EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Towards Building a Trustworthy Deep Learning Framework for Medical Image Analysis

Kai Ma, Siyuan He, Grant Sinha, Ashkan Ebadi iD, Adrian Florea, Stéphane Tremblay, Alexander Wong, Pengcheng Xi iD

Sensors · 2023

DOI: 10.3390/s23198122 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Kai Ma und 7 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada. Hauptthemen laut MEDLINE: COVID-19, Deep Learning, Melanoma. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Council Canada.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Computer vision and deep learning have the potential to improve medical artificial intelligence (AI) by assisting in diagnosis, prediction, and prognosis. However, the application of deep learning to medical image analysis is challenging due to limited data availability and imbalanced data. While model performance is undoubtedly essential for medical image analysis, model trust is equally important. To address these challenges, we propose TRUDLMIA, a trustworthy deep learning framework for medical image analysis, which leverages image features learned through self-supervised learning and utilizes a novel surrogate loss function to build trustworthy models with optimal performance. The framework is validated on three benchmark data sets for detecting pneumonia, COVID-19, and melanoma, and the created models prove to be highly competitive, even outperforming those designed specifically for the tasks. Furthermore, we conduct ablation studies, cross-validation, and result visualization and demonstrate the contribution of proposed modules to both model performance (up to 21%) and model trust (up to 5%). We expect that the proposed framework will support researchers and clinicians in advancing the use of deep learning for dealing with public health crises, improving patient outcomes, increasing diagnostic accuracy, and enhancing the overall quality of healthcare delivery.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

COVID-19Deep LearningMelanomaHumansArtificial IntelligenceBenchmarking

Stichwörter der Autor:innen

AUCCOVID-19computer-aided diagnosiscontrastive learningfeature learningself-supervised learningtrustworthiness

Autor:innen und Institutionen

  • Faculty of Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada.
  • Digital Technologies Research Centre, National Research Council of Canada, Ottawa, ON K1A 0R6, Canada.
  • Faculty of Mathematics, University of Waterloo, Waterloo, ON N2L 3G1, Canada.
  • Department of Emergency Medicine, McGill University, Montreal, QC H4A 3J1, Canada.

ORCID-Profile: Ashkan Ebadi, Pengcheng Xi

Förderung

  • National Research Council Canada

Zitieren

APA

Ma, K., He, S., Sinha, G., Ebadi, A., Florea, A., Tremblay, S., Wong, A., & Xi, P. (2023). Towards Building a Trustworthy Deep Learning Framework for Medical Image Analysis. Sensors. https://doi.org/10.3390/s23198122

Vancouver

Ma K, He S, Sinha G, Ebadi A, Florea A, Tremblay S, et al. Towards Building a Trustworthy Deep Learning Framework for Medical Image Analysis. Sensors. 2023. doi:10.3390/s23198122

BibTeX
@article{Ma2023,
  author = {Ma, Kai and He, Siyuan and Sinha, Grant and Ebadi, Ashkan and Florea, Adrian and Tremblay, Stéphane and Wong, Alexander and Xi, Pengcheng},
  title = {Towards Building a Trustworthy Deep Learning Framework for Medical Image Analysis},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23198122}
}
Kostenlos starten →