Classifying Melanoma and Seborrheic Keratosis Automatically with Polarization Speckle Imaging
Bibliographic record
Abstract
Skin cancer is the most common cancer in western countries with a high incidence rate. Among all different types of skin cancers, malignant melanoma is the most fatal but has a promising prognosis if it is detected and treated at the early stages. However, melanoma often resemble to seborrheic keratosis (SK), a benign skin condition, and cause mis-diagnosis. Therefore, it is important to develop a framework with computer aided system and non-invasive techniques to assist in the clinical diagnosis of melanoma. In this study, we extend a recent polarization speckle imaging method based on depolarization rate and achieved automatic detection of melanoma by leveraging the power of machine learning strategies. We collected 143 malignant melanoma and seborrheic keratosis lesions. Different machine learning methods, including support vector machine, random forest and k-nearest neighbor, were employed for the classification between melanoma and seborrheic keratosis. In order to explore the impact of different light sources, we further compared the classification performance of depolarization rate with blue and red light sources using different classifiers. The results suggested that the most reliable classification performance was achieved by support vector machine, yielding a high accuracy of 86.31% and the most balanced performance between sensitivity and specificity. In addition, the depolarization rate with the blue light source demonstrated a consistently better performance than that with the red light source across different methods. Our promising classification performance shows evidence for the potentials of computer aided diagnosis of melanoma with polarization speckle imaging, providing an additional non-invasive in vivo tool for skin cancer detection which could benefit future clinical dermatology research.
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 | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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".