MRI-based radiomics models for the preoperative prediction of massive intraoperative blood loss in spinal metastases patients.
7 affiliations
- 1School of Medicine, Shanghai University, Shanghai, China.
- 2Department of Radiology, Second Affiliated Hospital of Naval Medical University, Shanghai, China.
- 3Department of Radiology, The First Naval Hospital of Southern Theater Command, Zhanjiang, China.
- 4Shanghai Jiuzhou Intelligent Medical Imaging Institute, Shanghai, China.
- 5Department of Radiology, Second Affiliated Hospital of Naval Medical University, Shanghai, China. [email protected].
- 6School of Medicine, Shanghai University, Shanghai, China. [email protected].
- 7Department of Radiology, Second Affiliated Hospital of Naval Medical University, Shanghai, China. [email protected].
Abstract
Objectives
To develop and validate MRI-based radiomics models for predicting intraoperative massive blood loss (MBL) in patients with spinal metastases.Materials and methods
A total of 507 patients diagnosed with spinal metastases were enrolled in this study, who were classified as MBL and non-MBL group, with the 2500 ml as the threshold. Radiomic features were extracted from T2WI and CET1 sequences and dimensionality reduction was performed by LASSO regression analysis. Radiomics models were developed using radiomics features, yielding a radiomics signature from the best model. Clinical variables were analyzed to create a clinical model. The combined model incorporated both clinical variables and Rad-signature. The predictive performance was assessed through the area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score. Calibration curves and decision curve analyses (DCA) were generated to evaluate the model's accuracy and clinical utility. Finally, a nomogram was developed to visualize the optimal model.Results
Tumor vascularity, preoperative embolization, tumor location, and surgical segments were independent risk factors for MBL. Among 11 machine learning models evaluated, the AdaBoost model demonstrated optimal predictive performance (AUC = 0.775) and was selected as the radiomics model. The combined radiomics-clinical model achieved the highest discriminative ability (AUC = 0.818; 95% CI: 0.7191-0.9165), outperforming both the radiomics model (AUC = 0.768) and the clinical model (AUC = 0.583). The nomogram showed good calibration and provided the greatest net clinical benefit.Conclusions
Radiomics-based prediction models enable preoperative assessment of MBL risk in surgery and support personalized perioperative management strategies.
Related
- CT-based multi-station lymph-node radiomics for preoperative prediction of lymph node metastasis in colorectal cancer: a proof-of-concept comparison with primary-tumor radiomics
- Habitat-based ultrasound radiomics for preoperative prediction of axillary lymph node metastasis in breast cancer: a two-center study
- Nodule subtype dependency of CT-based radiomics for preoperative prediction of spread through air spaces in stage I lung adenocarcinoma: a multi-centre study
- MRI-derived habitat radiomics integrated with transformer deep learning for preoperative prediction of high CD9 expression: a novel prognostic marker in adult-type diffuse gliomas
- Multiparametric MRI radiomics model for preoperative prediction of IDH1 R132H immunopositivity status in adult diffuse Glioma
BibTeX
@article{deng2026mribased,
title = {{MRI-based radiomics models for the preoperative prediction of massive intraoperative blood loss in spinal metastases patients.}},
author = {Heng Deng and Jiayang Yan and Jiayi Zhang and Fukai Li and Guangwen Duan and Wenhao Jia and Xiang Wang and Shiyuan Liu},
journal = {BMC medical imaging},
year = {2026},
month = jul,
doi = {10.1186/s12880-026-02541-7},
url = {https://europepmc.org/article/MED/42928150},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - MRI-based radiomics models for the preoperative prediction of massive intraoperative blood loss in spinal metastases patients.
AU - Heng Deng
AU - Jiayang Yan
AU - Jiayi Zhang
AU - Fukai Li
AU - Guangwen Duan
AU - Wenhao Jia
AU - Xiang Wang
AU - Shiyuan Liu
PY - 2026
DA - 2026/07/28
JO - BMC medical imaging
DO - 10.1186/s12880-026-02541-7
UR - https://europepmc.org/article/MED/42928150
AB - Objectives To develop and validate MRI-based radiomics models for predicting intraoperative massive blood loss (MBL) in patients with spinal metastases.Materials and methods A total of 507 patients diagnosed with spinal metastases were enrolled in this study, who were classified as MBL and non-MBL group, with the 2500 ml as the threshold. Radiomic features were extracted from T2WI and CET1 sequences and dimensionality reduction was performed by LASSO regression analysis. Radiomics models were developed using radiomics features, yielding a radiomics signature from the best model. Clinical variables were analyzed to create a clinical model. The combined model incorporated both clinical variables and Rad-signature. The predictive performance was assessed through the area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score. Calibration curves and decision curve analyses (DCA) were generated to evaluate the model's accuracy and clinical utility. Finally, a nomogram was developed to visualize the optimal model.Results Tumor vascularity, preoperative embolization, tumor location, and surgical segments were independent risk factors for MBL. Among 11 machine learning models evaluated, the AdaBoost model demonstrated optimal predictive performance (AUC = 0.775) and was selected as the radiomics model. The combined radiomics-clinical model achieved the highest discriminative ability (AUC = 0.818; 95% CI: 0.7191-0.9165), outperforming both the radiomics model (AUC = 0.768) and the clinical model (AUC = 0.583). The nomogram showed good calibration and provided the greatest net clinical benefit.Conclusions Radiomics-based prediction models enable preoperative assessment of MBL risk in surgery and support personalized perioperative management strategies.
SN - 1471-2342
ER -