor volume in lung cancer: inter-observer variability. Radiother Oncol 62:37–49CrossRefGoogle Scholar
  26. 26.
    Bradley JD, Perez CA, Dehdashti F et al (2004) Implementing biologic target volumes in radiation treatment planning for non-small cell lung cancer. J Nucl Med 45:96S–101SGoogle Scholar
  27. 27.
    Nakamura K, Shioyama Y, Tokumaru S et al (2008) Variation of clinical target volume definition among Japanese radiation oncologist in external beam radiotherapy for prostate cancer. Jpn J Clin Oncol 38(4):275–280CrossRefGoogle Scholar
  28. 28.
    Day E, Betler J, Parda D et al (2009) A region growing method for tumor volume segmentation on PET images for rectal and anal cancer patients. Med Phys 36(10):4349–4358CrossRefGoogle Scholar
  29. 29.
    Biehl JB, Kong FM, Dehdashti F et al (2006) 18F-FDG PET definition of gross tumor volume for radiotherapy of non-small cell lung cancer: is a single standardized uptake value threshold approach appropriate? J Nucl Med 47(11):1808–1812Google Scholar
  30. 30.
    Zhang T, Tachiya Y, Sakaguchi Y et al (2010) Phantom study on three-dimensional target volume delineation by PET/CT-based auto-contouring. Fukuoka Acta Media 101(11):238–246Google Scholar
  31. 31.
    Aristophanous M, Penney BC, Martel MK et al (2007) Gaussian mixture model for definition of lung tumor volumes in positron emission tomography. Med Phys 34(11):4223–4235CrossRefGoogle Scholar
  32. 32.
    Belhassen S, Zaidi H (2010) A novel fuzzy C-means algorithm for unsupervised heterogeneous tumor quantification in PET. Med Phys 37(3):1309–1324CrossRefGoogle Scholar
  33. 33.
    Hatt M, Rest CC, Turzo A et al (2009) A fuzzy locally adaptive Bayesian segmentation approach for volume determination in PET. IEEE Trans Med Imaging 28(6):881–893CrossRefGoogle Scholar
  34. 34.
    Hatt M, Rest CC, Nidal A et al (2011) PET functional volume delineation: a robustness and repeatability study. Eur J Nucl Med Mol Imaging 38:3663–3672Google Scholar
  35. 35.
    Geets X, Lee JA, Bol A et al (2007) A gradient-based method for segmenting FDG-PET images: methodology and validation. Eur J Nucl Med Mol Imaging 34:1427–1438CrossRefGoogle Scholar
  36. 36.
    Rousson M, Khamene A, Diallo M et al (2005) Constrained surface evolutions for prostate and bladder segmentation in CT images. In: Liu Y, Jiang T, Zhang C (eds) Lecture notes in computer science (LNCS), vol 3765. Springer, New York, pp 251–260Google Scholar
  37. 37.
    Strassmann G, Abdellaoui S, Richter D et al (2010) Atlas-based semiautomatic target volume definition (CTV) for head-and-neck tumors. Int J Radiat Oncol Biol Phys 78(4):1270–1276CrossRefGoogle Scholar
  38. 38.
    El Naqa I, Yang D, Apte A et al (2007) Concurrent multimodality image segmentation by active contours for radiotherapy treatment planning. Med Phys 34(2):4738–4749CrossRefGoogle Scholar
  39. 39.
    Pluim JP, Maintz JB, Viergever MA (2003) Mutual-information-based registration of medical images: a survey. IEEE Trans Med Imaging 22(8):986–1004CrossRefGoogle Scholar
  40. 40.
    Joachims T (2008) SVMlight. Cornell University.
  41. 41.
    Okada T, Kamada T, Tsuji H, Mizoe JE, Baba M, Kato S, Yamada S, Sugahara S, Yasuda S, Yamamoto N, Imai R, Hasegawa A, Imada H, Kiyohara H, Jingu K, Shinoto M, Tsujii H (2010) Carbon ion radiotherapy: clinical experiences at National Institute of Radiological Science (NIRS). J Radiat Res 51:355–364CrossRefGoogle Scholar
  42. 42.
