Deep Learning-Based Tumor Segmentation of Murine Magnetic Resonance Images of Prostate Cancer Patient-Derived Xenografts
Tomography · 2025
DOI: 10.3390/tomography11030021 ↗Kurz gefasst
Fachartikel in der Zeitschrift Tomography, 2025. Verfasst von Satvik Nayak und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology and Biomedical Imaging, University of California-San Francisco, San Francisco, CA 94158, USA. Hauptthemen laut MEDLINE: Prostatic Neoplasms, Deep Learning, Magnetic Resonance Imaging, Image Processing, Computer-Assisted. Die Arbeit nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIBIB NIH HHS, NCI NIH HHS, NIH.
Abstract (Originalsprache)
Background/Objective: Longitudinal in vivo studies of murine xenograft models are widely utilized in oncology to study cancer biology and develop therapies. Magnetic resonance imaging (MRI) of these tumors is an invaluable tool for monitoring tumor growth and characterizing the tumors as well. Methods: In this work, a pipeline for automating the segmentation of xenografts in mouse models was developed. T2-weighted (T2-wt) MRI images from mice implanted with six different prostate cancer patient-derived xenografts (PDX) in the kidneys, liver, and tibia were used. The segmentation pipeline included a slice classifier to identify the slices that had tumors and subsequent training and validation using several U-Net-based segmentation architectures. Multiple combinations of the algorithm and training images for different sites were evaluated for inference quality. Results and Conclusions: The slice classifier network achieved 90% accuracy in identifying slices containing tumors. Among the various segmentation architectures tested, the dense residual recurrent U-Net achieved the highest performance in kidney tumors. When evaluated across the kidneys, tibia, and liver, this architecture performed the best when trained on all data as compared to training on only data from a single site (and inferring on a multi-site tumor images), achieving a Dice score of 0.924 across the test set.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology and Biomedical Imaging, University of California-San Francisco, San Francisco, CA 94158, USA.
ORCID-Profile: Satvik Nayak, Ernesto Diaz, Avantika Sinha, Nikhil Deveshwar, Matthew Gibbons, Sule Sahin, Peder E Z Larson, Renuka Sriram
Förderung
- NIBIB NIH HHS
- NCI NIH HHS
- NIH
- UCSF Center for Intelligent Imaging summer internship program
Zitieren
APA
Nayak, S., Salkever, H., Diaz, E., Sinha, A., Deveshwar, N., Hess, M., Gibbons, M., Sahin, S., Rajagopal, A., Larson, P. E. Z., & Sriram, R. (2025). Deep Learning-Based Tumor Segmentation of Murine Magnetic Resonance Images of Prostate Cancer Patient-Derived Xenografts. Tomography. https://doi.org/10.3390/tomography11030021
Vancouver
Nayak S, Salkever H, Diaz E, Sinha A, Deveshwar N, Hess M, et al. Deep Learning-Based Tumor Segmentation of Murine Magnetic Resonance Images of Prostate Cancer Patient-Derived Xenografts. Tomography. 2025. doi:10.3390/tomography11030021
BibTeX
@article{Nayak2025,
author = {Nayak, Satvik and Salkever, Henry and Diaz, Ernesto and Sinha, Avantika and Deveshwar, Nikhil and Hess, Madeline and Gibbons, Matthew and Sahin, Sule and Rajagopal, Abhejit and Larson, Peder E Z and Sriram, Renuka},
title = {Deep Learning-Based Tumor Segmentation of Murine Magnetic Resonance Images of Prostate Cancer Patient-Derived Xenografts},
journal = {Tomography},
year = {2025},
doi = {10.3390/tomography11030021}
}
EUVIMED