AI Quantified Tissue Factors from Breast MRI and the Risk of Breast Cancer
Bibliographic record
Abstract
To improve high-risk Breast Cancer (BCa) screening, patients must be classified into more specific subgroups based on tissue factors found in breast Magnetic Resonance (MR) imaging. Screening programs often adopt a universal approach for high-risk women, which may not account for individual risk levels. For example, it has been observed that high-risk women with BRCA1 mutations have a greater likelihood of developing tumours quickly and experiencing interval cancers compared to women with a family history but no confirmed genetic mutation. Because these patientsare typically screened with MR imaging, breast density and Background Parenchymal Enhancement (BPE), a measure of blood circulation and hormonal exposure, can aid in assessing the risk of BCa in high-risk women. Some significant challenges are the absence of an accurate quantitative method and the necessity to examine fluctuations during menopause. At Sunnybrook Research Institute, we have the unique opportunity to analyze personalized tissue trends in a high-risk screening group receiving annual MR imaging screenings, including patients who have undergone 10 or more years of the program. We aim to develop proper measurement tools, investigate longitudinal fluctuations, and measure risk on a case-control dataset from this database. By utilizing large language models, patient records and radiology reports were analyzed comprehensively. Validated AI models and quantitative methods were developed, exhibiting a strong correlation with radiologist interpretations. It was uncovered that post-menopausal women at high risk face a strong risk for BCa associated with both quantitative density and BPE, as quantitative measurements decrease over menopause. These results could aid in developing personalized screening guidelines and assisting in complex preventative decisions like chemoprevention, prophylacticmastectomy or oophorectomy. These advancements have the potential to enhance the quality of care for women who are at risk of developing BCa.
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 | 0.003 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| 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".