    Minohara S, Fukuda S, Kanematsu N, Takei Y, Furukawa T, Inaniwa T, Matsufuji N, Mori S, Noda K (2010) Recent innovations in carbon–ion radiotherapy. J Radiat Res 51:385–392CrossRefGoogle Scholar
  43. 43.
    Hui Z, Zhang X, Starkschall G, Li Y, Mohan R, Komaki R, Cox JD, Chang JY (2008) Effects of interfractional motion and anatomic changes on proton therapy dose distribution in lung cancer. Int J Radiat Oncol Biol Phys 72:1385–1395CrossRefGoogle Scholar
  44. 44.
    Inaniwa T, Kanematsu N, Furukawa T, Hasegawa A (2011) A robust algorithm of intensity modulated proton therapy for critical tissue sparing and target coverage. Phys Med Biol 56:4749–4770CrossRefGoogle Scholar
  45. 45.
    Lomax AJ (2008) Intensity modulated proton therapy and its sensitivity to treatment uncertainties 2: the potential effects of inter-fraction and inter-field motions. Phys Med Biol 53:1043–1056CrossRefGoogle Scholar
  46. 46.
    Pflugfelder D, Wilkens JJ, Oelfke U (2008) Worst case optimization: a method to account for uncertainties in optimization of intensity modulated proton therapy. Phys Med Biol 53:1689–1700CrossRefGoogle Scholar
  47. 47.
    Sejpal SV, Amos RA, Bluett JB, Levy LB, Kudchadker RJ, Johnson J, Choi S, Lee AK (2009) Dosimetric changes resulting from patient rotational setup errors in proton therapy prostate plans. Int J Radiat Oncol Biol Phys 75:40–48CrossRefGoogle Scholar
  48. 48.
    Unkelbach J, Bortfeld T, Martin BC, Soukup M (2009) Reducing the sensitivity of IMPT treatment plans to setup errors and range uncertainties via probabilistic treatment planning. Med Phys 36:149–163CrossRefGoogle Scholar
  49. 49.
    Zhang X, Dong L, Lee AK, Cox JD, Kuban DA, Zhu RX, Wang X, Li Y, Newhauser WD, Gillin M, Mohan R (2007) Effect of anatomic motion on proton therapy dose distribution in prostate cancer treatment. Int J Radiat Oncol Biol Phys 67:620–629CrossRefGoogle Scholar
  50. 50.
    Kakiuchi G, Arimura H, Shioyama Y, Nagano A, Minohara S, Mizoguchi A, Honda H, Toyofuku F, Ohki M, Hirata H (2011) Optimization of robust beam angles to patient setup errors for head and neck cancer in hadron particle therapy. ASTRO 2011, Abstract 3413Google Scholar
  51. 51.
    Saw CB, Loper A, Komanduri K, Combine T, Huq S, Scicutella C (2005) Determination of CT-to-density conversion relationship for image-based treatment planning system. Med Dosim 30:145–148CrossRefGoogle Scholar
  52. 52.
    Otsu N (1979) A threshold selection method from gray level histograms. IEEE Trans Syst Man Cybern SMC-9:62–66Google Scholar
  53. 53.
    Herman GT, Zheng J, Bucholtz CA (1992) Shape-based interpolation. IEEE Comput Graph Appl 12:69–79CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  • Hidetaka Arimura
    • 1
  • Taiki Magome
    • 1
  • Genyu Kakiuchi
    • 1
  • Jumpei Kuwazuru
    • 1
  • Asumi Mizoguchi
    • 1
  1. 1.Division of Medical Quantum Sciences, Department of Health Sciences, Faculty of Medical SciencesKyushu UniversityFukuokaJapan

Personalised recommendations