Characterization and pattern recognition of color images of dermatological ulcers: a pilot study
Bibliographic record
Abstract
We present color image processing methods for the char\-ac\-te\-ri\-za\-tion of images of dermatological lesions for the purpose of content-based image retrieval (CBIR) and computer-aided di\-ag\-no\-sis. The intended application is to segment the images and perform classification and analysis of the tissue composition of skin lesions or ulcers, in terms of granulation (red), fibrin (yel\-low), necrotic (black), callous (white), and mixed tissue composition. The images were analyzed and classified by an expert dermatologist following the red-yellow-black-white model. Automatic segmentation was performed by means of clustering using Gauss\-ian mixture modeling, and its performance was evaluated by deriving the Jaccard coefficient between the automatically and manually segmented images. Statistical texture features were derived from cooccurrence matrices of RGB, HSI, L$^*$a$^*$b$^*$, and L$^*$u$^*$v$^*$ color components. A retrieval engine was implemented using the k-nearest-neighbor classifier and the Euclidean, Man\-hat\-tan, and Chebyshev distance metrics. Classification was performed by means of a metaclassifier using logistic regression. The average Jaccard coefficient after the segmentation step between the automatically and manually segmented images was 0.560, with a standard deviation of 0.220. The performance in CBIR was mea\-sured in terms of precision of retrieval, with average values of up to 0.617 obtained with the Chebyshev distance. The metaclassifier yielded an average area under the receiver operating char\-ac\-ter\-is\-tic curve of 0.772.
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 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".