Thermography-based Breast Abnormality Detection using Pre-Trained RadImageNet Models
Bibliographic record
Abstract
With breast cancer accounting for a large number of cancer-related deaths worldwide, there exists a need to develop tools and imaging modalities that aid in the early detection of breast abnormalities. While mammography is considered the standard imaging modality for breast cancer diagnosis, it cannot be used on pregnant women and is not as effective with denser breasts. Thermography, which is a non-invasive and radiation-free technique, is an adjunct tool to help detect breast abnormalities. Various pre-trained models have been applied to breast thermograms in the literature to detect breast abnormalities. This is a preliminary study that explores the use of pre-trained models trained on a medically sourced database like RadImageNet, in the analysis of breast thermograms from the Database for Mastology Research (DMR). Models trained from medically-sourced databases like RadImageNet have been known to extract features and patterns more relevant for medical imaging analysis and classification. In this study, the performances of RadImageNet models were compared with models trained on non-medically sourced databases, like ImageNet. Preliminary findings suggest that ImageNet models outperform their equivalent RadImageNet models. This preliminary study emphasizes the importance of using relevant and targeted datasets for the development of models that aid in breast abnormality detection.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| 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) | 0.002 | 0.001 |
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".