CNN–PVT: A Hybrid Deep Learning Model for Accurate Pneumonia Detection from Chest X-Rays
Bibliographic record
Abstract
Accurate detection of pneumonia from chest X-ray images is essential for early diagnosis and effective medical treatment. Traditional manual examination of X-rays is time-consuming and prone to human error. To classify whether the chest X-ray images are pneumonia or normal, a standalone CNN were used against a hybrid CNN– Pyramid Vision Transformer (CNN+PVT). The standalone CNN that extracts the local features in the image, whereas the PVT acquire the global contextual insight and long-range dependencies, thereby boosting the overall learning of the model. Five evaluation metrics which includes accuracy, precision, recall, F1-score, and AUC-ROC metrics were used to detect how well the model performs. The standalone CNN obtained a training accuracy of 96.59 %, testing accuracy of 71.96 % and validation accuracy of 97.02 %. On the other hand, the hybrid CNN+PVT obtained a training accuracy of 97.42 %, testing accuracy of 73.40 %, and validation accuracy of 97.13 %. This clearly indicates that the CNN+PVT model handles much complicated medical image effectively and the better proficiency of the hybrid model shows, the use of transformer-based attention mechanisms into convolutional networks supports more effective contextual and spatial learning. By the results, it can be stated that CNN+PVT delivers a more trustworthy and effective way to detect pneumonia from chest X-ray images.
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 | 0.001 |
| 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 | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".