Parallel Multispectral Image Segmentation for Computer Aided Thyroid Cytology

  • Shishir Shah
  • Edgar Gabriel


Cancer continues to remain a major health problem in the United States, with one of two men and one of three women developing cancer in their lifetime. Thyroid nodule is one of many common cancers. Nodules are more common in women and increase in frequency with age and with decreasing iodine intake. It has been estimated that up to 20% of the world population [1, 2] and approximately 50% of 60-year-old persons [4] have palpable thyroid nodule or nodules. In the US, up to 7% of the adult population has a palpable thyroid nodule [3]. The clinical spectrum ranges from the incidental, asymptotic, small, solitary nodule, in which the exclusion of cancer is a major concern, to the large, partly intrathoracic nodule that causes pressure symptoms, for which treatment is warranted regardless of cause [4, 5] . The most common cytologic diagnoses of thyroid nodules are colloid nodules, cysts, thyroiditis, follicular neoplasm, and thyroid carcinomas. Colloid nodules are the most common and do not have an increased risk of malignancy, therefore, the choice of management is conservative. Follicular neoplasm includes follicular adenoma and follicular carcinoma, which cannot be distinguished visually from each other based on cytology and the management remains controversial [2, 4, 5]. Thyroid carcinoma occurs in roughly 10% of all palpable nodules and the management is surgical removal [41].


Thyroid Nodule Fine Needle Aspiration Cytology Message Passing Interface Multispectral Image Follicular Adenoma 
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.


