Diversity, inclusivity and traceability of mammography datasets used in development of Artificial Intelligence technologies: a systematic review
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
PURPOSE: There are many radiological datasets for breast cancer, some which have supported the development of AI medical devices for breast cancer screening and image classification. This review aims to identify mammography datasets (including digitised screen film mammography, 2D digital mammography and digital breast tomosynthesis) used in the development of AI technologies and present their characteristics, including their transparency of documentation, content, populations included and accessibility. MATERIALS AND METHODS: MEDLINE and Google Dataset searches identified studies describing AI technology development and referencing breast imaging datasets up to June 2024. The characteristics of each dataset are summarised. In particular, the accompanying documentation was reviewed with a focus on diversity and inclusion of populations represented within each dataset. RESULTS: 254 datasets were referenced in the literature search, 190 were privately held, 36 had barriers which prevented access, and 28 were accessible. Most datasets originated from Europe, East Asia and North America. There was poor reporting of individuals' attributes: 32 (12 %) datasets reported race or ethnicity; 76 (30 %) reported female/male categories with only one dataset explicitly defining whether these categories represented sex or gender attributes. CONCLUSION: Through this review, we demonstrate gaps in the data landscape for mammography, highlighting poor representation globally. To ensure datasets in breast imaging have maximum utility for researchers, their characteristics should be documented and limitations of datasets, such as their representativeness of populations and settings, should inform scientific efforts to translate data-driven insights into technologies and discoveries.
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.
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 | 0.006 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.003 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.002 | 0.008 |
| 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 it