Efficacy Validation of a Novel MRI-Based Whole-Body Rapid Bone Scan (WB-RBS) Strategy for Diagnosing Bone Metastases: A Prospective Trial
Wu, X.; Zhang, J.; He, Y.; Zhang, Y.; Kang, X.; Hu, W.; Li, Y.; Ma, H.; Wang, Y.; Song, Y.; Chen, X.; Huo, F.; Zhang, Y.; Yin, H.; Xi, Y.
Show abstract
Background: Traditional bone scintigraphy for detecting malignant bone metastases is limited by suboptimal accuracy and radiation exposure. Whole-body magnetic resonance imaging (WB-MRI), while an alternative, requires lengthy scan times and high patient compliance. Purpose: To develop a novel, rapid whole body bone screening (WB-RBS) MRI protocol and evaluate its diagnostic performance for bone metastasis detection. Materials and Methods: Patients with pathologically confirmed malignancies and healthy controls were prospectively enrolled. All participants underwent WB-RBS (acquisition time: about 10 min); patients additionally underwent WB-MRI (about 70 min). Three radiologists, blinded to clinical data, independently evaluated the images for bone metastases. A consensus expert diagnosis served as the reference standard to calculate the diagnostic performance of WB-RBS. Specificity was further assessed in the healthy control group. Results: Seventy patients and 19 healthy controls were included. WB-RBS demonstrated excellent inter-reader agreement at the patient level. Compared with the reference standard, WB-RBS achieved an accuracy of 77.1%-91.4% at the patient level and a slightly lower accuracy (70.6%-82.5%) at the lesion level. At diagnostic confidence thresholds 1-3, the correlations between WB-RBS ratings and the reference standard were statistically significant for both patient- and lesion-level analyses. Conclusion: WB-RBS showed favorable inter-reader agreement and high accuracy for bone metastasis screening at the patient level, while substantially reducing scan time and cost. Its rapid, radiation-free nature and high accessibility offer distinct clinical advantages, supporting its potential as an alternative screening tool to conventional bone scintigraphy.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Impact of Non-Contrast Enhanced Imaging Input Sequences on the Generation of Virtual Contrast-Enhanced Breast MRI Scans using Neural Networks 93%
- Evaluating Large Language Model-Generated Brain MRI Protocols: Performance of GPT4o, o3-mini, DeepSeek-R1 and Qwen2.5-72B 92%
- Pairwise learning of MRI scans using a convolutional Siamese network for prediction of knee pain 92%
Similar papers in this journal
- Correcting B0 inhomogeneity-induced distortions in whole-body diffusion MRI of bone metastases 94%
- Deep neural networks allow expert-level brain meningioma detection, segmentation and improvement of current clinical practice 92%
- An AI-based segmentation and analysis pipeline for high-field MR monitoring of cerebral organoids 92%
Similar papers in this journal
- Diffusion Histology Imaging Combining Diffusion Basis Spectrum Imaging (DBSI) and Machine Learning Improves Detection and Classification of Glioblastoma Pathology 92%
- Discrimination of breast cancer from healthy breast tissues using a three-component diffusion-weighted MRI model 90%
- Solid stress estimations via intraoperative 3D navigation in patients with brain tumors 90%
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.