Applying laser speckle images to skin science: skin lesion differentiation by polarization
Bibliographic record
Abstract
Skin cancer is a worldwide health problem. It is the most common cancer in the countries with a large white population; furthermore, the incidence of malignant melanoma, the most dangerous form of skin cancer, has been increasing steadily over the last three decades. There is an urgent need to develop in-vivo, noninvasive diagnostic tools for the disease. This paper attempts to response to the challenge by introducing a simple and fast method based on polarization and laser speckle. The degree of maintaining polarization estimates the fraction of linearly maintaining polarization in the backscattered speckle field. Clinical experiments of 214 skin lesions including malignant melanomas, squamous cell carcinomas, basal cell carcinomas, nevi, and seborrheic keratoses demonstrated that such a parameter can potentially diagnose different skin lesion types. ROC analyses showed that malignant melanoma and seborrheic keratosis could be differentiated by both the blue and red lasers with the area under the curve (AUC) = 0.8 and 0.7, respectively. Also malignant melanoma and squamous cell carcinoma could be separated by the blue laser (AUC = 0.9), while nevus and seborrheic keratosis could be identified using the red laser (AUC = 0.7). These experiments demonstrated that polarization could be a potential in-vivo diagnostic indicator for skin diseases.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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 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".