Training melanoma detection in photographs using the perceptual expertise training approach
Bibliographic record
Abstract
Although a deadly form of skin cancer, melanoma is treatable if detected early. Existing approaches in melanoma detection training employ a rule-based method where lesions are assessed by their Asymmetry, Border, Color, Diameter and Evolvement in appearance (i.e., the ABCDE rule). However, the rule-based training practices in melanoma detection were not effective. In the current study, we assessed an innovative way to train melanoma detection using the principles of perceptual expertise training. All participants first reviewed the ABCDE rules pamphlet, and were then given the Melanoma Detection Test (MDT) as the pre-test where they categorized a set of skin lesion images as either "melanoma" or "benign". Participants in the perceptual expertise training group received four training sessions where they were taught to categorize melanoma and benign lesions to 95% accuracy. Participants in the control group received no training. After training, all participants were retested with the same items on the MDT. As compared to the control group, the training group showed significant improvement in melanoma detection and a shifted response criterion from liberal (i.e., bias toward categorizing a lesion as melanoma) to neutral, and both improvements maintained a week after the training. These findings indicate that perceptual expertise training is a promising approach to train melanoma detection. Meeting abstract presented at VSS 2016
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 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".