ChestBioX-Gen: contextual biomedical report generation from chest X-ray images using BioGPT and co-attention mechanism
Bibliographic record
Abstract
Efficient and accurate radiology reporting is critical in modern healthcare for timely diagnosis and patient care. In this paper, we present a novel deep learning approach that leverages BioGPT and co-attention mechanisms for automatic chest X-ray report generation. Our model, termed “ChestBioX-Gen” is designed to bridge the gap between medical images and textual reports. BioGPT, a biological language model, contributes its contextual understanding to the task, while the co-attention mechanism efficiently aligns relevant regions of the image with textual descriptions. This collaborative combination enables ChestBioX-Gen to generate coherent and contextually accurate reports that embed complex medical findings. Our model not only reduces the burden on radiologists but also enhances the consistency and quality of reports. By automating the report generation process, ChestBioX-Gen contributes to faster diagnoses and improved patient care. Quantitative evaluations, measured through BLEU-N and Rouge-L metrics, demonstrate the model's proficiency in producing clinically relevant reports with scores of 0.6685, 0.6247, 0.5689, 0.4806, and 0.7742 on BLUE 1, 2, 3, 4, and Rouge-L, respectively. In conclusion, the integration of BioGPT and co-attention mechanisms in ChestBioX-Gen represents an advancement in AI-driven medical image analysis. As radiology reporting plays a critical role in healthcare, our model holds the potential to revolutionize how medical insights are extracted and communicated, ultimately benefiting both radiologists and patients.
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 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 | 0.001 | 0.000 |
| 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 | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".