Advertisement

Cell and Tissue Research

, Volume 375, Issue 2, pp 371–381 | Cite as

Digital pathology imaging and computer-aided diagnostics as a novel tool for standardization of evaluation of aganglionic megacolon (Hirschsprung disease) histopathology

  • Florian Schilling
  • Carol E. Geppert
  • Johanna Strehl
  • Arndt Hartmann
  • Stefanie Kuerten
  • Axel Brehmer
  • Samir JabariEmail author
Regular Article

Abstract

Based on a recently introduced immunohistochemical panel (Bachmann et al. 2015) for aganglionic megacolon (AM), also known as Hirschsprung disease, histopathological diagnosis, we evaluated whether the use of digital pathology and ‘machine learning’ could help to obtain a reliable diagnosis. Slides were obtained from 31 specimens of 27 patients immunohistochemically stained for MAP2, calretinin, S100β and GLUT1. Slides were digitized by whole slide scanning. We used a Definiens Developer Tissue Studios as software for analysis. We configured necessary parameters in combination with ‘machine learning’ to identify pathological aberrations. A significant difference between AM- and non-AM-affected tissues was found for calretinin (AM 0.55% vs. non-AM 1.44%) and MAP2 (AM 0.004% vs. non-AM 0.07%) staining measurements and software-based evaluations. In contrast, S100β and GLUT1 staining measurements and software-based evaluations showed no significant differences between AM- and non-AM-affected tissues. However, no difference was found in comparison of suction biopsies with resections. Applying machine learning via an ensemble voting classifier, we achieved an accuracy of 87.5% on the test set. Automated diagnosis of AM by applying digital pathology on immunohistochemical panels was successful for calretinin and MAP2, whereas S100β and GLUT1 were not effective in diagnosis. Our method suggests that software-based approaches are capable of diagnosing AM. Our future challenge will be the improvement of efficiency by reduction of the time-consuming need for large pre-labelled training data. With increasing technical improvement, especially in unsupervised training procedures, this method could be helpful in the future.

Keywords

Calretinin Digital pathology Hirschsprung disease Immunohistochemistry Machine learning 

Notes

Acknowledgements

The present work was performed in fulfilment of the requirements of the Friedrich-Alexander Universität Erlangen-Nürnberg (FAU) for obtaining the degree ‘Dr. med.dent’ of Florian Schilling. We would like to thank Nicole Fuhrich and Definines Support for their excellent technical assistance.

Compliance with ethical standards

The use of the FFPE materials was approved by the local ethics committee (approval number: 85_12b, date 04/19/2012).

Conflict and interest statement

The authors declare that they have no conflict of interests.

Informed consent

Informed consent was obtained from all individual participants for whom identifying information is included in this article.

Supplementary material

441_2018_2911_MOESM1_ESM.docx (19 kb)
ESM 1 (DOCX 19 kb)
441_2018_2911_MOESM2_ESM.docx (16 kb)
ESM 2 (DOCX 16 kb)
441_2018_2911_MOESM3_ESM.docx (22 kb)
ESM 3 (DOCX 21 kb)
441_2018_2911_MOESM4_ESM.docx (17 kb)
ESM 4 (DOCX 17 kb)

