Related Experiment Video
Updated: Jul 26, 2025
Hybrid PET/MRI Imaging of Alzheimer's Disease Based on 18F-AV-1451
Published on: April 18, 2025
Do radiomics or diffusion-tensor images provide additional information to predict brain amyloid-beta positivity?
Sungyang Jo1, Hyunna Lee2, Hyung-Ji Kim3
1Department of Neurology, Asan Medical Center, University of Ulsan College of Medicine, 88, Olympic-ro 43-gil, Songpa-gu, Seoul, 05505, Republic of Korea.
Abstract:
The aim of the present study was to predict amyloid-beta positivity using a conventional T1-weighted image, radiomics, and a diffusion-tensor image obtained by magnetic resonance imaging (MRI). We included 186 patients with mild cognitive impairment (MCI) who underwent Florbetaben positron emission tomography (PET), MRI (three-dimensional T1-weighted and diffusion-tensor images), and neuropsychological tests at the Asan Medical Center. We developed a stepwise machine learning algorithm using demographics, T1 MRI features (volume, cortical thickness and radiomics), and diffusion-tensor image to distinguish amyloid-beta positivity on Florbetaben PET. We compared the performance of each algorithm based on the MRI features used. The study population included 72 patients with MCI in the amyloid-beta-negative group and 114 patients with MCI in the amyloid-beta-positive group. The machine learning algorithm using T1 volume performed better than that using only clinical information (mean area under the curve [AUC]: 0.73 vs. 0.69, p < 0.001). The machine learning algorithm using T1 volume showed better performance than that using cortical thickness (mean AUC: 0.73 vs. 0.68, p < 0.001) or texture (mean AUC: 0.73 vs. 0.71, p = 0.002). The performance of the machine learning algorithm using fractional anisotropy in addition to T1 volume was not better than that using T1 volume alone (mean AUC: 0.73 vs. 0.73, p = 0.60). Among MRI features, T1 volume was the best predictor of amyloid PET positivity. Radiomics or diffusion-tensor images did not provide additional benefits.
Insights
T1 MRI volume is the best predictor of amyloid-beta positivity in mild cognitive impairment patients, outperforming radiomics and diffusion-tensor imaging. This finding aids in early disease detection using standard MRI scans.
Area of Science:
- Neurology
- Radiology
- Medical Imaging
Background:
- Alzheimer's disease diagnosis relies on detecting amyloid-beta plaques.
- Early detection of amyloid-beta positivity in mild cognitive impairment (MCI) is crucial for timely intervention.
- Magnetic Resonance Imaging (MRI) offers various techniques for brain assessment.
Purpose of the Study:
- To predict amyloid-beta positivity in MCI patients using conventional T1-weighted MRI, radiomics, and diffusion-tensor imaging.
- To compare the predictive performance of different MRI-derived features for amyloid-beta status.
- To identify the optimal MRI-based predictors for amyloid-beta positivity.
Main Methods:
- A cohort of 186 MCI patients underwent Florbetaben positron emission tomography (PET), MRI (T1-weighted and diffusion-tensor images), and neuropsychological testing.
- A stepwise machine learning algorithm was developed using demographics, T1 MRI features (volume, cortical thickness, radiomics), and diffusion-tensor imaging.
- Performance was evaluated by comparing the area under the curve (AUC) of algorithms utilizing different MRI features.
Main Results:
- The machine learning algorithm using T1 volume achieved a higher AUC (0.73) than using clinical information alone (0.69).
- T1 volume outperformed cortical thickness (AUC 0.68) and radiomic texture features (AUC 0.71) in predicting amyloid-beta positivity.
- Incorporating diffusion-tensor imaging features (fractional anisotropy) with T1 volume did not improve predictive performance (AUC 0.73 vs. 0.73).
Conclusions:
- T1-weighted MRI volume is the most effective MRI-derived feature for predicting amyloid-beta PET positivity in MCI patients.
- Radiomics and diffusion-tensor imaging do not offer additional predictive benefits over T1 volume for this task.
- Conventional T1 MRI volume can serve as a valuable, accessible tool for predicting amyloid-beta status in MCI.
