MétaCan
Menu
Back to cohort
Record W2617301898

EVALUATING MICROWAVE BREAST IMAGES

2015· article· en· W2617301898 on OpenAlexaffvenue
Yilin Zhao, Elise Fear

Bibliographic record

VenueJournal of undergraduate research in Alberta · 2015
Typearticle
Languageen
FieldEngineering
TopicMicrowave Imaging and Scattering Analysis
Canadian institutionsUniversity of Calgary
Fundersnot available
KeywordsImage qualityMicrowave imagingArtificial intelligenceLuminanceComputer scienceHuman visual system modelComputer visionMetric (unit)Medical imagingPattern recognition (psychology)MicrowaveMathematicsImage (mathematics)Telecommunications
DOInot available

Abstract

fetched live from OpenAlex

INTRODUCTION Microwave imaging shows potential in medical applications such as tracking breast tumors [1]. It is advantageous over some of the other modalities such as MRI due to its relatively low cost, non-ionizing nature, and non-invasiveness [1]. The Tissue Sensing Adaptive Radar (TSAR) system is developed for microwave breast imaging and acquires reflected signals as an antenna scans the subject at a number of locations [2]. Then, the data is processed and an image is formed using a delay and sum focusing method [2]. The TSAR imaging algorithm involves many parameters, but the effect of each parameter on the image is unclear. Some parameters, such as wave speed (related to permittivity), are difficult to estimate and often inaccurate. A lack of objective image evaluation metrics makes it difficult to determine the magnitude of the effect of a parameter. The structural similarity (SSIM) index is a tool for objective image quality assessment [3]. It is known for its simplicity and relevance to the human visual system [3]. The SSIM index evaluates how similar two images are by modelling the difference as a weighted product of three independent parameters: luminance, contrast, and structure [3]. This study evaluates if the SSIM index is a suitable metric for evaluating microwave breast images. The dominance of each component of the SSIM Index is also investigated. METHODS In this study, the effectiveness of the SSIM index is evaluated by changing parameters in the TSAR imaging algorithm, then comparing the image produced to the known reference image using the built-in MATLAB ssim function. Both simulated data and experimental data are investigated. Parameters investigated include wave speed in different regions (using permittivity) and different methods to reduce the dominant reflection from the skin. RESULTS The SSIM index is observed to be indicative of the degree of similarities in microwave images. In the cases tested, structure generally has been the most dominant component while contrast is often the least dominant component (Figure 1). Maps of local SSIM index, luminance, contrast, and structure values proved useful in identifying areas of change. The SSIM index indicated that skin permittivity has the least effect on imaging while interior permittivity is important to be within 10-15%. These observations match expectations. DISCUSSION AND CONCLUSIONS The SSIM index looks promising as a suitable image quality metric for microwave breast imaging. It provides an objective and numerical method of evaluating similarity and change between different microwave images. In the future, an improved SSIM index could help identify the effect of some parameters in the TSAR algorithm and optimize the imaging process.

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 imitation

Not 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.

metaresearch head score (Codex)0.004
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.404
Threshold uncertainty score0.532

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0040.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.109
GPT teacher head0.390
Teacher spread0.281 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

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".

Quick stats

Citations0
Published2015
Admission routes2
Has abstractyes

Explore more

Same venueJournal of undergraduate research in AlbertaSame topicMicrowave Imaging and Scattering AnalysisFrench-language works237,207