Single Photon Emission Computed Tomography/X-ray Computed Tomography-based radiomics analysis for diagnosis of bone metastases in patients with breast cancer

Purpose: Bones are the most metastatic site for breast cancer (BC), which can cause complications such as pathologic osteolysis, seriously affecting the quality of life of patients. This study intended to investigate the efficacy of Single Photon Emission Computed Tomography/X-ray Computed Tomograph...

Full description

Saved in:
Bibliographic Details
Main Authors: Huiyu Su, Chunwen Ma, Dongli Sun, Jianhua Jin
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Journal of Bone Oncology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2212137425000272
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849330236708093952
author Huiyu Su
Chunwen Ma
Dongli Sun
Jianhua Jin
author_facet Huiyu Su
Chunwen Ma
Dongli Sun
Jianhua Jin
author_sort Huiyu Su
collection DOAJ
description Purpose: Bones are the most metastatic site for breast cancer (BC), which can cause complications such as pathologic osteolysis, seriously affecting the quality of life of patients. This study intended to investigate the efficacy of Single Photon Emission Computed Tomography/X-ray Computed Tomography (SPECT/CT) in diagnosing bone metastases in BC and to develop a model for predicting the diagnostic effectiveness. Methods: In this study, we enrolled 185 patients with BC who underwent SPECT/CT scanning. The region of interest (ROI) of each SPECT/CT image was demarcated, and the radiomics features were determined from the ROIs and screened for the optimal features signature to construct the radiomics model. Based on clinical characteristics, the clinical model was developed, and the independent predictive factors were discovered through univariate and multivariate COX regression analyses. Additionally, the radiomics nomogram was created through integrating the radiomics score and independent predictive factors. Thereafter, the receiver operating characteristic (ROC) was applied to determine the diagnostic performance of various models. Results: The radiomics model was constructed based on 29 optimal features. The N stage was an independent factor, and the radiomics nomogram was created through integrating the radiomics score and N stage. Among three models, the radiomics nomogram had the highest diagnostic value for BC bone metastasis (AUC: the training set: 0.956 (0.909–1.000); the validation set: 0.936 (0.866–1.000)). Conclusion: Radiomics analysis based on SPECT/CT can effectively diagnose bone metastasis in BC patients, establishing a theoretical foundation for the formulation of personalized treatment options in clinical practice.
format Article
id doaj-art-60ea508f6d1c41a48615409f3bc2043c
institution Kabale University
issn 2212-1374
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Journal of Bone Oncology
spelling doaj-art-60ea508f6d1c41a48615409f3bc2043c2025-08-20T03:47:01ZengElsevierJournal of Bone Oncology2212-13742025-06-015210068610.1016/j.jbo.2025.100686Single Photon Emission Computed Tomography/X-ray Computed Tomography-based radiomics analysis for diagnosis of bone metastases in patients with breast cancerHuiyu Su0Chunwen Ma1Dongli Sun2Jianhua Jin3Department of Nuclear Medicine, First Hospital of Shanxi Medical University, Taiyuan 030001 Shanxi, China; Collaborative Innovation Center for Molecular Imaging of Precision Medicine, Taiyuan 030001 Shanxi, China; Department of Breast Surgery, Peking University First Hospital Taiyuan Hospital (Taiyuan Central Hospital, The Directly Affiliated Hospital of Shanxi Medical University and the Ninth Clinical Medical College), Taiyuan 030001 Shanxi, ChinaDepartment of Nuclear Medicine, First Hospital of Shanxi Medical University, Taiyuan 030001 Shanxi, China; Collaborative Innovation Center for Molecular Imaging of Precision Medicine, Taiyuan 030001 Shanxi, ChinaDepartment of Nuclear Medicine, The Second Hospital of Shanxi Medical University, Taiyuan 030001 Shanxi, ChinaDepartment of Nuclear Medicine, First Hospital of Shanxi Medical University, Taiyuan 030001 Shanxi, China; Collaborative Innovation Center for Molecular Imaging