Bibliographic record
Abstract
Digital mammography was developed to address several technical limitations of screen film mammography with the goal of improving the accuracy of detecting breast cancer. The recent publication of the results of the ACRIN DMIST study has demonstrated such an improvement in a subset of women, notably, younger women and those with dense breasts. Nevertheless, the study also indicated that a significant fraction of cancers were not detected by either film or digital mammography. This is likely due to a number of reasons including the biology of the cancers, inadequate conspicuity of the lesions and variability of the skills of the radiologists. While it probably is not possible to detect all these cancers with mammography there are promising new techniques that can be developed on the platform of digital mammography to improve detection. One of these is computer‐aided detection, the use of computer artificial intelligence algorithms to identify patterns in the digital images that are suspicious for the presence of cancer. These provide some of the advantages of double reading of the mammograms (interpretation by two different radiologists), a process known to improve the sensitivity of cancer detection. Another new technique is contrast‐enhanced digital mammography (CEDM), which images leakage of an iodine contrast agent from microscopic vessels formed in the vicinity of a growing tumour. By imaging this tumour angiogenesis, cancers that are invisible on mammography might be seen. In addition, better information about the extent of the disease will be helpful in planning therapy. In mammography all of the anatomy in the 3‐dimensional breast is superimposed in two dimensions to form the image. Tomosynthesis and breast CT provide three‐dimensional images to separate the structures within the breast, possibly allowing tumors to be seen more easily and eliminating the overlap of structures from different parts of the breast that can falsely resemble a cancer. Telemammography can help improve the accessibility of high quality mammography in sparsely‐populated communities. In this presentation, the current status and the potential of these exciting new techniques will be considered. Disclosure: Martin Yaffe's laboratory carries out research on topics related to digital mammography in collaboration with GE Healthcare. Martin Yaffe is a member of the Scientific Advisory Board of XCounter. Educational Objectives: 1. Become familiar with current challenges in breast cancer imaging. 2. Learn about new techniques that are available or under development to address these challenges.
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 | 0.004 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".