EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning for Histopathological Assessment of Esophageal Adenocarcinoma Precursor Lesions

Michel Botros, Onno J de Boer, Bryan Cardenas, Erik J Bekkers, Marnix Jansen, Myrtle J van der Wel, Clara I Sánchez, Sybren L Meijer

Modern Pathology · 2024

DOI: 10.1016/j.modpat.2024.100531 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Modern Pathology, 2024. Verfasst von Michel Botros und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pathology, Amsterdam University Medical Centers, Amsterdam, The Netherlands; Department of Biomedical Engineering and Physics, Amsterda…. Hauptthemen laut MEDLINE: Esophageal Neoplasms, Deep Learning, Adenocarcinoma, Barrett Esophagus. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Maag Lever Darm Stichting.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Histopathological assessment of esophageal biopsies is a key part in the management of patients with Barrett esophagus (BE) but prone to observer variability and reliable diagnostic methods are needed. Artificial intelligence (AI) is emerging as a powerful tool for aided diagnosis but often relies on abstract test and validation sets while real-world behavior is unknown. In this study, we developed a 2-stage AI system for histopathological assessment of BE-related dysplasia using deep learning to enhance the efficiency and accuracy of the pathology workflow. The AI system was developed and trained on 290 whole-slide images (WSIs) that were annotated at glandular and tissue levels. The system was designed to identify individual glands, grade dysplasia, and assign a WSI-level diagnosis. The proposed method was evaluated by comparing the performance of our AI system with that of a large international and heterogeneous group of 55 gastrointestinal pathologists assessing 55 digitized biopsies spanning the complete spectrum of BE-related dysplasia. The AI system correctly graded 76.4% of the WSIs, surpassing the performance of 53 out of the 55 participating pathologists. Furthermore, the receiver-operating characteristic analysis showed that the system's ability to predict the absence (nondysplastic BE) versus the presence of any dysplasia was with an area under the curve of 0.94 and a sensitivity of 0.92 at a specificity of 0.94. These findings demonstrate that this AI system has the potential to assist pathologists in assessment of BE-related dysplasia. The system's outputs could provide a reliable and consistent secondary diagnosis in challenging cases or be used for triaging low-risk nondysplastic biopsies, thereby reducing the workload of pathologists and increasing throughput.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Esophageal NeoplasmsDeep LearningAdenocarcinomaBarrett EsophagusPrecancerous ConditionsHumansImage Interpretation, Computer-AssistedBiopsy

Stichwörter der Autor:innen

Barrett esophagusartificial intelligencedeep learningesophageal adenocarcinoma

Autor:innen und Institutionen

  • Department of Pathology, Amsterdam University Medical Centers, Amsterdam, The Netherlands; Department of Biomedical Engineering and Physics, Amsterdam University Medical Centers, Amsterdam, The Netherlands; Quantitative…
  • Department of Pathology, Amsterdam University Medical Centers, Amsterdam, The Netherlands.
  • Department of Pathology, Amsterdam University Medical Centers, Amsterdam, The Netherlands; Amsterdam Machine Learning Lab, Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands.
  • Amsterdam Machine Learning Lab, Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands.
  • Research Department of Pathology, Cancer Institute, University College London, London, United Kingdom.
  • Department of Biomedical Engineering and Physics, Amsterdam University Medical Centers, Amsterdam, The Netherlands; Quantitative Healthcare Analysis Group, Informatics Institute, University of Amsterdam, Amsterdam, The…

Förderung

  • Maag Lever Darm Stichting

Zitieren

APA

Botros, M., de Boer, O. J., Cardenas, B., Bekkers, E. J., Jansen, M., van der Wel, M. J., Sánchez, C. I., & Meijer, S. L. (2024). Deep Learning for Histopathological Assessment of Esophageal Adenocarcinoma Precursor Lesions. Modern Pathology. https://doi.org/10.1016/j.modpat.2024.100531

Vancouver

Botros M, de Boer OJ, Cardenas B, Bekkers EJ, Jansen M, van der Wel MJ, et al. Deep Learning for Histopathological Assessment of Esophageal Adenocarcinoma Precursor Lesions. Modern Pathology. 2024. doi:10.1016/j.modpat.2024.100531

BibTeX
@article{Botros2024,
  author = {Botros, Michel and de Boer, Onno J and Cardenas, Bryan and Bekkers, Erik J and Jansen, Marnix and van der Wel, Myrtle J and Sánchez, Clara I and Meijer, Sybren L},
  title = {Deep Learning for Histopathological Assessment of Esophageal Adenocarcinoma Precursor Lesions},
  journal = {Modern Pathology},
  year = {2024},
  doi = {10.1016/j.modpat.2024.100531}
}
Kostenlos starten →