A Hybrid Deep Learning Pipeline for Melanoma Detection Using Modified U-Net and VGG-19 Features
Bibliographic record
Abstract
Melanoma, the deadliest form of skin cancer, remains challenging to detect early due to lesion variability and diagnostic subjectivity. Artificial Intelligence (AI), particularly deep learning, offers promising avenues to enhance diagnostic accuracy and automation. In this study, we propose a robust hybrid AI framework for automated melanoma detection, integrating deep segmentation and supervised classification techniques. A custom U-Net architecture is employed for precise lesion segmentation, supported by preprocessing operations including data augmentation, class balancing, contrast enhancement, normalization, and resizing. High-level discriminative features are extracted using transfer learning from pre-trained Convolutional Neural Networks (CNNs), and dimensionality reduction is applied via Principal Component Analysis (PCA) to improve classifier efficiency. We evaluate multiple supervised classifiers, with Nu-Support Vector Machine (NuSVM) achieving the best performance. Experimental results on the PH2 and HAM10000 datasets demonstrate the effectiveness of the proposed framework, with Dice segmentation scores of 96.6% and 95.3%, and classification accuracies of 90.44% and 96.87%, respectively. These results highlight the potential of combining deep segmentation models with optimized feature-based classifiers to enhance the reliability and scalability of melanoma diagnosis 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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".