EUVIMEDEUVIMED entdecken
Multizentrische StudieKohortenstudieOpen Access · CC BY 4.0

Deep Learning‐Based Segmentation of Locally Advanced Breast Cancer on MRI in Relation to Residual Cancer Burden: A Multi‐Institutional Cohort Study

Markus H A Janse iD, Liselore M Janssen iD, Bas H M van der Velden iD, Maaike R Moman, Elian J M Wolters-van der Ben, Marc C J M Kock, Max A Viergever iD, Paul J van Diest iD, Kenneth G A Gilhuijs iD

Journal of Magnetic Resonance Imaging · 2023

DOI: 10.1002/jmri.28679 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Journal of Magnetic Resonance Imaging, 2023. Verfasst von Markus H A Janse und 8 weiteren Autor:innen. Beteiligte Einrichtung: Image Sciences Institute, University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands. Hauptthemen laut MEDLINE: Breast Neoplasms, Deep Learning. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Horizon 2020 Framework Programme.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

While several methods have been proposed for automated assessment of breast‐cancer response to neoadjuvant chemotherapy on breast MRI, limited information is available about their performance across multiple institutions.

Purpose

To assess the value and robustness of deep learning‐derived volumes of locally advanced breast cancer (LABC) on MRI to infer the presence of residual disease after neoadjuvant chemotherapy. Study Type Retrospective. Subjects Training cohort: 102 consecutive female patients with LABC scheduled for neoadjuvant chemotherapy (NAC) from a single institution (age: 25–73 years). Independent testing cohort: 55 consecutive female patients with LABC from four institutions (age: 25–72 years). Field Strength/Sequence Training cohort: single vendor 1.5 T or 3.0 T. Testing cohort: multivendor 3.0 T. Gradient echo dynamic contrast‐enhanced sequences. Assessment A convolutional neural network (nnU‐Net) was trained to segment LABC. Based on resulting tumor volumes, an extremely randomized tree model was trained to assess residual cancer burden (RCB)‐0/I vs. RCB‐II/III. An independent model was developed using functional tumor volume (FTV). Models were tested on an independent testing cohort and response assessment performance and robustness across multiple institutions were assessed. Statistical Tests The receiver operating characteristic (ROC) was used to calculate the area under the ROC curve (AUC). DeLong's method was used to compare AUCs. Correlations were calculated using Pearson's method. P values

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsDeep LearningHumansAdultMiddle AgedAgedFemaleRetrospective StudiesNeoplasm, ResidualTreatment OutcomeMagnetic Resonance ImagingNeoadjuvant Therapy

Stichwörter der Autor:innen

breast MRIdeep learninglocally advanced breast cancerresponse monitoringsegmentation

Autor:innen und Institutionen

  • Image Sciences Institute, University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands.
  • Alexander Monro Hospital, Bilthoven, The Netherlands.
  • Department of Radiology, St. Antonius Hospital, Nieuwegein, The Netherlands.
  • Department of Radiology, Albert Schweitzer Hospital, Dordrecht, The Netherlands.
  • Department of Pathology, University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands.

ORCID-Profile: Markus H A Janse, Liselore M Janssen, Bas H M van der Velden, Max A Viergever, Paul J van Diest, Kenneth G A Gilhuijs

Förderung

  • Horizon 2020 Framework Programme

Zitieren

APA

Janse, M. H. A., Janssen, L. M., van der Velden, B. H. M., Moman, M. R., Wolters-van der Ben, E. J. M., Kock, M. C. J. M., Viergever, M. A., van Diest, P. J., & Gilhuijs, K. G. A. (2023). Deep Learning‐Based Segmentation of Locally Advanced Breast Cancer on MRI in Relation to Residual Cancer Burden: A Multi‐Institutional Cohort Study. Journal of Magnetic Resonance Imaging. https://doi.org/10.1002/jmri.28679

Vancouver

Janse MHA, Janssen LM, van der Velden BHM, Moman MR, Wolters-van der Ben EJM, Kock MCJM, et al. Deep Learning‐Based Segmentation of Locally Advanced Breast Cancer on MRI in Relation to Residual Cancer Burden: A Multi‐Institutional Cohort Study. Journal of Magnetic Resonance Imaging. 2023. doi:10.1002/jmri.28679

BibTeX
@article{Janse2023,
  author = {Janse, Markus H A and Janssen, Liselore M and van der Velden, Bas H M and Moman, Maaike R and Wolters-van der Ben, Elian J M and Kock, Marc C J M and Viergever, Max A and van Diest, Paul J and Gilhuijs, Kenneth G A},
  title = {Deep Learning‐Based Segmentation of Locally Advanced Breast Cancer on MRI in Relation to Residual Cancer Burden: A Multi‐Institutional Cohort Study},
  journal = {Journal of Magnetic Resonance Imaging},
  year = {2023},
  doi = {10.1002/jmri.28679}
}
Kostenlos starten →