of Precision Medicine, Taiyuan 030001 Shanxi, China; Corresponding author.Purpose: Bones are the most metastatic site for breast cancer (BC), which can cause complications such as pathologic osteolysis, seriously affecting the quality of life of patients. This study intended to investigate the efficacy of Single Photon Emission Computed Tomography/X-ray Computed Tomography (SPECT/CT) in diagnosing bone metastases in BC and to develop a model for predicting the diagnostic effectiveness. Methods: In this study, we enrolled 185 patients with BC who underwent SPECT/CT scanning. The region of interest (ROI) of each SPECT/CT image was demarcated, and the radiomics features were determined from the ROIs and screened for the optimal features signature to construct the radiomics model. Based on clinical characteristics, the clinical model was developed, and the independent predictive factors were discovered through univariate and multivariate COX regression analyses. Additionally, the radiomics nomogram was created through integrating the radiomics score and independent predictive factors. Thereafter, the receiver operating characteristic (ROC) was applied to determine the diagnostic performance of various models. Results: The radiomics model was constructed based on 29 optimal features. The N stage was an independent factor, and the radiomics nomogram was created through integrating the radiomics score and N stage. Among three models, the radiomics nomogram had the highest diagnostic value for BC bone metastasis (AUC: the training set: 0.956 (0.909–1.000); the validation set: 0.936 (0.866–1.000)). Conclusion: Radiomics analysis based on SPECT/CT can effectively diagnose bone metastasis in BC patients, establishing a theoretical foundation for the formulation of personalized treatment options in clinical practice.http://www.sciencedirect.com/science/article/pii/S2212137425000272Breast cancerBone metastasisRadiomicsSingle Photon Emission Computed Tomography/X-ray Computed Tomography
spellingShingle Huiyu Su
Chunwen Ma
Dongli Sun
Jianhua Jin
Single Photon Emission Computed Tomography/X-ray Computed Tomography-based radiomics analysis for diagnosis of bone metastases in patients with breast cancer
Journal of Bone Oncology
Breast cancer
Bone metastasis
Radiomics
Single Photon Emission Computed Tomography/X-ray Computed Tomography
title Single Photon Emission Computed Tomography/X-ray Computed Tomography-based radiomics analysis for diagnosis of bone metastases in patients with breast cancer
title_full Single Photon Emission Computed Tomography/X-ray Computed Tomography-based radiomics analysis for diagnosis of bone metastases in patients with breast cancer
title_fullStr Single Photon Emission Computed Tomography/X-ray Computed Tomography-based radiomics analysis for diagnosis of bone metastases in patients with breast cancer
title_full_unstemmed Single Photon Emission Computed Tomography/X-ray Computed Tomography-based radiomics analysis for diagnosis of bone metastases in patients with breast cancer
title_short Single Photon Emission Computed Tomography/X-ray Computed Tomography-based radiomics analysis for diagnosis of bone metastases in patients with breast cancer
title_sort single photon emission computed tomography x ray computed tomography based radiomics analysis for diagnosis of bone metastases in patients with breast cancer
topic Breast cancer
Bone metastasis
Radiomics
Single Photon Emission Computed Tomography/X-ray Computed Tomography
url http://www.sciencedirect.com/science/article/pii/S2212137425000272
work_keys_str_mv AT huiyusu singlephotonemissioncomputedtomographyxraycomputedtomographybasedradiomicsanalysisfordiagnosisofbonemetastasesinpatientswithbreastcancer
AT chunwenma singlephotonemissioncomputedtomographyxraycomputedtomographybasedradiomicsanalysisfordiagnosisofbonemetastasesinpatientswithbreastcancer
AT donglisun singlephotonemissioncomputedtomographyxraycomputedtomographybasedradiomicsanalysisfordiagnosisofbonemetastasesinpatientswithbreastcancer
AT jianhuajin singlephotonemissioncomputedtomographyxraycomputedtomographybasedradiomicsanalysisfordiagnosisofbonemetastasesinpatientswithbreastcancer