Computer-aided detection of early neoplastic lesions in Barrett’s Esophagus

F. van der Sommen, S. Zinger, W.L. Curvers, R. Bisschops, O. Pech, B. Weusten, J.J. Bergman, P.H.N. de With, E.J. Schoon

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

48 Citaten (Scopus)
5 Downloads (Pure)

Samenvatting

Background and study aims: Early neoplasia in Barrett’s esophagus is difficult to detect and often overlooked during Barrett’s surveillance. An automatic detection system could be beneficial, by assisting endoscopists with detection of early neoplastic lesions. The aim of this study was to assess the feasibility of a computer system to detect early neoplasia in Barrett’s esophagus.

Patients and methods: Based on 100 images from 44 patients with Barrett’s esophagus, a computer algorithm, which employed specific texture, color filters, and machine learning, was developed for the detection of early neoplastic lesions in Barrett’s esophagus. The evaluation by one endoscopist, who extensively imaged and endoscopically removed all early neoplastic lesions and was not blinded to the histological outcome, was considered the gold standard. For external validation, four international experts in Barrett’s neoplasia, who were blinded to the pathology results, reviewed all images.

Results: The system identified early neoplastic lesions on a per-image analysis with a sensitivity and specificity of 0.83. At the patient level, the system achieved a sensitivity and specificity of 0.86 and 0.87, respectively. A trade-off between the two performance metrics could be made by varying the percentage of training samples that showed neoplastic tissue.

Conclusion: The automated computer algorithm developed in this study was able to identify early neoplastic lesions with reasonable accuracy, suggesting that automated detection of early neoplasia in Barrett’s esophagus is feasible. Further research is required to improve the accuracy of the system and prepare it for real-time operation, before it can be applied in clinical practice.
Originele taal-2Engels
Artikelnummer617
Pagina's (van-tot)617-624
Aantal pagina's8
TijdschriftEndoscopy
Volume48
Nummer van het tijdschrift7
DOI's
StatusGepubliceerd - 2016

Vingerafdruk Duik in de onderzoeksthema's van 'Computer-aided detection of early neoplastic lesions in Barrett’s Esophagus'. Samen vormen ze een unieke vingerafdruk.

  • Pers/Media

    TU/e software helps recognizing early esophageal cancer

    Peter H.N. de With & Fons van der Sommen

    5/07/16

    1 item van Media-aandacht

    Pers / media: Vakinhoudelijk commentaar

    New detection method paves the way for 100% detection of esophageal cancer

    Peter H.N. de With & Fons van der Sommen

    5/07/16

    2 items van Media-aandacht

    Pers / media: Vakinhoudelijk commentaar

    Citeer dit

    van der Sommen, F., Zinger, S., Curvers, W. L., Bisschops, R., Pech, O., Weusten, B., Bergman, J. J., de With, P. H. N., & Schoon, E. J. (2016). Computer-aided detection of early neoplastic lesions in Barrett’s Esophagus. Endoscopy, 48(7), 617-624. [617]. https://doi.org/10.1055/s-0042-105284