Deep learning-based magnetic resonance imaging image reconstruction in the assessment of brain microstructural changes in Parkinson's disease patients
Bibliographic record
Abstract
Objective This study was aimed to investigate the application value of deep learning-based magnetic resonance imaging (MRI) image reconstruction technology in the assessment of brain microstructural changes in patients with Parkinson's disease (PD). Methods A total of 78 early-stage PD patients and 78 healthy controls were enrolled. Diffusion tensor imaging (DTI) was performed using MRI, and images were reconstructed using a multi-object interactive neural network-based brain MRI segmentation model. Parameters including fractional anisotropy (FA), mean diffusivity (MD), and radial diffusivity (RD) were calculated to assess microstructural changes in brain regions such as the substantia nigra, basal ganglia, and hippocampus. Pearson correlation analysis was employed to examine the association between regional parameters and Montreal cognitive assessment (MoCA) scores, while receiver operating characteristic (ROC) curves were used to evaluate the diagnostic efficacy of these parameters for PD. Results The constructed segmentation model achieved a Dice similarity coefficient (DSC) of 0.922, with relative volume difference (RVD) and root mean square (RMS) values of 0.042 and 0.46, respectively, outperforming related algorithms. The PD group exhibited significantly reduced FA and increased RD in the substantia nigra, hippocampus, and thalamus. Hippocampal RD demonstrated a strong negative correlation with MoCA scores ( r= -0.67, P< 0.001). ROC analysis indicated that hippocampal RD had the best diagnostic efficacy for PD [area under the curve (AUC) = 0.90, sensitivity 88 %/specificity 87 %], followed by substantia nigra RD (AUC = 0.88) and thalamic RD (AUC = 0.87). Conclusion Deep learning-based MRI reconstruction technology can accurately quantify early brain microstructural damage in PD patients. The RD of the hippocampus and substantia nigra are sensitive biomarkers for diagnosing PD and screen cognitive impairment, providing a new imaging strategy for the early precise diagnosis and treatment of PD.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".