Novel multiple markers to distinguish melanoma from dysplastic nevi

Abstract

Background: Distinguishing melanoma from dysplastic nevi can be challenging.

Objective: To assess which putative molecular biomarkers can be optimally combined to aid in the clinical diagnosis of melanoma from dysplastic nevi.

Methods: Immunohistochemical expressions of 12 promising biomarkers (pAkt, Bim, BRG1, BRMS1, CTHRC1, Cul1, ING4, MCL1, NQO1, SKP2, SNF5 and SOX4) were studied in 122 melanomas and 33 dysplastic nevi on tissue microarrays. The expression difference between melanoma and dysplastic nevi was performed by univariate and multiple logistic regression analysis, diagnostic accuracy of single marker and optimal combinations were performed by receiver operating characteristic (ROC) curve and artificial neural network (ANN) analysis. Classification and regression tree (CART) was used to examine markers simultaneous optimizing the accuracy of melanoma. Ten-fold cross-validation was analyzed for estimating generalization error for classification.

Results: Four (Bim, BRG1, Cul1 and ING4) of 12 markers were significantly differentially expressed in melanoma compared with dysplastic nevi by both univariate and multiple logistic regression analysis (p < 0.01). These four combined markers achieved 94.3% sensitivity, 81.8% specificity and attained 84.3% area under the ROC curve (AUC) and the ANN classified accuracy with training of 83.2% and testing of 81.2% for distinguishing melanoma from dysplastic nevi. The classification trees identified ING4, Cul1 and BRG1 were the most important classification parameters in ranking top-performing biomarkers with cross-validation error of 0.03.

Conclusions: The multiple biomarkers ING4, Cul1, BRG1 and Bim described here can aid in the discrimination of melanoma from dysplastic nevi and provide a new insight to help clinicians recognize melanoma.

Figure 1. Representative images of immunochemistry staining of dysplastic nevi and melanoma.

(a) Dysplastic nevi with strong BRMS1 staining; (b) Dysplastic nevi with weak Cul1 staining; (c) Melanoma with weak BRMS1 staining; (d) Melanoma with strong Cul1 staining. Magnification, ×200.

Figure 2. ROC curve for 4-markers (ING4-Cul1-BRG1-Bim, purple curve), 3-markers (ING4-Cul1- BRG1, green curve) and 2-marker (ING4-Cul1, blue curve).

Figure 3. Architecture and performance of ANN. (a)

ANN architecture. The network consisted of three layers: Input (boxes 1–12), hidden (circles 1–6) and output (group 1: dysplastic nevi, group 2: melanoma) layer, respectively. (b) ANN predicted-by-observed performance chart. The box plots represent the predicted-pseudo-probabilities for the output category; dysplastic nevi (blue) and melanoma (green) plotted against the known clinical status for dysplastic nevi and melanoma. (c) The ROC curve for dysplastic nevi and melanoma separately.

Figure 4. Classification tree of ING4, Cul1, BRG1 and Bim biomarkers for dysplastic nevi and melanoma.

Nevi, dysplastic nevi; PM+MM, primary and metastatic melanoma.

Figure 5. Classification tree of Cul1, ING4 and CTHRC1 biomarkers for dysplastic nevi and primary melanoma.

Nevi, dysplastic nevi; PM, primary melanoma.

Figure 6. Classification tree for ING4, Cul1 and BRMS1 biomarkers for dysplastic nevi and metastatic melanoma.

Nevi, dysplastic nevi; MM, metastatic melanoma.