References

  1. Aldridge RT, Campbell PE (1968) Ganglion cell distribution in the normal rectum and anal canal. A basis for the diagnosis of Hirschsprung’s disease by anorectal biopsy. J Pediatr Surg 3:475–490CrossRefGoogle Scholar
  2. Andrassy RJ, Isaacs H, Weitzman JJ (1981) Rectal suction biopsy for the diagnosis of Hirschsprung’s disease. Ann Surg 193:419–424CrossRefGoogle Scholar
  3. Bachmann L, Besendorfer M, Carbon R, Lux P, Agaimy A, Hartmann A, Rau TT (2015) Immunohistochemical panel for the diagnosis of Hirschsprung's disease using antibodies to MAP 2, calretinin, GLUT1 and S100. Histopathology 66:824–835CrossRefGoogle Scholar
  4. Badner JA, Sieber WK, Garver KL, Chakravarti A (1990) A genetic study of Hirschsprung disease. Am J Hum Genet 46:568–580Google Scholar
  5. Barnes PR, Lennard-Jones JE, Hawley PR, Todd IP (1986) Hirschsprung’s disease and idiopathic megacolon in adults and adolescents. Gut 27:534–541CrossRefGoogle Scholar
  6. Barshack I, Fridman E, Goldberg I, Chowers Y, Kopolovic J (2004) The loss of calretinin expression indicates aganglionosis in Hirschsprung’s disease. J Clin Pathol 57:712–716CrossRefGoogle Scholar
  7. Bekkali N, Hamers SL, Schipperus MR, Reitsma JB, Valerio PG, Van Toledo L, Benninga MA (2008) Duration of meconium passage in preterm and term infants. Arch Dis Child Fetal Neonatal Ed 93:F376–F379CrossRefGoogle Scholar
  8. Beuscher N, Jabari S, Strehl J, Neuhuber W, Brehmer A (2014) What neurons hide behind calretinin immunoreactivity in the human gut? Histochem Cell Biol 141:393–405CrossRefGoogle Scholar
  9. Bodian M, Carter OO (1963) A family study of Hirschsprung’s disease. Ann Hum Genet 26:261–277CrossRefGoogle Scholar
  10. Brehmer A, Rupprecht H, Neuhuber W (2010) Two submucosal nerve plexus in human intestines. Histochem Cell Biol 133:149–161CrossRefGoogle Scholar
  11. Burkardt DD, Graham JM Jr, Short SS, Frykman PK (2014) Advances in Hirschsprung disease genetics and treatment strategies: an update for the primary care pediatrician. Clin Pediatr (Phila) 53:71–81CrossRefGoogle Scholar
  12. Burtelow MA, Longacre TA (2009) Utility of microtubule associated protein-2 (MAP-2) immunohistochemistry for identification of ganglion cells in paraffin-embedded rectal suction biopsies. Am J Surg Pathol 33:1025–1030CrossRefGoogle Scholar
  13. Butler Tjaden NE, Trainor PA (2013) The developmental etiology and pathogenesis of Hirschsprung disease. Transl Res 162:1–15CrossRefGoogle Scholar
  14. Caceres A, Binder LI, Payne MR, Bender P, Rebhun L, Steward O (1984) Differential subcellular localization of tubulin and the microtubule-associated protein MAP 2 in brain tissue as revealed by immunocytochemistry with monoclonal hybridoma antibodies. J Neurosci 4:394–410CrossRefGoogle Scholar
  15. Clark DA (1977) Times of first void and first stool in 500 newborns. Pediatrics 60:457–459Google Scholar
  16. de Arruda Lourencao PL, Takegawa BK, Ortolan EV, Terra SA, Rodrigues MA (2013) A useful panel for the diagnosis of Hirschsprung disease in rectal biopsies: calretinin immunostaining and acetylcholinesterase histochesmistry. Ann Diagn Pathol 17:352–356CrossRefGoogle Scholar
  17. Definiens A (2015) Definiens Tissue Studio 4.3 User Guide. Defineins Documentation München, GermanyGoogle Scholar
  18. Deo RC (2015) Machine learning in medicine. Circulation 132:1920–1930CrossRefGoogle Scholar
  19. Dobbins WO 3rd, Bill AH Jr (1965) Diagnosis of Hirschsprung’s disease excluded by rectal suction biopsy. N Engl J Med 272:990–993CrossRefGoogle Scholar
  20. Duhamel B (1960) A new operation for the treatment of Hirschsprung’s disease. Arch Dis Child 35:38–39CrossRefGoogle Scholar
