Applying Transfer Learning Based Deep Models on Structural and Functional Brain Images to Predict Alzheimer's Disease
Bibliographic record
Abstract
Alzheimer's disease (AD) destroys brain cells and can even cause death in older people. Therefore, diagnosis in the early stages is essential for proper treatment. Computer-aided diagnosis based on machine learning has become an accessible and suitable tool. However, the majority of traditional models focus on binary classification and utilize multi-step architectures, which are intricate and heavily reliant on human experts. This paper presents deep architectures that eliminate the need for handcrafted feature generation and significantly improve the process for accurate diagnosis. We design and train several enhanced convolutional neural networks (CNNs) based on transfer learning (TL) using smaller datasets to analyze neuroimaging scans and classify them into different AD stages. These CNNs are tested on the ADNI and OASIS benchmark datasets and found to outperform the best TL methods with regard to accuracy, precision, recall, f1-score and area under the ROC curve. The results show that NASNetLarge achieves finest performance, outperforming comparative models such as NASNet-Mobile, Inception-ResNetV2, and InceptionV3.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".