Sensitivity of a Direct Computer-aided Detection System in Full-field Digital Mammography for Detection of Microcalcifications Not Associated with Mass or Architectural Distortion
Bibliographic record
Abstract
PURPOSE: The purpose of this study was to evaluate the sensitivity of a direct computer-aided detection (CAD) system (d-CAD) in full-field digital mammography (FFDM) for the detection of microcalcifications not associated with mass or architectural distortion. MATERIALS AND METHODS: A database search of 1063 consecutive stereotactic core biopsies performed between 2002 and 2005 identified 196 patients with Breast Imaging-Reporting and Data System (BI-RADS) 4 and 5 microcalcifications not associated with mass or distortion detected exclusively by bilateral FFDM. A commercially available CAD system (Second Look, version 7.2) was retrospectively applied to the craniocaudal and mediolateral oblique views in these patients (mean age, 59 years; range, 35-84 years). Breast density, location and mammographic size of the lesion, distribution, and tumour histology were recorded and analysed by using chi(2), Fisher exact, or McNemar tests, when applicable. RESULTS: When using d-CAD, 71 of 74 malignant microcalcification cases (96%) and 101 of 122 benign microcalcifications (83%) were identified. There was a significant difference (P < .05) between CAD sensitivity on the craniocaudal view, 91% (68 of 75), vs CAD sensitivity on the mediolateral oblique view, 80% (60 of 75). The d-CAD sensitivity for dense breast tissue (American College of Radiology [ACR] density 3 and 4) was higher (97%) than d-CAD sensitivity (95%) for nondense tissue (ACR density 1 and 2), but the difference was not statically significant. All 28 malignant calcifications larger than 10 mm were detected by CAD, whereas the sensitivity for lesions small than or equal to 10 mm was 94%. CONCLUSIONS: D-CAD had a high sensitivity in the depiction of asymptomatic breast cancers, which were seen as microcalcifications on FFDM screening, with a sensitivity of d-CAD on the craniocaudal view being significantly better. All malignant microcalcifications larger than 10 mm were detected by d-CAD.
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 | 0.002 | 0.014 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".