Leveraging Spatial and Temporal Features using CNN-LSTM for Improved Bone Fracture Classification from X-ray Images
Bibliographic record
Abstract
X-ray imaging remains the primary diagnostic tool for identifying bone fractures. Accurate classification of bone fractures from X-ray images is a critical task in the field of orthopedic diagnosis and treatment. However, this task poses several challenges due to the complex and variable nature of fracture patterns, as well as the need to consider the temporal progression of fracture healing. Traditional convolutional neural network (CNN) architectures, while effective in extracting spatial features from X-ray images, may not be sufficient to capture the dynamic and sequential aspects of fracture healing. In this work, we propose an improved Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) architecture to address the limitations of CNN-only models in bone fracture classification. The proposed method aims to leverage the strengths of both CNNs and LSTMs to enhance the classification performance. The CNN component of the network is responsible for extracting relevant visual features from the X-ray images, while the LSTM layers are used to model the temporal relationships between these features, which are crucial for understanding the progression of fracture healing. Experimental results on a dataset of X-ray images of bone fractures demonstrate the superior performance of the CNN-LSTM architecture compared to traditional CNN-based approaches with 97.33%
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) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".