Deep Learning-Based Tumor Segmentation of Murine Magnetic Resonance Images of Prostate Cancer Patient-Derived Xenografts

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. Metho...

Full description

Saved in:
Bibliographic Details
Main Authors: Satvik Nayak, Henry Salkever, Ernesto Diaz, Avantika Sinha, Nikhil Deveshwar, Madeline Hess, Matthew Gibbons, Sule Sahin, Abhejit Rajagopal, Peder E. Z. Larson, Renuka Sriram
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Tomography
Subjects:
Online Access:https://www.mdpi.com/2379-139X/11/3/21
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850088165314920448
author Satvik Nayak
Henry Salkever
Ernesto Diaz
Avantika Sinha
Nikhil Deveshwar
Madeline Hess
Matthew Gibbons
Sule Sahin
Abhejit Rajagopal
Peder E. Z. Larson
Renuka Sriram
author_facet Satvik Nayak
Henry Salkever
Ernesto Diaz
Avantika Sinha
Nikhil Deveshwar
Madeline Hess
Matthew Gibbons
Sule Sahin
Abhejit Rajagopal
Peder E. Z. Larson
Renuka Sriram
author_sort Satvik Nayak
collection DOAJ
description 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. T<sub>2</sub>-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.
format Article
id doaj-art-59e15776a31d43a3afd3fc5d9b9ab787
institution DOAJ
issn 2379-1381
2379-139X
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Tomography
spelling doaj-art-59e15776a31d43a3afd3fc5d9b9ab7872025-08-20T02:43:04ZengMDPI AGTomography2379-13812379-139X2025-02-011132110.3390/tomography11030021Deep Learning-Based Tumor Segmentation of Murine Magnetic Resonance Images of Prostate Cancer Patient-Derived XenograftsSatvik Nayak0Henry Salkever1Ernesto Diaz2Avantika Sinha3Nikhil Deveshwar4Madeline Hess5Matthew Gibbons6Sule Sahin7Abhejit Rajagopal8Peder E. Z. Larson9Renuka Sriram10Department of Radiology and Biomedical Imaging, University of California-San Francisco, San Francisco, CA 94158, USADepartment of Radiology and Biomedical Imaging, University of California-San Francisco, San Francisco, CA 94158, USADepartment of Radiology and Biomedical Imaging, University of California-San Francisco, San Francisco, CA 94158, USADepartment of Radiology and Biomedical Imaging, University of California-San Francisco, San Francisco, CA 94158, USADepartment of Radiology and Biomedical Imaging, University of California-San Francisco, San Francisco, CA 94158, USADepartment of Radiology and Biomedical Imaging, University of California-San Francisco, San Francisco, CA 94158, USADepartment of Radiology and Biomedical Imaging, University of California-San Francisco, San Francisco, CA 94158, USADepartment of Radiology and Biomedical Imaging, University of California-San Francisco, San Francisco, CA 94158, USADepartment of Radiology and Biomedical Imaging, University of California-San Francisco, San Francisco, CA 94158, USADepartment of Radiology and Biomedical Imaging, University of California-San Francisco, San Francisco, CA 94158, USADepartment of Radiology and Biomedical Imaging, University of California-San Francisco, San Francisco, CA 94158, USABackground/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. T<sub>2</sub>-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.https://www.mdpi.com/2379-139X/11/3/21prostate cancermagnetic resonance imagingpatient-derived xenograftsdeep learningtumor segmentation
spellingShingle Satvik Nayak
Henry Salkever
Ernesto Diaz
Avantika Sinha
Nikhil Deveshwar
Madeline Hess
Matthew Gibbons
Sule Sahin
Abhejit Rajagopal
Peder E. Z. Larson
Renuka Sriram
Deep Learning-Based Tumor Segmentation of Murine Magnetic Resonance Images of Prostate Cancer Patient-Derived Xenografts
Tomography
prostate cancer
magnetic resonance imaging
patient-derived xenografts
deep learning
tumor segmentation
title Deep Learning-Based Tumor Segmentation of Murine Magnetic Resonance Images of Prostate Cancer Patient-Derived Xenografts
title_full Deep Learning-Based Tumor Segmentation of Murine Magnetic Resonance Images of Prostate Cancer Patient-Derived Xenografts
title_fullStr Deep Learning-Based Tumor Segmentation of Murine Magnetic Resonance Images of Prostate Cancer Patient-Derived Xenografts
title_full_unstemmed Deep Learning-Based Tumor Segmentation of Murine Magnetic Resonance Images of Prostate Cancer Patient-Derived Xenografts
title_short Deep Learning-Based Tumor Segmentation of Murine Magnetic Resonance Images of Prostate Cancer Patient-Derived Xenografts
title_sort deep learning based tumor segmentation of murine magnetic resonance images of prostate cancer patient derived xenografts
topic prostate cancer
magnetic resonance imaging
patient-derived xenografts
deep learning
tumor segmentation
url https://www.mdpi.com/2379-139X/11/3/21
work_keys_str_mv AT satviknayak deeplearningbasedtumorsegmentationofmurinemagneticresonanceimagesofprostatecancerpatientderivedxenografts
AT henrysalkever deeplearningbasedtumorsegmentationofmurinemagneticresonanceimagesofprostatecancerpatientderivedxenografts
AT ernestodiaz deeplearningbasedtumorsegmentationofmurinemagneticresonanceimagesofprostatecancerpatientderivedxenografts
AT avantikasinha deeplearningbasedtumorsegmentationofmurinemagneticresonanceimagesofprostatecancerpatientderivedxenografts
AT nikhildeveshwar deeplearningbasedtumorsegmentationofmurinemagneticresonanceimagesofprostatecancerpatientderivedxenografts
AT madelinehess deeplearningbasedtumorsegmentationofmurinemagneticresonanceimagesofprostatecancerpatientderivedxenografts
AT matthewgibbons deeplearningbasedtumorsegmentationofmurinemagneticresonanceimagesofprostatecancerpatientderivedxenografts
AT sulesahin deeplearningbasedtumorsegmentationofmurinemagneticresonanceimagesofprostatecancerpatientderivedxenografts
AT abhejitrajagopal deeplearningbasedtumorsegmentationofmurinemagneticresonanceimagesofprostatecancerpatientderivedxenografts
AT pederezlarson deeplearningbasedtumorsegmentationofmurinemagneticresonanceimagesofprostatecancerpatientderivedxenografts
AT renukasriram deeplearningbasedtumorsegmentationofmurinemagneticresonanceimagesofprostatecancerpatientderivedxenografts