We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

MedImaging

Download Mobile App
Recent News Radiography MRI Ultrasound Nuclear Medicine General/Advanced Imaging Imaging IT Industry News

MRI-Based Algorithm Accurately Predicts Spinal Pathologies

By MedImaging International staff writers
Posted on 09 Oct 2023

Various types of spinal pathologies exist, ranging from trauma and degenerative diseases to infections, neoplasms, inflammatory conditions, and tumors. Therefore, clinical evaluation often relies on laboratory tests and imaging studies to guide diagnosis and treatment decisions. Although biopsy is the definitive method for diagnosis, it's invasive and expensive. Now, a new study has revealed that a deep-learning algorithm using MRI scans can effectively distinguish between different types of spinal pathologies. The study showed that the algorithm's accuracy was moderate for the validation group but high for the test group.

Researchers from the Tel Aviv Medical Center (Tel Aviv, Israel) built the deep-learning algorithm on the Fast.ai framework on top of the PyTorch environment and uses pre-surgery MRI data and post-surgery pathological findings for its evaluations. The data used for training and validation were organized in a five-fold cross-validation format. The study examined MRI data from 231 patients who had different spinal pathologies: carcinoma, infection, meningioma, and schwannoma. The research indicated that the algorithm achieved an average accuracy of 0.78 in the validation set and 0.93 in the test set.


Image: The MRI-based algorithm can differentiate between different spinal pathologies (Photo courtesy of 123RF)
Image: The MRI-based algorithm can differentiate between different spinal pathologies (Photo courtesy of 123RF)

While the researchers admit that the algorithm isn't as precise as traditional pathology reports, they see it as a promising tool for the timely diagnosis of spinal conditions. It could potentially reduce the need for riskier, more invasive procedures like biopsies. Future research, they suggest, should focus on integrating larger and more diverse patient datasets to assess the algorithm's broader applicability. They also highlighted the need for additional studies to explore the practicality of using deep-learning methods for identifying spinal pathologies via MRI.

“Although based on a relatively small, segregated cohort, this study represents the power of deep learning tools in prediction spinal pathologies and lays the foundations for developing deep learning-based algorithms for this purpose,” wrote the authors.

Related Links:
Tel Aviv Medical Center


Diagnostic Ultrasound System
MS1700C
Radiology Software
DxWorks
New
Prostate Cancer MRI Analysis Tool
DynaCAD Urology
Multi-Use Ultrasound Table
Clinton

Latest MRI News

Ultra-Powerful MRI Scans Enable Life-Changing Surgery in Treatment-Resistant Epileptic Patients

AI-Powered MRI Technology Improves Parkinson’s Diagnoses

Biparametric MRI Combined with AI Enhances Detection of Clinically Significant Prostate Cancer