Interpretability of deep neural networks used for the diagnosis of Alzheimer's disease
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Abstract Alzheimer's disease (AD) is a chronic brain disorder and is the most common cause of dementia. Patients suffering from AD experience memory loss, confusion, and other cognitive and behavioral complications. As the disease progresses, these symptoms become severe enough to interfere with the patient's daily life. Since AD is an irreversible disease and existing treatments can only slow down its progress, early diagnosis of AD is a key moment in fighting this disease. In this article, we propose a novel approach for diagnosing AD via deep neural networks from magnetic resonance imaging images. Additionally, we propose three new propagation rules for the layer‐wise relevance propagation (LRP) method, which is a method used for visualizing evidence in deep neural networks to obtain a better understanding of the network's behavior. We also propose various rule configurations for the LRP to achieve better interpretability of the network. Our proposed classification method achieves a 92% accuracy when classifying AD versus healthy controls, which is comparable to state‐of‐the‐art approaches and could potentially aid doctors in AD diagnosis and reduce the occurrence of human error. Our proposed visualization approaches also show improvements in evidence visualization, which helps the spread of computer‐aided diagnosis in the medical domain by eliminating the “black‐box” nature of the neural networks.
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.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 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 it