Journal of bone oncology · 2025
Single Photon Emission Computed Tomography/X-ray Computed Tomography-based radiomics analysis for diagnosis of bone metastases in patients with breast cancer.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Su Huiyu, Ma Chunwen, Sun Dongli, Jin Jianhua
Аннотация
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.
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.