EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access · CC BY 4.0

Minimally interactive segmentation of soft-tissue tumors on CT and MRI using deep learning

Douwe J Spaanderman, Martijn P A Starmans, Gonnie C M van Erp, David F Hanff, Judith H Sluijter, Anne-Rose W Schut, Geert J L H van Leenders, Cornelis Verhoef, Dirk J Grünhagen, Wiro J Niessen, Jacob J Visser, Stefan Klein

European Radiology · 19.11.2024 · 35 (5) · 2736-2745

DOI: 10.1007/s00330-024-11167-8 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift European Radiology, online erschienen am 19.11.2024. Verfasst von Douwe J Spaanderman und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, The Netherlands. d.spaanderman@erasmusmc.nl. Hauptthemen laut MEDLINE: Deep Learning, Magnetic Resonance Imaging, Tomography, X-Ray Computed, Soft Tissue Neoplasms. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Dutch national e-infrastructure with the support of the SURF Cooperative, Hanarth Fonds.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Segmentations are crucial in medical imaging for morphological, volumetric, and radiomics biomarkers. Manual segmentation is accurate but not feasible in clinical workflow, while automatic segmentation generally performs sub-par.

Purpose

To develop a minimally interactive deep learning-based segmentation method for soft-tissue tumors (STTs) on CT and MRI. Material and methods The interactive method requires the user to click six points near the tumor’s extreme boundaries in the image. These six points are transformed into a distance map and serve, with the image, as input for a convolutional neural network. A multi-center public dataset with 514 patients and nine STT phenotypes in seven anatomical locations, with CT or T1-weighted MRI, was used for training and internal validation. For external validation, another public dataset was employed, which included five unseen STT phenotypes in extremities on CT, T1-weighted MRI, and T2-weighted fat-saturated (FS) MRI.

Results

Internal validation resulted in a dice similarity coefficient (DSC) of 0.85 ± 0.11 (mean ± standard deviation) for CT and 0.84 ± 0.12 for T1-weighted MRI. External validation resulted in DSCs of 0.81 ± 0.08 for CT, 0.84 ± 0.09 for T1-weighted MRI, and 0.88 ± 0.08 for T2-weighted FS MRI. Volumetric measurements showed consistent replication with low error internally (volume: 1 ± 28 mm 3 , r = 0.99; diameter: − 6 ± 14 mm, r = 0.90) and externally (volume: − 7 ± 23 mm 3 , r = 0.96; diameter: − 3 ± 6 mm, r = 0.99). Interactive segmentation time was considerably shorter (CT: 364 s, T1-weighted MRI: 258s) than manual segmentation (CT: 1639s, T1-weighted MRI: 1895s).

Conclusion

The minimally interactive segmentation method effectively segments STT phenotypes on CT and MRI, with robust generalization to unseen phenotypes and imaging modalities. Key Points Question Can this deep learning-based method segment soft-tissue tumors faster than can be done manually and more accurately than other automatic methods?

Findings

The minimally interactive segmentation method achieved accurate segmentation results in internal and external validation, and generalized well across soft-tissue tumor phenotypes and imaging modalities. Clinical relevance This minimally interactive deep learning-based segmentation method could reduce the burden of manual segmentation, facilitate the integration of imaging-based biomarkers (e.g., radiomics) into clinical practice, and provide a fast, semi-automatic solution for volume and diameter measurements (e.g., RECIST).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMagnetic Resonance ImagingTomography, X-Ray ComputedSoft Tissue NeoplasmsImage Interpretation, Computer-AssistedHumansMaleFemaleMiddle AgedReproducibility of ResultsAdultAged

Stichwörter der Autor:innen

Deep learningDiagnostic imagingMagnetic resonance imagingSoft-tissue neoplasmsTomography (X-ray computed)

Autor:innen und Institutionen

  • Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, The Netherlands. d.spaanderman@erasmusmc.nl.
  • Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, The Netherlands.
  • Department of Surgical Oncology, Erasmus MC Cancer Institute, Rotterdam, The Netherlands.
  • Department of Medical Oncology, Erasmus MC Cancer Institute, Rotterdam, The Netherlands.
  • Department of Pathology, Erasmus MC Cancer Institute, Rotterdam, The Netherlands.
  • Faculty of Medical Sciences, University of Groningen, Groningen, The Netherlands.

Förderung

  • Dutch national e-infrastructure with the support of the SURF Cooperative
  • Hanarth Fonds

Zitieren

APA

Spaanderman, D. J., Starmans, M. P. A., van Erp, G. C. M., Hanff, D. F., Sluijter, J. H., Schut, A. W., van Leenders, G. J. L. H., Verhoef, C., Grünhagen, D. J., Niessen, W. J., Visser, J. J., & Klein, S. (2024). Minimally interactive segmentation of soft-tissue tumors on CT and MRI using deep learning. European Radiology, 35(5), 2736-2745. https://doi.org/10.1007/s00330-024-11167-8

Vancouver

Spaanderman DJ, Starmans MPA, van Erp GCM, Hanff DF, Sluijter JH, Schut AW, et al. Minimally interactive segmentation of soft-tissue tumors on CT and MRI using deep learning. European Radiology. 2024;35(5):2736-2745. doi:10.1007/s00330-024-11167-8

BibTeX
@article{Spaanderman2024,
  author = {Spaanderman, Douwe J and Starmans, Martijn P A and van Erp, Gonnie C M and Hanff, David F and Sluijter, Judith H and Schut, Anne-Rose W and van Leenders, Geert J L H and Verhoef, Cornelis and Grünhagen, Dirk J and Niessen, Wiro J and Visser, Jacob J and Klein, Stefan},
  title = {Minimally interactive segmentation of soft-tissue tumors on CT and MRI using deep learning},
  journal = {European Radiology},
  year = {2024},
  volume = {35},
  number = {5},
  pages = {2736--2745},
  doi = {10.1007/s00330-024-11167-8}
}
Kostenlos starten →