Microwave breast Cancer detection and sequential inference with particle flow
Bibliographic record
Abstract
Microwave breast screening has been proposed as a complementary modality to conventional screening modalities including mammography.Microwave techniques involve no ionization radiation, cause minimal discomfort, and can be fabricated inexpensively.This offers women the opportunity to conduct self-screening on a more regular basis.With frequent screening, the assessment burden on the radiologist becomes unreasonable.The aim of this thesis is to develop detection algorithms customized for automatic breast cancer screening based on microwave scans.The original contributions can be organized into two categories.First, we propose cost-sensitive ensemble detection algorithms for microwave breast cancer detection.We design three ensemble detection structures to fuse information from different antenna pairs to detect abnormalities in the breast.A principled Neyman-Pearson approach is developed to allow the control of the trade-off between the false positive rate and the false negative rate.We evaluate performance using data derived from measurements of heterogeneous breast phantoms and data collected in a clinical trial that monitored 12 healthy patients monthly over an eight-month period.Second, breast cancer screening can be formulated as a sequential inference task involving high-dimensional data.Accordingly, we study and develop novel sequential inference techniques that are effective when applied to high-dimensional models.These techniques are based on recently proposed particle flow filters.We modify particle flow procedures to construct invertible particle flows, which allows efficient evaluation of the proposal densities in a particle filtering framework.We also use clustering to further reduce the computational cost of the flow procedure, and incorporate the invertible particle flow into a Sequential Markov chain Monte Carlo (SMCMC) framework that significantly improves the performance of the state-of-the-art SMCMC algorithm in examined highdimensional filtering settings.
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) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| 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 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".