EUVIMEDEUVIMED entdecken
Crossref

Layer-selective deep representation to improve esophageal cancer classification

Luis A Souza, Leandro A Passos, Marcos Cleison S Santana, Robert Mendel, David Rauber, Alanna Ebigbo, Andreas Probst, Helmut Messmann, João Paulo Papa, Christoph Palm

Medical & Biological Engineering & Computing · 2024

DOI: 10.1007/s11517-024-03142-8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical & Biological Engineering & Computing, 2024. Verfasst von Luis A Souza und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Informatics, Espírito Santo Federal University, Vitória, Brazil. la.souza@inf.ufes.br. Hauptthemen laut MEDLINE: Esophageal Neoplasms, Deep Learning, Barrett Esophagus, Adenocarcinoma. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: Alexander von Humboldt-Stiftung, Conselho Nacional de Desenvolvimento Científico e Tecnológico, Conselho Nacional de Desenvolvimento Científico e Tecnológic.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Even though artificial intelligence and machine learning have demonstrated remarkable performances in medical image computing, their accountability and transparency level must be improved to transfer this success into clinical practice. The reliability of machine learning decisions must be explained and interpreted, especially for supporting the medical diagnosis. For this task, the deep learning techniques' black-box nature must somehow be lightened up to clarify its promising results. Hence, we aim to investigate the impact of the ResNet-50 deep convolutional design for Barrett's esophagus and adenocarcinoma classification. For such a task, and aiming at proposing a two-step learning technique, the output of each convolutional layer that composes the ResNet-50 architecture was trained and classified for further definition of layers that would provide more impact in the architecture. We showed that local information and high-dimensional features are essential to improve the classification for our task. Besides, we observed a significant improvement when the most discriminative layers expressed more impact in the training and classification of ResNet-50 for Barrett's esophagus and adenocarcinoma classification, demonstrating that both human knowledge and computational processing may influence the correct learning of such a problem.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Esophageal NeoplasmsDeep LearningBarrett EsophagusAdenocarcinomaHumansNeural Networks, ComputerAlgorithms

Stichwörter der Autor:innen

Barrett’s esophagus detectionConvolutional neural networksDeep learningMultistep training

Autor:innen und Institutionen

  • Department of Informatics, Espírito Santo Federal University, Vitória, Brazil. la.souza@inf.ufes.br.
  • Regensburg Medical Image Computing (ReMIC), Ostbayerische Technische Hochschule Regensburg (OTH Regensburg), Regensburg, Germany. la.souza@inf.ufes.br.
  • CMI Lab, School of Engineering and Informatics, University of Wolverhampton, Wolverhampton, UK.
  • Department of Computing, São Paulo State University, Bauru, Brazil.
  • Regensburg Medical Image Computing (ReMIC), Ostbayerische Technische Hochschule Regensburg (OTH Regensburg), Regensburg, Germany.
  • Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany.

Förderung

  • Alexander von Humboldt-Stiftung
  • Conselho Nacional de Desenvolvimento Científico e Tecnológico
  • Conselho Nacional de Desenvolvimento Científico e Tecnológic
  • Fundação de Amparo à Pesquisa do Estado de São Paulo
  • Engineering and Physical Sciences Research Council

Zitieren

APA

Souza, L. A., Passos, L. A., Santana, M. C. S., Mendel, R., Rauber, D., Ebigbo, A., Probst, A., Messmann, H., Papa, J. P., & Palm, C. (2024). Layer-selective deep representation to improve esophageal cancer classification. Medical & Biological Engineering & Computing. https://doi.org/10.1007/s11517-024-03142-8

Vancouver

Souza LA, Passos LA, Santana MCS, Mendel R, Rauber D, Ebigbo A, et al. Layer-selective deep representation to improve esophageal cancer classification. Medical & Biological Engineering & Computing. 2024. doi:10.1007/s11517-024-03142-8

BibTeX
@article{Souza2024,
  author = {Souza, Luis A and Passos, Leandro A and Santana, Marcos Cleison S and Mendel, Robert and Rauber, David and Ebigbo, Alanna and Probst, Andreas and Messmann, Helmut and Papa, João Paulo and Palm, Christoph},
  title = {Layer-selective deep representation to improve esophageal cancer classification},
  journal = {Medical & Biological Engineering & Computing},
  year = {2024},
  doi = {10.1007/s11517-024-03142-8}
}
Kostenlos starten →