Automated Detection of Knee Osteoarthritis Using CNN with Adaptive Moment Estimation
Bibliographic record
Abstract
In deep learning, particularly with convolutional neural networks (CNNs), overfitting is a common challenge, especially when training data is scarce.CNNs usually need large amounts of training data to avoid overfitting when working with new datasets.However, there is often not enough disease data available.To address this, using the right architecture is crucial for accurate disease prediction.In this study, we optimized our models using the adaptive moment estimation (ADAM) algorithm, which efficiently handles multiple parameters and requires less memory.The test scenario was structured with two primary objectives.The first objective was to evaluate the regularization and convergence of the CNN classifier model.A model is deemed convergent when it attains an acceptable level of error and regularization.The second objective was to assess the overall performance of the model utilizing metrics such as accuracy, precision, recall, and F1-score.We compared five CNN architectures and found that ShuffleNet achieved the highest accuracy at 98%, followed by EfficientNet at 96% and MobileNet at 93%.Although these architectures showed similar performance, the quality of input images significantly affects disease localization.Additionally, deep learning models are sensitive to noise, which can hinder performance.Future efforts will focus on enhancing prediction accuracy, class imbalance and model robustness.
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) | 0.001 | 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 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".