Related Experiment Video
Updated: Jul 6, 2025
Diffusion Tensor Magnetic Resonance Imaging in Chronic Spinal Cord Compression
Published on: May 7, 2019
A deep neural network for MRI spinal inflammation in axial spondyloarthritis
Yingying Lin1, Shirley Chiu Wai Chan2, Ho Yin Chung2,3
1Department of Diagnostic Radiology, The University of Hong Kong, LG3 Sassoon Road No. 5, Pok Fu Lam, Hong Kong.
Objective:
To develop a deep neural network for the detection of inflammatory spine in short tau inversion recovery (STIR) sequence of magnetic resonance imaging (MRI) on patients with axial spondyloarthritis (axSpA).
Methods:
A total 330 patients with axSpA were recruited. STIR MRI of the whole spine and clinical data were obtained. Regions of interests (ROIs) were drawn outlining the active inflammatory lesion consisting of bone marrow edema (BME). Spinal inflammation was defined by the presence of an active inflammatory lesion on the STIR sequence. The 'fake-color' images were constructed. Images from 270 and 60 patients were randomly separated into the training/validation and testing sets, respectively. Deep neural network was developed using attention UNet. The neural network performance was compared to the image interpretation by a radiologist blinded to the ground truth.
Results:
Active inflammatory lesions were identified in 2891 MR images and were absent in 14,590 MR images. The sensitivity and specificity of the derived deep neural network were 0.80 ± 0.03 and 0.88 ± 0.02, respectively. The Dice coefficient of the true positive lesions was 0.55 ± 0.02. The area under the curve of the receiver operating characteristic (AUC-ROC) curve of the deep neural network was 0.87 ± 0.02. The performance of the developed deep neural network was comparable to the interpretation of a radiologist with similar sensitivity and specificity.
Conclusion:
The developed deep neural network showed similar sensitivity and specificity to a radiologist with four years of experience. The results indicated that the network can provide a reliable and straightforward way of interpreting spinal MRI. The use of this deep neural network has the potential to expand the use of spinal MRI in managing axSpA.
Insights
A new deep neural network accurately detects spinal inflammation in axial spondyloarthritis (axSpA) patients using MRI scans. This AI tool shows performance comparable to experienced radiologists, aiding axSpA management.
Area of Science:
- Radiology
- Artificial Intelligence
- Medical Imaging
Background:
- Axial spondyloarthritis (axSpA) is a chronic inflammatory disease affecting the spine.
- Early detection of spinal inflammation is crucial for effective management.
- Short tau inversion recovery (STIR) sequence magnetic resonance imaging (MRI) is used to identify active inflammatory lesions.
Purpose of the Study:
- To develop and evaluate a deep neural network (DNN) for detecting spinal inflammation on STIR MRI in axSpA patients.
- To compare the DNN's performance against human radiologists.
Main Methods:
- A dataset of 330 axSpA patients' STIR MRI scans was utilized.
- Regions of interest (ROIs) were drawn to identify bone marrow edema (BME) as active inflammatory lesions.
- An attention UNet-based DNN was developed and trained on 270 patients' data, with validation.
- The DNN's performance was assessed on a separate testing set of 60 patients and compared to a blinded radiologist.
Main Results:
- The DNN achieved a sensitivity of 0.80 ± 0.03 and specificity of 0.88 ± 0.02.
- The Dice coefficient for true positive lesions was 0.55 ± 0.02.
- The area under the receiver operating characteristic curve (AUC-ROC) was 0.87 ± 0.02.
- The DNN's performance was comparable to that of a radiologist.
Conclusions:
- The developed DNN demonstrates reliable performance in detecting spinal inflammation on STIR MRI for axSpA.
- The network offers a straightforward and potentially expandable method for spinal MRI interpretation.
- This AI tool could enhance the clinical utility of spinal MRI in managing axSpA.
