Microwave breast cancer detection: Signal processing and device prototype
Bibliographic record
Abstract
Breast cancer, one of the primary causes of women mortality worldwide, can be effectively treated if detected at its early stage.Microwave Imaging (MWI), an emerging technique, promises to complement the currently used diagnostic modalities.It is safe, non-ionizing and potentially inexpensive, thus possessing key features to make it a good candidate for frequent and mass screenings.This thesis summarizes results of novel research done towards a prototype of a microwave device aimed at screening breast tissues.The author first presents the results of a research to combine Microwave Radar (MWR) breast imaging technique with Microwave-Induced Thermoacoustic (MWIT) imaging to improve tumor detection rate.An optimal rule for fusing information from the two modalities is developed and applied to numerically-simulated microwave and acoustic signals.The results demonstrate advantages of the hybrid method, compared to the MWR and MWIT methods used individually.Next, the thesis describes a research study to address the challenge of data acquisition in MWI.Recording microwave signals with high signal-to-noise ratio is either too expensive or suffers from numerous artifacts and measurement errors.The author presents studies aimed to improve the quality of collected time-domain data by minimizing the effect of phase uncertainties using software compensation.Finally, the thesis focuses on MWI algorithms.A comparative analysis of several existing time-domain MWI algorithms is accomplished to identify their advantages and weaknesses.This analysis yields important lessons on algorithm development in the light of the specific challenges presented by the MWI of the breast tissue.The author presents two improved MWI algorithms that address the identified drawbacks of the existing algorithms.The performance of the new algorithms is evaluated with experimentally-recorded data sets.I thank Prof. Mark Coates for co-supervising my research in the area of signal processing.His critical feedback was always valuable.I would like to acknowledge all members of our research group, with whom I collaborated: Emily Porter, Adam Santorelli, Guangran Kevin Zhu and Boris Oreshkin.I am happy to remember the days of our meetings, discussions and experiments with the equipment.Great support has been provided from the laboratory of telecommunications and signal processing: I highly appreciate all the help from Prof. Mike Rabbat for sharing the network cluster, which significantly accelerated our numerical computations.I was lucky to have helpful and cheerful lab mates.I am grateful to Tapabrata Mukherjee for his sincere friendship.I would like to thank Hussein Moghnieh for his warm welcome to the lab and further
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".