EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DLLabelsCT: Annotation tool using deep transfer learning to assist in creating new datasets from abdominal computed tomography scans, case study: Pancreas

Henrik Mustonen iD, Antti Isosalo, Minna Nortunen, Mika Nevalainen, Miika T Nieminen, Heikki Huhta

PLOS ONE · 2024

DOI: 10.1371/journal.pone.0313126 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, 2024. Verfasst von Henrik Mustonen und 5 weiteren Autor:innen. Beteiligte Einrichtung: Research Unit of Health Sciences and Technology, Faculty of Medicine, University of Oulu, Oulu, Finland. Hauptthemen laut MEDLINE: Deep Learning, Pancreas, Tomography, X-Ray Computed, Neural Networks, Computer. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Suomen Kulttuurirahasto, Mary och Georg C. Ehrnrooths Stiftelse, Suomen Lääketieteen Säätiö.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The utilization of artificial intelligence (AI) is expanding significantly within medical research and, to some extent, in clinical practice. Deep learning (DL) applications, which use large convolutional neural networks (CNN), hold considerable potential, especially in optimizing radiological evaluations. However, training DL algorithms to clinical standards requires extensive datasets, and their processing is labor-intensive. In this study, we developed an annotation tool named DLLabelsCT that utilizes CNN models to accelerate the image analysis process. To validate DLLabelsCT, we trained a CNN model with a ResNet34 encoder and a UNet decoder to segment the pancreas on an open-access dataset and used the DL model to assist in annotating a local dataset, which was further used to refine the model. DLLabelsCT was also tested on two external testing datasets. The tool accelerates annotation by 3.4 times compared to a completely manual annotation method. Out of 3,715 CT scan slices in the testing datasets, 50% did not require editing when reviewing the segmentations made by the ResNet34-UNet model, and the mean and standard deviation of the Dice similarity coefficient was 0.82±0.24. DLLabelsCT is highly accurate and significantly saves time and resources. Furthermore, it can be easily modified to support other deep learning models for other organs, making it an efficient tool for future research involving larger datasets.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningPancreasTomography, X-Ray ComputedNeural Networks, ComputerHumansImage Processing, Computer-AssistedAlgorithms

Autor:innen und Institutionen

  • Research Unit of Health Sciences and Technology, Faculty of Medicine, University of Oulu, Oulu, Finland.
  • Research Unit of Translational Medicine, Oulu University Hospital, Oulu, Finland.
  • Department of Surgery, Oulu University Hospital, Oulu, Finland.
  • Department of Diagnostic Radiology, Oulu University Hospital, Oulu, Finland.

ORCID-Profile: Henrik Mustonen

Förderung

  • Suomen Kulttuurirahasto
  • Mary och Georg C. Ehrnrooths Stiftelse
  • Suomen Lääketieteen Säätiö
  • Sigrid Juséliuksen Säätiö
  • Teknologiateollisuuden 100-Vuotisjuhlasäätiö
  • Jane ja Aatos Erkon Säätiö

Zitieren

APA

Mustonen, H., Isosalo, A., Nortunen, M., Nevalainen, M., Nieminen, M. T., & Huhta, H. (2024). DLLabelsCT: Annotation tool using deep transfer learning to assist in creating new datasets from abdominal computed tomography scans, case study: Pancreas. PLOS ONE. https://doi.org/10.1371/journal.pone.0313126

Vancouver

Mustonen H, Isosalo A, Nortunen M, Nevalainen M, Nieminen MT, Huhta H. DLLabelsCT: Annotation tool using deep transfer learning to assist in creating new datasets from abdominal computed tomography scans, case study: Pancreas. PLOS ONE. 2024. doi:10.1371/journal.pone.0313126

BibTeX
@article{Mustonen2024,
  author = {Mustonen, Henrik and Isosalo, Antti and Nortunen, Minna and Nevalainen, Mika and Nieminen, Miika T and Huhta, Heikki},
  title = {DLLabelsCT: Annotation tool using deep transfer learning to assist in creating new datasets from abdominal computed tomography scans, case study: Pancreas},
  journal = {PLOS ONE},
  year = {2024},
  doi = {10.1371/journal.pone.0313126}
}
Kostenlos starten →