Advanced Transformer-Based Framework for Breast Cancer Detection in Ultrasound Imaging
Bibliographic record
Abstract
Ultrasound is a safe, radiation-free modality that is well suited to frequent screening in dense breasts, where it can distinguish cysts from solid masses and guide real-time biopsy. This work proposes a transformer-based classifier for breast ultrasound lesion diagnosis that captures long-range dependencies and directs attention to diagnostically relevant regions. Using the Breast Ultrasound Images Dataset, we compute 30 descriptive features (e.g., radius, texture, area) and model them as a sequence processed by an architecture comprising an Input layer, Layer Normalization, Multi-Head Self-Attention with residual (skip) connections, Dropout, Conv1D, Global Average Pooling, and a Dense classification head. The pipeline includes t-SNE for feature visualization and is benchmarked against conventional and ensemble learning classifiers. Across 5-fold cross-validation, the proposed model achieves a receiver operating characteristic (ROC) AUC of approximately 0.99 and an accuracy around 98%, with lower variance than the baselines, indicating both high discriminative power and stable generalization. These results highlight the promise of transformer attention for breast ultrasound and suggest potential for decision support in clinical workflows.
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) | 0.003 | 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".