EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep learning-based overall survival prediction model in patients with rare cancer: a case study for primary central nervous system lymphoma

Ziyu She, Aldo Marzullo, Michela Destito, Maria Francesca Spadea, Riccardo Leone, Nicoletta Anzalone, Sara Steffanoni, Federico Erbella, Andrés J M Ferreri, Giancarlo Ferrigno, Teresa Calimeri, Elena De Momi

International Journal of Computer Assisted Radiology and Surgery · 2023

DOI: 10.1007/s11548-023-02886-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Assisted Radiology and Surgery, 2023. Verfasst von Ziyu She und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy. ziyu.she@polimi.it. Hauptthemen laut MEDLINE: Deep Learning, Brain Neoplasms, Lymphoma, Central Nervous System Neoplasms. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Politecnico di Milano.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Primary central nervous system lymphoma (PCNSL) is a rare, aggressive form of extranodal non-Hodgkin lymphoma. To predict the overall survival (OS) in advance is of utmost importance as it has the potential to aid clinical decision-making. Though radiomics-based machine learning (ML) has demonstrated the promising performance in PCNSL, it demands large amounts of manual feature extraction efforts from magnetic resonance images beforehand. deep learning (DL) overcomes this limitation.

Methods

In this paper, we tailored the 3D ResNet to predict the OS of patients with PCNSL. To overcome the limitation of data sparsity, we introduced data augmentation and transfer learning, and we evaluated the results using r stratified k -fold cross-validation. To explain the results of our model, gradient-weighted class activation mapping was applied.

Results

We obtained the best performance (the standard error) on post-contrast T1-weighted (T1Gd)—area under curve $$=0.81(0.03)$$ = 0.81 ( 0.03 ) , accuracy $$=0.87(0.07)$$ = 0.87 ( 0.07 ) , precision $$=0.88(0.07)$$ = 0.88 ( 0.07 ) , recall $$=0.88(0.07)$$ = 0.88 ( 0.07 ) and F 1-score $$=0.87(0.07)$$ = 0.87 ( 0.07 ) , while compared with ML-based models on clinical data and radiomics data, respectively, further confirming the stability of our model. Also, we observed that PCNSL is a whole-brain disease and in the cases where the OS is less than 1 year, it is more difficult to distinguish the tumor boundary from the normal part of the brain, which is consistent with the clinical outcome.

Conclusions

All these findings indicate that T1Gd can improve prognosis predictions of patients with PCNSL. To the best of our knowledge, this is the first time to use DL to explain model patterns in OS classification of patients with PCNSL. Future work would involve collecting more data of patients with PCNSL, or additional retrospective studies on different patient populations with rare diseases, to further promote the clinical role of our model.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningBrain NeoplasmsLymphomaCentral Nervous System NeoplasmsHumansRetrospective StudiesCentral Nervous System

Stichwörter der Autor:innen

Deep learningGrad-CAMModel explainabilityOS predictionPCNSL

Autor:innen und Institutionen

  • Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy. ziyu.she@polimi.it.
  • Department of Mathematics and Computer Science, University of Calabria, Rende, Italy.
  • Department of Experimental and Clinical Medicine, University of Catanzaro, Catanzaro, Italy.
  • Neuroradiology Unit, IRCCS San Raffaele Scientific Institute, Milan, Italy.
  • Lymphoma Unit, IRCCS San Raffaele Scientific Institute, Milan, Italy.
  • Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy.

Förderung

  • Politecnico di Milano

Zitieren

APA

She, Z., Marzullo, A., Destito, M., Spadea, M. F., Leone, R., Anzalone, N., Steffanoni, S., Erbella, F., Ferreri, A. J. M., Ferrigno, G., Calimeri, T., & De Momi, E. (2023). Deep learning-based overall survival prediction model in patients with rare cancer: a case study for primary central nervous system lymphoma. International Journal of Computer Assisted Radiology and Surgery. https://doi.org/10.1007/s11548-023-02886-2

Vancouver

She Z, Marzullo A, Destito M, Spadea MF, Leone R, Anzalone N, et al. Deep learning-based overall survival prediction model in patients with rare cancer: a case study for primary central nervous system lymphoma. International Journal of Computer Assisted Radiology and Surgery. 2023. doi:10.1007/s11548-023-02886-2

BibTeX
@article{She2023,
  author = {She, Ziyu and Marzullo, Aldo and Destito, Michela and Spadea, Maria Francesca and Leone, Riccardo and Anzalone, Nicoletta and Steffanoni, Sara and Erbella, Federico and Ferreri, Andrés J M and Ferrigno, Giancarlo and Calimeri, Teresa and De Momi, Elena},
  title = {Deep learning-based overall survival prediction model in patients with rare cancer: a case study for primary central nervous system lymphoma},
  journal = {International Journal of Computer Assisted Radiology and Surgery},
  year = {2023},
  doi = {10.1007/s11548-023-02886-2}
}
Kostenlos starten →