A Novel Radiology-Adapted Logistic Model for Non-Invasive Risk Stratification of Pigmented Superficial Skin Lesions: A Methodological Pilot Study

Abstract

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.

Keywords: Doppler ultrasound; high-frequency ultrasound; logistic regression; methodological pilot study; non-invasive diagnosis; novel logistic model; pigmented skin lesions; radiology-adapted risk stratification; vascularity patterns.

Figure 1

Representative images from a patient with histopathologically confirmed pigmented basal cell carcinoma (BCC). Panel (a) shows the clinical appearance of the lesion located on the inner lower lip, with ulceration and asymmetrical pigmentation. Panel (b) presents a magnified view highlighting the heterogeneous surface texture and crusted areas. Panel (c) displays a grayscale high-frequency ultrasound image demonstrating a hypoechoic, irregularly contoured subepidermal mass with ill-defined borders. Panel (d) shows color Doppler imaging with both central and peripheral vascular flow, suggestive of neovascularization. Panel (e) illustrates spectral Doppler analysis with a peak systolic velocity (PSV) of 30.6 cm/s and a resistive index (RI) of 0.648, indicating increased vascular resistance consistent with malignancy.

Figure 2

Receiver operating characteristic (ROC) curve for the radiology-adapted logistic model based on lesion size and depth. The black dashed line represents the reference line (AUC = 0.5), indicating no discriminative power.

Figure 3

Receiver operating characteristic (ROC) analysis based on vascularity pattern. The black dashed line represents the reference line (AUC = 0.5), indicating no discriminative power.

Figure 4

ROC curve for logistic model based on lesion size and depth (malignant vs. benign). The black dashed line represents the reference line (AUC = 0.5), indicating no discriminative power.

Figure 5

Receiver operating characteristic (ROC) curve for the vascularity-based logistic model distinguishing malignant and benign lesions.

Figure 6

ROC curve for combined logistic regression model incorporating lesion size, depth, and vascularity. The black dotted line represents the reference line (AUC = 0.5), indicating no discriminative power.