Processing of thermal images to detect breast cancer: comparison with previous work
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
In the early 1980s, thermography began to be used to detect pain and breast cancer. However, the images were interpreted through the naked eye, and thus subtle differences were difficult to identify. More recently, widespread use of PCs led to the application of computer processing to the analysis of thermal images. For example, Head et al. (1997) reported three methods to calculate temperature differences between the right and left breast to help detect and diagnose breast cancer. Their analysis of 13 patients had better results with their 3/sup rd/ method than with their methods 1 and 2, but still showed 3 false positives out of 10 patients who were diagnosed as "normal" and 1 false negative out of 3 patients diagnosed with cancer. We applied these authors' three techniques to nine of our patients (6 with a diagnosis of normal and 3 with cancer) and found that only method 3 provided reliable results. With the lower threshold of 1/spl deg/C suggested by Head et al., we had 2 false positives. However, when we raised the threshold to of normalcy to 1.5/spl deg/C (instead of 1), we found no false negatives or false positives on this sample of nine patients. Future work should focus on improving the third approach and find new ways of enhancing differences, which would be significant for a correct diagnosis. These preliminary results are encouraging but a properly designed prospective clinical trial needs to be done to show if this technique can play a useful role in the future or not.
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.
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 | 0.001 |
| 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) | 0.001 | 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 it