Related Experiment Video
Updated: Jun 18, 2025
In vivo Macrophage Imaging Using MR Targeted Contrast Agent for Longitudinal Evaluation of Septic Arthritis
Published on: October 20, 2013
Bone marrow edema detection for diagnostic support of axial spondyloarthritis using MRI
Akira Kojima1, Tetsuya Tomita2, Shigeyoshi Tsuji3
1Institute of Engineering, Tokyo University of Agriculture and Technology, Tokyo, Japan.
Purpose:
This study proposes a process for detecting slices with bone marrow edema (BME), a typical finding of axSpA, using MRI scans as the input. This process does not require manual input of ROIs and provides the results of the judgment of the presence or absence of BME on a slice and the location of edema as the rationale for the judgment.
Methods:
First, the signal intensity of the MRI scans of the sacroiliac joint was normalized to reduce the variation in signal values between scans. Next, slices containing synovial joints were extracted using a slice selection network. Finally, the BME slice detection network determines the presence or absence of the BME in each slice and outputs the location of the BME.
Results:
The proposed method was applied to 86 MRI scans collected from 15 hospitals in Japan. The results showed that the average absolute error of the slice selection process was 1.49 slices for the misalignment between the upper and lower slices of the synovial joint range. The accuracy, sensitivity, and specificity of the BME slice detection network were 0.905, 0.532, and 0.974, respectively.
Conclusion:
This paper proposes a process to detect the slice with BME and its location as the rationale of the judgment from an MRI scan and shows its effectiveness using 86 MRI scans. In the future, we plan to develop a process for detecting other findings such as bone erosion from MR scans, followed by the development of a diagnostic support system.
Insights
This study introduces an automated MRI analysis to detect bone marrow edema (BME) in axSpA patients, identifying BME location for diagnostic support without manual region input.
Area of Science:
- Radiology
- Medical Imaging Analysis
- Artificial Intelligence in Medicine
Background:
- Bone marrow edema (BME) is a key indicator of active axial spondyloarthritis (axSpA).
- Accurate detection of BME on MRI is crucial for diagnosis and monitoring of axSpA.
- Current methods may involve manual region of interest (ROI) selection, which can be time-consuming and subjective.
Purpose of the Study:
- To develop and validate an automated process for detecting slices with BME in MRI scans.
- To identify the specific location of BME within slices to serve as a rationale for detection.
- To eliminate the need for manual ROI input in the BME detection process.
Main Methods:
- MRI scans underwent signal intensity normalization.
- A slice selection network identified synovial joint-containing slices.
- A BME slice detection network determined BME presence/absence and location.
Main Results:
- The method was tested on 86 MRI scans from 15 Japanese hospitals.
- Slice selection achieved an average absolute error of 1.49 slices.
- The BME detection network demonstrated 0.905 accuracy, 0.532 sensitivity, and 0.974 specificity.
Conclusions:
- The proposed automated process effectively detects BME slices and their locations in MRI scans.
- The system provides a rationale for BME detection without manual intervention.
- Future work includes expanding the system for other findings like bone erosion and developing a comprehensive diagnostic support tool.
