Background: Imaging-based logistic models are widely used for non-invasive risk stratification; however, their structural robustness and transportability across heterogeneous biological contexts remain insufficiently examined. Purpose: This study aimed to develop a simulation-based stress-testing framework to evaluate the structural robustness and transportability of a radiology-adapted logistic risk model across distinct cutaneous lesion phenotypes under both aligned and structurally perturbed conditions. Methods: A simulation-based methodological framework was implemented using three synthetic cohorts representing nodular, subcutaneous, and vascular lesion phenotypes (n = 2000 per cohort). Model performance was evaluated under naïve transfer, recalibration, and revision conditions. To address potential structural alignment bias, additional simulation scenarios incorporating coefficient perturbations, nonlinear transformations, and interaction effects were used to generate outcome processes partially independent from the original model structure. Model performance was assessed using discrimination (ROC-AUC, PR-AUC), calibration metrics, decision curve analysis, and Monte Carlo-based stability assessments. Results: Under naïve transfer, discrimination remained stable across phenotypes (ROC-AUC ≈ 0.78–0.84). Calibration shifts were observed but were effectively corrected through recalibration. Under structurally perturbed outcome generation, discrimination showed only modest reduction, while overall performance patterns remained consistent. Structural variables demonstrated high transferability, whereas vascular features exhibited phenotype-dependent variability. Decision curve analysis indicated consistent clinical utility across relevant thresholds. Conclusions: The radiology-adapted logistic model demonstrated structural robustness across heterogeneous phenotype conditions, with performance variations driven primarily by calibration differences rather than structural failure. Importantly, robustness was preserved under conditions of structural perturbation, supporting the model’s stability beyond idealized alignment assumptions. These findings suggest that simulation-based stress-testing frameworks provide a rigorous methodological approach for evaluating model transportability prior to large-scale clinical validation.

Background: Pigmented superficial skin lesions pose a persistent diagnostic challenge due to overlapping clinical and dermoscopic appearances between benign and malignant entities. While histopathology remains the gold standard, there is growing interest in non-invasive imaging models that can preoperatively stratify malignancy risk. This methodological pilot study was designed to explore the feasibility and initial diagnostic performance of a novel radiology-adapted logistic regression approach. To develop and preliminarily evaluate a new logistic model integrating both structural (lesion size, depth) and vascular (Doppler patterns) ultrasonographic features for non-invasive risk stratification of pigmented superficial skin lesions. Material and Methods: In this prospective single-center pilot investigation, 44 patients underwent standardized high-frequency grayscale and Doppler ultrasound prior to excisional biopsy. Lesion size, depth, and vascularity patterns were systematically recorded. Three logistic regression models were constructed: (1) based on lesion size and depth, (2) based on vascularity patterns alone, and (3) combining all parameters. Model performance was assessed via ROC curve analysis. Intra-observer reliability was determined by repeated measurements on a random subset. Results: The lesion size and depth model yielded an AUC of 0.79, underscoring the role of structural features. The vascularity-only model showed an AUC of 0.76. The combined model demonstrated superior discriminative ability, with an AUC of approximately 0.85. Intra-observer analysis confirmed excellent repeatability (κ > 0.80; ICC > 0.85). Conclusions: This pilot study introduces a novel logistic framework that combines grayscale and Doppler ultrasound parameters to enhance non-invasive malignancy risk assessment in pigmented superficial skin lesions. These encouraging initial results warrant larger multicenter studies to validate and refine this promising approach.