  1. 1.
    Hegedus L (2004) The thyroid nodule. New Eng J Med 351:1764–1771CrossRefGoogle Scholar
  2. 2.
    Hegedus L, Bonnema SJ, Bennedbaek FN (2003) Management of simple nodular goiter: current status and future perspective. Endocr Rev 24:102–132CrossRefGoogle Scholar
  3. 3.
    Singer PA, Cooper DS et al (1996) Treatment guidelines for patients with thyroid nodules and well differentiated thyroid cancer. Arch Intern Med 156:2165–2172CrossRefGoogle Scholar
  4. 4.
    Bennedbaek FN, Perrild H, Hegedus L (1999) Diagnosis and treatment of solitary thyroid nodule: results of a European survey. Clin Endocrinol (Oxf) 50:357–363CrossRefGoogle Scholar
  5. 5.
    Bennedbaek FN, Perrild H, Hegedus L (2000) Diagnosis and treatment of solitary thyroid nodule: results of a North American survey. J Clin Endocrinol Metab 85:2493–2498CrossRefGoogle Scholar
  6. 6.
    Feldman JA (1982) Dynamic connections in neural networks. Biol Cybern 46:27–39CrossRefGoogle Scholar
  7. 7.
    Papanicolaou Society of Cytopathology Task Force on Standard of Practice (1996) Guidelines of the papanicolaou society of cytopathology for the examination of fine-needle aspitation specimens from thyroid nodules. Mod Pathol 9:710–715Google Scholar
  8. 8.
    McCall A, Jarosz H, Lawrence AM, Paloyan E (1986) The incidence of thyroid carcinoma in solitary cold nodules and multinodular goiter. Surgery 100:1128–1132Google Scholar
  9. 9.
    Rosai J, Carangiu ML, DeLillis RA (1990) Atlas of tumor pathology. Armed Forces Institute of Pathology, WashingtonGoogle Scholar
  10. 10.
    The American Thyroid Association (2003) Consensus guidelines for thyroid testing in the new millenniumGoogle Scholar
  11. 11.
    Gutman PD, Henry M (1998) Fine needle aspiration cytology of the thyroid. Clin Lab Med 18:461–482Google Scholar
  12. 12.
    Kim E, Choi Y, Yang HS, Kang M, Jeong S, Yang S, Kim ED, Lee JH, Rasheed AA, Nasir HM, Rosdi MR (2003) A high-resolution multi-spectral imaging system for small satellites. Acta Astronaut 52(9):813–818CrossRefGoogle Scholar
  13. 13.
    Kerekes J, Baum J (2002) Spectral imaging system analytical model for subpixel object detection. IEEE Trans Geosci Remote Sens 40(5):1088–1101CrossRefGoogle Scholar
  14. 14.
    Kulcke A, Gurschler C, Spock G, Leitner R, Kraft M (2003) On-line classification of synthetic polymers using near infrared spectral imaging. J Near Infrared Spectrosc 11(1):71–81CrossRefGoogle Scholar
  15. 15.
    Schrock E, Manoir SD, Veldman T, Schoell B, Weinberg J, Ferguson-Smith M, Ning Y, Ledbetter D, Bar-Am I, Soenksen D, Sarini Y, Reid T (1996) Multicolor spectral karyotyping of human chromosomes. Science 273:494–497CrossRefGoogle Scholar
  16. 16.
    Maiti D, Sennoune S, Martinez-Zaguilan R (2003) Proton gradients in human breast cancer cells determined by confocal, multiphoton, and spectral imaging microscopy. FASEB J 17(4):A467Google Scholar
  17. 17.
    Haraguchi T et al (2002) Spectral imaging fluorescence spectroscopy. Genes Cells 7(9): 881–887CrossRefGoogle Scholar
  18. 18.
    Roy K, Bottrill I, Ingrams D, Pankratov M, Rebeiz E, Woo P, Shapshay S, Kabani S, Manoharan R (1995) Diagnostic fluorescence spectroscopy of oral mucosa. Proc SPIE 2395:135–142CrossRefGoogle Scholar
  19. 19.
    Feng C, Shuzhen C, Libo Z (2007) New abnormal cervical cell detection method of multi-spectral pap smears. Wuhan Univ J Nat Sci 12:476–480CrossRefGoogle Scholar
  20. 20.
    Shah S, Schwartz MR, Mody DR, Scheiber-Pacht M, Amrikachi M (2008) The role of multispectral microscopy in differentiating benign and malignant thyroid nodules: a pilot study of 24 cases. In: Proceedings of the annual meeting of the United States and Canadian academy of pathologyGoogle Scholar
  21. 21.
    Suen KC (2002) Fine-needle aspiration biopsy of the thyroid. Can Med Assoc J 167:491–495Google Scholar
  22. 22.
    Chapman B, Jost G, Pas R. v. d. (2008) Using OpenMP: portable shared memory parallel programming. MIT, Cambridge, MAGoogle Scholar
  23. 23.
    Message Passing Interface Forum (2008) MPI: A Message Passing Interface Standard version 2.1.Google Scholar
  24. 24.
    Shah S, Thigpen J, Merchant F, Castleman K (2006) Photometric calibration for automated multispectral imaging of biological samples. In: Proceedings of 1st workshop on microscopic image analysis with applications in biology (in conjunction with MICCAI, Copenhagen), 27–33Google Scholar
  25. 25.
    Serra J (1982) Image analysis and mathematical morphology. Academic, LondonMATHGoogle Scholar
  26. 26.
    Vincent L, Soille P (1991) Watersheds in digital spaces: An efficient algorithm based on immersion simulations. IEEE Trans Pattern Anal Mach Intell 13:583–598CrossRefGoogle Scholar
  27. 27.
    Hartigan JA, Wong MA (1979) A K-means clustering algorithm. Appl Stat 28:100–108MATHCrossRefGoogle Scholar
  28. 28.
    Faugeras OD, Pratt WK (1980) Decorrelation methods of texture feature extraction. IEEE Trans Pattern Anal Mach Intell 2:323–332CrossRefGoogle Scholar
  29. 29.
    Bamford P, Lovell B (1998) Unsupervised cell nucleus segmentation with active contours. Signal Process 71:203–213MATHCrossRefGoogle Scholar
  30. 30.
    Kurugollu F, Sankur B (1998) Color cell image segmentation using pyramidal constraint satisfaction neural network. IAPR Workshop Mach Vis Appl 85–88Google Scholar
  31. 31.
    Lu J, Li S, Yang J, Liu L, He A, Liu K (1998) Lung cancer cell recognition based on multiple color space. Proc SPIE 3522:378–386CrossRefGoogle Scholar
  32. 32.
    Pardo XM, Cabello D (2000) Biomedical active segmentation guided by edge saliency. Pattern Recognit Lett 21:559–572CrossRefGoogle Scholar
  33. 33.
    Ablameyko S, Nedzved A, Lagunovsky D, Patsko O, Kirillov V (2001) Cell image segmentation: review of approaches. Proc ICPR 2:26–34Google Scholar
  34. 34.
    Pal NR, Pal SK (1993) A review on image segmentation techniques. Pattern Recognit 26: 1277–1294CrossRefGoogle Scholar
  35. 35.
    Manjunath BS, Ma WY (1996) Texture features for browsing and retrieval of image data. IEEE Trans Pattern Anal Mach Intell (PAMI – Special issue on Digital Libraries) 18:837–842Google Scholar
  36. 36.
    Frigo M, Johnson SG (2005) The design and implementation of FFTW3. Proc IEEE 93: 216–231CrossRefGoogle Scholar
  37. 37.
    Malony AD, Shende S, Bell R, Li K, Li L, Trebon N (2004) Advances in the TAU performance system. Perform Anal Grid Comput 129–144Google Scholar
  38. 38.
    Gabriel E, Venkatesan V, Shah S (2008) Towards high performance cell segmentation in multispectral fine needle aspiration cytology of thyroid lesions. In: 11th international conference on medical image computing and computer assisted intervention, workshop on high-performance medical image computing and computer aided intervention, New York, NY, USAGoogle Scholar
  39. 39.
    Gabriel E, Fagg GE, Bosilca G, Angskun T, Dongarra JJ, Squyres JM, Sahay V, Kambadur P, Barrett B, Lumsdaine A, Castain RH, Daniel DJ, Graham RL, Woodall TS (2004) Open MPI: goals, concept, and design of a next generation mpi implementation. In: Proceedings, 11th European PVM/MPI Users’ Group Meeting, Budapest, HungaryGoogle Scholar
  40. 40.
    Mazzaferi EL (1992) Thyroid cancer in thyroid nodules: finding a needle in the haystack. Am J Med 93:359–362CrossRefGoogle Scholar
  41. 41.
    Mazzaferi EL (1993) Management of a solitary thyroid nodule. N Engl J Med 328:553–559CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of HoustonHoustonUSA

Personalised recommendations