Differentiating Dementia with Lewy Bodies and Alzheimer's Disease by Deep Learning to Structural MRI
Bibliographic record
Abstract
BACKGROUND AND PURPOSE: Dementia with Lewy bodies (DLB) is the second most prevalent cause of degenerative dementia next to Alzheimer's disease (AD). Though current DLB diagnostic criteria employ several indicative biomarkers, relative preservation of the medial temporal lobe as revealed by structural MRI suffers from low sensitivity and specificity, making them unreliable as sole supporting biomarkers. In this study, we investigated how a deep learning approach would be able to differentiate DLB from AD with structural MRI data. METHODS: Two-hundred and eight patients (101 DLB, 69 AD, and 38 controls) participated in this retrospective study. Gray matter images were extracted using voxel-based morphometry (VBM). In order to compare the conventional statistical analysis with deep-learning feature extraction, we built a classification model for DLB and AD with a residual neural network (ResNet) type of convolutional neural network architecture, which is one of the deep learning models. The anatomically standardized gray matter images extracted in the same way as for the VBM process were used as inputs, and the classification performance achieved by our model was evaluated. RESULTS: Conventional statistical analysis detected no significant atrophy other than fine differences on the middle temporal pole and hippocampal regions. The feature extracted by the deep learning method differentiated DLB from AD with 79.15％ accuracy compared to the 68.41% of the conventional method. CONCLUSIONS: Our results confirmed that the deep learning method with gray matter images can detect fine differences between DLB and AD that may be underestimated by the conventional method.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| 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) | 0.001 | 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 source (direct Gemma or distilled Codex), 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".