Multimodal Analysis of Unbalanced Dermatological Data for Skin Cancer Recognition
Bibliographic record
Abstract
To date, skin cancer is the most commonly diagnosed form of cancer in humans and is one of the leading causes of death in cancer patients. AI technologies can match and exceed visual analysis methods in accuracy, but they carry the risk of a false negative response when a malignant pigmented lesion can be recognized as benign. Possible ways to improve accuracy and reduce the risk of false negatives are to analyze heterogeneous data, combine different preprocessing methods, and use modified loss functions to eliminate the negative impact of unbalanced dermatological data. The article proposes a multimodal neural network system with a modified cross-entropy loss function that is sensitive to unbalanced heterogeneous dermatological data. The novelty of the proposed system lies in the emerging synergy when using methods to improve the quality of intelligent systems, due to which there is a significant reduction in the number of false negative predictions and an increase in the accuracy of skin cancer recognition. Preliminary cleaning of hair structures on visual data, as well as parallel analysis of heterogeneous dermatological data using a multimodal neural network system sensitive to unbalanced data, were used as methods to improve accuracy. The recognition accuracy for 10 diagnostic categories for the proposed intelligent system was 85.20%. The introduction of weighting factors made it possible to reduce the number of false negative forecasts, as well as increase the accuracy by 1.99-4.28 percentage points compared to the original multimodal systems.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| 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 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".