Related Experiment Video
Updated: Jul 22, 2025
Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
Published on: July 24, 2019
Accurate measurement of magnetic resonance parkinsonism index by a fully automatic and deep learning quantification
Fuhai Sun1, Junyan Lyu1, Si Jian2
1Department of Electronic and Electrical Engineering, College of Engineering, Southern University of Science and Technology, Xili, Nanshan, Shenzhen, 518055, People's Republic of China.
Objectives:
This study aims at a fully automatic pipeline for measuring the magnetic resonance parkinsonism index (MRPI) using deep learning methods.
Methods:
MRPI is defined as the product of the pons area to the midbrain area ratio and the middle cerebellar peduncle (MCP) width to the superior cerebellar peduncle (SCP) width ratio. In our proposed pipeline, we first used nnUNet to segment the brainstem and then employed HRNet to identify two key boundary points so as to sub-divide the whole brainstem into midbrain and pons. HRNet was also employed to predict the MCP endpoints for measuring the MCP width. Finally, we segmented the SCP on an oblique coronal plane and calculated its width. A total of 400 T1-weighted magnetic resonance images (MRIs) were used to train the nnUNet and HRNet models. Five-fold cross-validation was conducted to evaluate our proposed pipeline's performance on the training dataset. We also evaluated the performance of our proposed pipeline on three external datasets. Two of them had two raters manually measuring the MRPI values, providing insights into automatic accuracy versus inter-rater variability.
Results:
We obtained average absolute percentage errors (APEs) of 17.21%, 18.17%, 20.83%, and 22.83% on the training dataset and the three external validation datasets, while the inter-rater average APE measured on the first two external validation datasets was 11.31%. Our proposed pipeline significantly improved the MRPI quantification accuracy over a representative state-of-the-art traditional approach (p < 0.001).
Conclusion:
The proposed automatic pipeline can accurately predict MRPI that is comparable with manual measurement.
Clinical Relevance Statement:
This study presents an automated magnetic resonance parkinsonism index measurement tool that can analyze large amounts of magnetic resonance images, enhance the efficiency of Parkinsonism-Plus syndrome diagnosis, reduce the workload of clinicians, and minimize the impact of human factors on diagnosis.
Key Points:
• We propose an automatic pipeline for measuring the magnetic resonance parkinsonism index from magnetic resonance images. • The effectiveness of the proposed pipeline is successfully established on multiple datasets and comparisons with inter-rater measurements. • The proposed pipeline significantly outperforms a state-of-the-art quantification approach, being much closer to ground truth.
Insights
This study introduces an automated deep learning pipeline for measuring the magnetic resonance parkinsonism index (MRPI). The automated tool achieves accuracy comparable to manual measurements, aiding Parkinsonism-Plus syndrome diagnosis.
Area of Science:
- Medical imaging analysis
- Deep learning in neuroimaging
- Quantitative MRI biomarkers
Background:
- Parkinsonism-Plus syndromes require accurate diagnostic biomarkers.
- The magnetic resonance parkinsonism index (MRPI) is a potential imaging biomarker.
- Manual MRPI measurement is time-consuming and subject to variability.
Purpose of the Study:
- To develop a fully automatic pipeline for MRPI measurement using deep learning.
- To evaluate the accuracy and reliability of the automated pipeline.
- To compare the automated approach with manual measurements and traditional methods.
Main Methods:
- A deep learning pipeline utilizing nnUNet for brainstem segmentation and HRNet for landmark identification was developed.
- The pipeline calculates MRPI based on ratios of pons/midbrain area and middle cerebellar peduncle (MCP)/superior cerebellar peduncle (SCP) width.
- Models were trained on 400 T1-weighted MRIs and validated using five-fold cross-validation and three external datasets.
Main Results:
- The automated pipeline achieved average absolute percentage errors (APEs) ranging from 17.21% to 22.83% across datasets.
- Inter-rater variability on external datasets showed an average APE of 11.31%.
- The proposed pipeline significantly outperformed a state-of-the-art traditional approach (p < 0.001).
Conclusions:
- The developed automatic pipeline accurately measures MRPI, achieving results comparable to manual assessments.
- This automated tool can efficiently analyze large MRI datasets, improving diagnostic efficiency for Parkinsonism-Plus syndromes.
- The pipeline reduces clinical workload and minimizes human error in MRPI quantification.
