The Added Value of Statistical Modeling of Backscatter Properties in the Management of Breast Lesions at US
Bibliographic record
Abstract
PURPOSE: To develop a classification method based on the statistical backscatter properties of tissues that can be used as an ancillary tool to the usual Breast Imaging Reporting and Data System (BI-RADS) classification for solid breast lesions identified at ultrasonography (US). MATERIALS AND METHODS: This study received institutional review board approval, and all subjects provided informed consent. Eighty-nine women (mean age, 50 years; age range, 22-82 years) with 96 indeterminate solid breast lesions (BI-RADS category 4-5; mean size, 13.2 mm; range, 2.6-44.7 mm) were enrolled. Prior to biopsy, additional radiofrequency US images were obtained, and a 3-second cine sequence was used. The research data were analyzed at a later time and were not used to modify patient management decisions. The lesions were segmented manually, and parameters of the homodyned K distribution (α, k, and μn values) were extracted for three regions: the intratumoral zone, a 3-mm supratumoral zone, and a 5-mm infratumoral zone. The Mann-Whitney rank sum test was used to identify parameters with the best discriminating value, yielding intratumoral α, supratumoral k, and infratumoral μn values. RESULTS: The 96 lesions were classified as follows: 48 BI-RADS category 4A lesions, 16 BI-RADS category 4B lesions, seven BI-RADS category 4C lesions, and 25 BI-RADS category 5 lesions. There were 24 cancers (25%). The area under the receiver operating characteristic curve was 0.76 (95% confidence interval: 0.65, 0.86). Overall, 24% of biopsies (in 17 of 72 lesions) could have been spared. By limiting analysis to lesions with a lower likelihood of malignancy (BI-RADS category 4A-4B), this percentage increased to 26% (16 of 62 lesions). Among benign lesions, the model was used to correctly classify 10 of 38 fibroadenomas (26%) and three of seven stromal fibroses (43%). CONCLUSION: The statistical model performs well in the classification of solid breast lesions at US, with the potential of preventing one in four biopsies without missing any malignancy.
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 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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".