Diagnosis of Alzheimer's Disease with Deep Convolutional Neural Networks Using FDG-PET Brain Images
Bibliographic record
Abstract
Early detection is crucial to prevent the progression of Alzheimer's disease (AD). Thus, specialists can begin preventive treatment as soon as possible. They require prompt and accurate diagnosis of AD in its earliest and most difficult-to-detect stages. The main objective of this work is to develop a system that automatically detects the presence of the disease using one of the most successful models of deep learning (DL), namely convolutional neural networks (CNNs). Using a smaller dataset, we design and train several enhanced CNNs based on transfer learning (TL) to analyze fluorodeoxyglucose positron emission tomography (FDG-PET) brain images and classify them into different AD stages. The obtained results show the effectiveness of the selected CNNs based on InceptionV3 and ResNetV2 networks as well as their hybrid Inception-ResNetV2 architecture. Especially, experiment on the Alzheimer's disease neuroimaging initiative dataset demonstrates the superiority of Inception-ResNet model compared to the other state-of-the-art TL approaches in terms of accuracy, precision, sensitivity, F1-score and area under the ROC curve. This architecture has achieved an accuracy of (83.9, 70.3, 87.4)% and F1-score of (89.7, 72.3, 87.4)% for (AD, mild impairment, normal cognitive) stages. Thus, even though there isn't a lot of data available, the FDG-PET image data and DL's powerful modeling technique can extract features that doctors can use to make decisions about how to treat complex AD disorders.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 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".