Role of ultra-high frequency ultrasound in the clinical and prognostic management of cutaneous melanoma
Bibliographic record
Abstract
Background: Cutaneous malignant melanoma (MM) derives from the malignant transformation of melanocytes and is one of the most aggressive malignant skin tumors. Ultra-high frequency ultrasound (UHFUS) represents a non-invasive new tool for the diagnosis and follow-up of skin lesions, including melanocytic naevi (MN) and MM. Objective: The first aim of our study is to evaluate the correspondence between the ultrasonographic thickness and the Breslow thickness in melanoma using VevoMD (Fujifilm, Visualsonics, Toronto, Canada). Moreover, we included in the first aim an evaluation of the intra- and inter-operator repeatability in the ultrasonographic measurements of MM depth. The second aim is to use machine-learning approaches to calculate the diagnostic performance of UHFUS as a diagnostic tool for the differential diagnosis of MN and MM. Materials and Methods: In order to achieve the first aim, we retrospectively analyzed 27 MM in a population of 27 patients who had an ultrasonographic examination of a suspected lesion before the surgical removal. B-mode images were obtained by one experienced dermatologist by using UHFUS equipped with a 70 MHz linear probe were. The images were then analyzed off-line by two skilled and blinded operators in order to evaluate intra- and inter-session repeatability, as well as inter-operator variability and Intra-Class Correlation (ICC) coefficients. The second aim was achieved by the examination of 20 MM and 19 MN whose B-Mode images were processed for calculating 8 morphological parameters and 122 texture parameters. Color-Doppler (CD) images were used to evaluate the vascularization. Features reduction was implemented by means of Principal Component Analysis (PCA) and 23 classification algorithms were tested on the reduced features using histological response as ground-truth. Results: We observed an excellent agreement between the Breslow thickness of MM and the ultrasonographic thickness measured with VevoMD. We also pointed out a reduced intra- and inter-operator variability (coefficient of variation value: 6,5%; ICC: 0.99) in the ultrasonographic measurements of melanoma depth. Moreover, through the use of our machine learning approach, we obtained optimal results using the first component of the PCA and the weighted k-nearest neighbor classifier; this combination led to accuracy of 76.9%, area under the ROC curve of 83%, sensitivity of 84% and specificity of 70%. Conclusions: We conclude that we may consider UHFUS as a complementary evaluation in MM clinical and prognostic management and that UHFUS images processing using a machine-learning approach could represent a valid future tool. In particular, we propose a protocol which may help clinicians to reduce the diagnostic delay, perform a surgical excision with negative margins, reduce the variability in the assessment of Breslow thickness and reduce the number of repetitive surgeries.
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 | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| 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".