  21. Gonzalo DH, Plesec T (2013) Hirschsprung disease and use of calretinin in inadequate rectal suction biopsies. Arch Pathol Lab Med 137:1099–1102CrossRefGoogle Scholar
  22. Guinard-Samuel V, Bonnard A, De Lagausie P, Philippe-Chomette P, Alberti C, El Ghoneimi A, Peuchmaur M, Berrebi-Binczak D (2009) Calretinin immunohistochemistry: a simple and efficient tool to diagnose Hirschsprung disease. Mod Pathol 22:1379–1384CrossRefGoogle Scholar
  23. Harjai MM (2000) Hirschsprung’s disease: revisited. J Postgrad Med 46:52–54Google Scholar
  24. Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference, and prediction, Second Edition. NY Springer Science & Business Media New YorkGoogle Scholar
  25. Holland SK, Hessler RB, Reid-Nicholson MD, Ramalingam P, Lee JR (2010) Utilization of peripherin and S-100 immunohistochemistry in the diagnosis of Hirschsprung disease. Mod Pathol 23:1173–1179CrossRefGoogle Scholar
  26. Irshad H, Veillard A, Roux L, Racoceanu D (2014) Methods for nuclei detection, segmentation, and classification in digital histopathology: a review-current status and future potential. IEEE Rev Biomed Eng 7:97–114CrossRefGoogle Scholar
  27. Joosten K, Pruszczynski M, Severijnen RS, Festen C (1989) Causes of late complications in children operated on for Hirschsprung’s disease: a preliminary immunohistochemical investigation using polyclonal antibodies against S-100 protein. Z Kinderchir 44:213–215Google Scholar
  28. Kakita Y, Oshiro K, O'Briain DS, Puri P (2000) Selective demonstration of mural nerves in ganglionic and aganglionic colon by immunohistochemistry for glucose transporter-1: prominent extrinsic nerve pattern staining in Hirschsprung disease. Arch Pathol Lab Med 124:1314–1319Google Scholar
  29. Kapur RP (2006) Can we stop looking? Immunohistochemistry and the diagnosis of Hirschsprung disease. Am J Clin Pathol 126:9–12CrossRefGoogle Scholar
  30. Kapur RP (2014) Calretinin-immunoreactive mucosal innervation in very short-segment Hirschsprung disease: a potentially misleading observation. Pediatr Dev Pathol 17:28–35CrossRefGoogle Scholar
  31. Kapur RP, Kennedy AJ (2012) Transitional zone pull through: surgical pathology considerations. Semin Pediatr Surg 21:291–301CrossRefGoogle Scholar
  32. Kapur RP, Reed RC, Finn LS, Patterson K, Johanson J, Rutledge JC (2009) Calretinin immunohistochemistry versus acetylcholinesterase histochemistry in the evaluation of suction rectal biopsies for Hirschsprung disease. Pediatr Dev Pathol 12:6–15CrossRefGoogle Scholar
  33. Koletzko S, Jesch I, Faus-Kebetaler T, Briner J, Meier-Ruge W, Muntefering H, Coerdt W, Wessel L, Keller KM, Nutzenadel W, Schmittenbecher P, Holschneider A, Sacher P (1999) Rectal biopsy for diagnosis of intestinal neuronal dysplasia in children: a prospective multicentre study on interobserver variation and clinical outcome. Gut 44:853–861CrossRefGoogle Scholar
  34. Kramer K, da Silveira AB, Jabari S, Kressel M, Raab M, Brehmer A (2011) Quantitative evaluation of neurons in the mucosal plexus of adult human intestines. Histochem Cell Biol 136:1–9CrossRefGoogle Scholar
  35. Linder N, Konsti J, Turkki R, Rahtu E, Lundin M, Nordling S, Haglund C, Ahonen T, Pietikainen M, Lundin J (2012) Identification of tumor epithelium and stroma in tissue microarrays using texture analysis. Diagn Pathol 7:22CrossRefGoogle Scholar
  36. Lopez-Alonso M, Ribas J, Hernandez A, Anguita FA, Gomez de Terreros I, Martinez-Caro A (1995) Efficiency of the anorectal manometry for the diagnosis of Hirschsprung’s disease in the newborn period. Eur J Pediatr Surg 5:160–163CrossRefGoogle Scholar
