Diagnosis of Hirschsprung disease by analyzing acetylcholinesterase staining using artificial intelligence.
aganglionosis
digital pathology
machine learning
rectal biopsy
Journal
Journal of pediatric gastroenterology and nutrition
ISSN: 1536-4801
Titre abrégé: J Pediatr Gastroenterol Nutr
Pays: United States
ID NLM: 8211545
Informations de publication
Date de publication:
09 Aug 2024
09 Aug 2024
Historique:
revised:
15
07
2024
received:
13
03
2024
accepted:
21
07
2024
medline:
9
8
2024
pubmed:
9
8
2024
entrez:
9
8
2024
Statut:
aheadofprint
Résumé
Classical Hirschsprung disease (HD) is defined by the absence of ganglion cells in the rectosigmoid colon. The diagnosis is made from rectal biopsy, which reveals the aganglionosis and the presence of cholinergic hyperinnervation. However, depending on the method of rectal biopsy, the quality of the specimens and the related diagnostic accuracy varies substantially. To facilitate and objectify the diagnosis of HD, we investigated whether software-based identification of cholinergic hyperinnervation in digitalized histopathology slides is suitable for distinguishing healthy individuals from affected individuals. N = 190 samples of 112 patients who underwent open surgical rectal biopsy at our pediatric surgery center between 2009 and 2019 were included in this study. Acetylcholinesterase (AChE) stained slides of these samples were collected and digitalized via slide scanning and analyzed using two digital imaging software programs (HALO, QuPath). The AChE-positive staining area in the mucosal layers of the intestinal wall was determined. In the next step machine learning was employed to identify patterns of cholinergic hyperinnervation. The area of AChE-positive staining was greater in HD patients compared to healthy individuals (p < 0.0001). Artificial intelligence-based assessment of parasympathetic hyperinnervation identified Hirschsprung disease with a high precision (area under the curve [AUC] 0.96). The accuracy of the prediction model increased when nonrectal samples were excluded (AUC 0.993). Software-assisted machine-learning analysis of AChE staining is suitable to improve the diagnostic accuracy of Hirschsprung disease.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Subventions
Organisme : None
Informations de copyright
© 2024 The Author(s). Journal of Pediatric Gastroenterology and Nutrition published by Wiley Periodicals LLC on behalf of European Society for Pediatric Gastroenterology, Hepatology, and Nutrition and North American Society for Pediatric Gastroenterology, Hepatology, and Nutrition.
Références
Montalva L, Cheng LS, Kapur R, et al. Hirschsprung disease. Nat Rev Dis Primers. 2023;9(1):54.
Meier‐Ruge W, Hunziker O, Tobler HJ, Walliser C. The pathophysiology of aganglionosis of the entire colon (Zuelzer‐Wilson syndrome). Morphometric investigations of the extent of sacral parasympathetic innervation of the circular muscles of the aganglionic colon. Beitr Pathol. 1972;147(3):228‐236.
Gosain A, Frykman PK, Cowles RA, et al. Guidelines for the diagnosis and management of Hirschsprung‐associated enterocolitis. Pediatr Surg Int. 2017;33(5):517‐521.
Badner JA, Sieber WK, Garver KL, Chakravarti A. A genetic study of Hirschsprung disease. Am J Hum Genet. 1990;46(3):568‐580.
Best KE, Addor MC, Arriola L, et al. Hirschsprung's disease prevalence in Europe: a register based study. Birth Defects Res Pt A Clin Molec Teratol. 2014;100(9):695‐702.
Ambartsumyan L, Smith C, Kapur RP. Diagnosis of Hirschsprung disease. Pediatr Dev Pathol. 2020;23(1):8‐22.
Feichter S, Meier‐Ruge WA, Bruder E. The histopathology of gastrointestinal motility disorders in children. Semin Pediatr Surg. 2009;18(4):206‐211.
Setiadi JA, Dwihantoro A, Iskandar K, Heriyanto DS, Gunadi S. The utility of the hematoxylin and eosin staining in patients with suspected Hirschsprung disease. BMC Surg. 2017;17(1):71.
Boston VE, Dale G, Riley KWA. Diagnosis of Hirschsprung's disease by quantitative biochemical assay of acetylcholinesterase in rectal tissue. Lancet. 1975;306(7942):951‐953.
Yoshimaru K, Yanagi Y, Obata S, et al. Acetylcholinesterase staining for the pathological diagnosis of Hirschsprung's disease. Surg Today. 2021;51(2):181‐186.
Barshack I, Fridman E, Goldberg I, Chowers Y, Kopolovic J. The loss of calretinin expression indicates aganglionosis in Hirschsprung's disease. J Clin Pathol. 2004;57(7):712‐716.
Friedmacher F, Puri P. Rectal suction biopsy for the diagnosis of Hirschsprung's disease: a systematic review of diagnostic accuracy and complications. Pediatr Surg Int. 2015;31(9):821‐830.
Vervloet G, De Backer A, Heyman S, et al. Rectal biopsy for Hirschsprung's disease: A multicentre study involving biopsy technique, pathology and complications. Children. 2023;10(9):1488.
Friedmacher F, Puri P. Current practice patterns of rectal suction biopsy in the diagnostic work‐up of Hirschsprung's disease: results from an international survey. Pediatr Surg Int. 2016;32(8):717‐722.
