A YOLO and Transformer-based Smart Scan Framework for Lung Disease Identification in Radiographic Imaging
Bibliographic record
Abstract
Accurate and timely diagnosis of lung disease using radiographic imaging continues to pose a formidable obstacle for contemporary healthcare systems, especially in low-resource settings where radiologist personnel are in limited supply. This study introduces a hybrid Smart Scan Framework, integrating a real-time, YOLO-based object detector with Transformer-driven attention modelling to achieve robust lung disease classification. The architecture first employs a custom fine-tuned YOLOv8 backbone to precisely delineate lung boundaries and to localize suspected lesions, after which a Vision Transformer module quantifies long-range spatial dependencies that refine diagnostic determination. To enhance feature observability in sub-optimal chest X-rays, the pipeline employs preprocessing techniques including Contrast-Limited Adaptive Histogram Equalization and Gaussian blur suppression. Rigorous experimentation on the CheXpert benchmark shows that the integrated system delivers a detection mean Average Precision of 96.4% and a classification accuracy of 94.7%, exceeding the performance of conventional convolutional neural networks, standalone YOLO, or Transformer approaches. The architecture further accelerates inference, processing 42 frames per second, and lowers the false-positive rate by 18% relative to the baselines, facilitating rapid and dependable triage within clinical workflows. These performance metrics position the Smart Scan Framework as a leading solution for automated lung disease screening, with compelling applicability across hospital settings and portable diagnostic units.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".