  37. Madabhushi A, Lee G (2016) Image analysis and machine learning in digital pathology: challenges and opportunities. Med Image Anal 33:170–175CrossRefGoogle Scholar
  38. Martin LW, Altemeier WA (1962) Clinical experience with a new operation (modified Duhamel procedure) for Hirschsprung’s disease. Ann Surg 156:678–681CrossRefGoogle Scholar
  39. Martucciello G (2008) Hirschsprung’s disease, one of the most difficult diagnoses in pediatric surgery: a review of the problems from clinical practice to the bench. Eur J Pediatr Surg 18:140–149CrossRefGoogle Scholar
  40. Meier-Ruge W, Lutterbeck PM, Herzog B, Morger R, Moser R, Scharli A (1972) Acetylcholinesterase activity in suction biopsies of the rectum in the diagnosis of Hirschsprung’s disease. J Pediatr Surg 7:11–17CrossRefGoogle Scholar
  41. Murphy F, Puri P (2005) New insights into the pathogenesis of Hirschsprung’s associated enterocolitis. Pediatr Surg Int 21:773–779CrossRefGoogle Scholar
  42. Pratap A, Gupta DK, ea TA (2007) Applicationofaplainab- dominal radiograph transition zone (PARTZ) in Hirschsprung’s disease. BMC Pediatr 7:5CrossRefGoogle Scholar
  43. Qualman SJ, Jaffe R, Bove KE, Monforte-Munoz H (1999) Diagnosis of hirschsprung disease using the rectal biopsy: multi-institutional survey. Pediatr Dev Pathol 2:588–596CrossRefGoogle Scholar
  44. Sarnat HB, Seagram GF, Trevenen CL, Rubin SZ (1985) A fluorochromic stain for nucleic acids to demonstrate submucosal and myenteric neurons in Hirschsprung’s disease. Am J Clin Pathol 83:722–725CrossRefGoogle Scholar
  45. Szylberg L, Marszalek A (2014) Diagnosis of Hirschsprung’s disease with particular emphasis on histopathology. A systematic review of current literature. Prz Gastroenterol 9:264–269Google Scholar
  46. Taguchi T, Tanaka K, Ikeda K (1985) Immunohistochemical study of neuron specific enolase and S-100 protein in Hirschsprung’s disease. Virchows Arch A Pathol Anat Histopathol 405:399–409CrossRefGoogle Scholar
  47. Volpe A, Alaggio R, Midrio P, Iaria L, Gamba P (2013) Calretinin, beta-tubulin immunohistochemistry, and submucosal nerve trunks morphology in Hirschsprung disease: possible applications in clinical practice. J Pediatr Gastroenterol Nutr 57:780–787CrossRefGoogle Scholar
  48. Wang H, Cruz-Roa A, Basavanhally A, Gilmore H, Shih N, Feldman M, Tomaszewski J, Gonzalez F, Madabhushi A (2014) Mitosis detection in breast cancer pathology images by combining handcrafted and convolutional neural network features. J Med Imaging (Bellingham) 1:034003CrossRefGoogle Scholar
  49. Wedel T, Roblick U, Gleiss J, Schiedeck T, Bruch HP, Kuhnel W, Krammer HJ (1999) Organization of the enteric nervous system in the human colon demonstrated by wholemount immunohistochemistry with special reference to the submucous plexus. Ann Anat 181:327–337CrossRefGoogle Scholar
  50. Yang WI, Oh JT (2013) Calretinin and microtubule-associated protein-2 (MAP-2) immunohistochemistry in the diagnosis of Hirschsprung’s disease. J Pediatr Surg 48:2112–2117CrossRefGoogle Scholar
  51. Yanlei H, Anupama B, Shan Z, Xianmin X, Lian C (2011) The expression of enteric nerve markers and nerve innervation in total colonic aganglionosis. Int J Surg Pathol 19:303–308CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  • Florian Schilling
    • 1
    • 2
  • Carol E. Geppert
    • 2
  • Johanna Strehl
    • 2
  • Arndt Hartmann
    • 2
  • Stefanie Kuerten
    • 1
  • Axel Brehmer
    • 1
  • Samir Jabari
    • 1
    • 2
    Email author
  1. 1.Institute of Anatomy and Cell BiologyFriedrich-Alexander-Universität Erlangen-NürnbergErlangenGermany
  2. 2.Institute of PathologyFriedrich-Alexander-Universität Erlangen-NürnbergErlangenGermany

Personalised recommendations