Bjørn N, Rasmussen L, Qvist N, Detlefsen S, Ellebæk MB. Full‐thickness rectal biopsy in children suspicious for Hirschsprung's disease is safe and yields a low number of insufficient biopsies. J Pediatr Surg. 2018;53(10):1942‐1944.
Niazi MKK, Parwani AV, Gurcan MN. Digital pathology and artificial intelligence. Lancet Oncol. 2019;20(5):e253‐e261.
Shmatko A, Ghaffari Laleh N, Gerstung M, Kather JN. Artificial intelligence in histopathology: enhancing cancer research and clinical oncology. Nature Cancer. 2022;3(9):1026‐1038.
Greenberg A, Aizic A, Zubkov A, Borsekofsky S, Hagege RR, Hershkovitz D. Automatic ganglion cell detection for improving the efficiency and accuracy of Hirschprung disease diagnosis. Sci Rep. 2021;11(1):3306.
Bankhead P, Loughrey MB, Fernández JA, et al. QuPath: open source software for digital pathology image analysis. Sci Rep. 2017;7(1):16878.
Kyrklund K, Sloots CEJ, de Blaauw I, et al. ERNICA guidelines for the management of rectosigmoid Hirschsprung's disease. Orphanet J Rare Dis. 2020;15(1):164.
Hwang S, Kapur RP. Advances and pitfalls in the diagnosis of Hirschsprung disease. Surg Pathol Clin. 2020;13(4):567‐579.
Holland SK, Ramalingam P, Podolsky RH, Reid‐Nicholson MD, Lee JR. Calretinin immunostaining as an adjunct in the diagnosis of Hirschsprung disease. Ann Diagn Pathol. 2011;15(5):323‐328.
Kawana T, Nada O, Ikeda K. An immunohistochemical study of glial fibrillary acidic (GFA) protein and S‐100 protein in the colon affected by Hirschsprung's disease. Acta Neuropathol. 1988;76(2):159‐165.
Beschorner R, Mittelbronn M, Bekure K, Meyermann R. Problems in fast intraoperative diagnosis in Hirschsprung's disease. Folia Neuropathol. 2004;42(4):191‐195.
Moore SW, Johnson G. Acetylcholinesterase in Hirschsprung's disease. Pediatr Surg Int. 2005;21(4):255‐263.
Elema JD, de Vries JA, Vos LJM. Intensity and proximal extension of acetylcholinesterase activity in the mucosa of the rectosigmoid in Hirschsprung's disease. J Pediatr Surg. 1973;8(3):361‐368.
Kapur RP, Reed RC, Finn LS, Patterson K, Johanson J, Rutledge JC. Calretinin immunohistochemistry versus acetylcholinesterase histochemistry in the evaluation of suction rectal biopsies for Hirschsprung disease. Pediatr Dev Pathol. 2009;12(1):6‐15.
Beltman L, Windster JD, Roelofs JJTH, van der Voorn JP, Derikx JPM, Bakx R. Diagnostic accuracy of calretinin and acetylcholinesterase staining of rectal suction biopsies in Hirschsprung disease examined by unexperienced pathologists. Virchows Arch. 2022;481(2):245‐252.
Huang S, Qian X, Cheng Y, Guo W, Zhou Z, Dai Y. Machine learning‐based quantitative analysis of barium enema and clinical features for early diagnosis of short‐segment Hirschsprung disease in neonate. J Pediatr Surg. 2021;56(10):1711‐1717.
Schilling F, Geppert CE, Strehl J, et al. Digital pathology imaging and computer‐aided diagnostics as a novel tool for standardization of evaluation of aganglionic megacolon (Hirschsprung disease) histopathology. Cell Tissue Res. 2019;375(2):371‐381.
Duci M, Magoni A, Santoro L, et al. Enhancing diagnosis of Hirschsprung's disease using deep learning from histological sections of post pull‐through specimens: preliminary results. Pediatr Surg Int. 2023;40(1):12.
Mondal R, Sandhu YK, Kamalia VM, et al. Measurement of Aβ amyloid plaques and tau protein in postmortem human Alzheimer's disease brain by autoradiography using [18F]Flotaza, [125I]IBETA, [124/125I]IPPI and immunohistochemistry analysis using QuPath. Biomedicines. 2023;11(4):1033.
Porter R, Din S, Bankhead P, Oniscu A, Arends M. QuPath algorithm accurately identifies MLH1‐deficient inflammatory bowel disease‐associated colorectal cancers in a tissue microarray. Diagnostics. 2023;13(11):1890.
Zheng Q, Jiang Z, Ni X, et al. Machine learning quantified tumor‐stroma ratio is an independent prognosticator in muscle‐invasive bladder cancer. Int J Mol Sci. 2023;24(3):2746.
Zhdanovich Y, Ackermann J, Wild PJ, et al. Evaluation of automatic discrimination between benign and malignant prostate tissue in the era of high precision digital pathology. BMC Bioinform. 2023;24(1):1.
Martino F, Varricchio S, Russo D, et al. A machine‐learning approach for the assessment of the proliferative compartment of solid tumors on hematoxylin‐eosin‐stained sections. Cancers. 2020;12(5):1344.
Demircioğlu A. Measuring the bias of incorrect application of feature selection when using cross‐validation in radiomics. Insights Imaging. 2021;12(1):172.