Machine learning for the identification of decision boundaries during the transition from radial to vertical growth phase superficial spreading melanomas
التفاصيل البيبلوغرافية
العنوان:
Machine learning for the identification of decision boundaries during the transition from radial to vertical growth phase superficial spreading melanomas
The objective of this study was to compute threshold values for the diameter of superficial spreading melanomas (SSMs) at which the radial growth phase (RGP) evolves into an invasive vertical growth phase (VGP). We examined reports from 1995 to 2019 of 834 primary SSMs. All the patients underwent complete surgical removal of the tumor and the diagnosis was confirmed after histologic examination. Machine learning was used to compute the thresholds. For invasive non-naevus-associated SSMs, a threshold for the diameter was found at 13.2 mm (n = 634). For the lower limb (n = 209) the threshold was at 9.8 mm, whereas for the upper limb (n = 117) at 14.1 mm. For the back (n = 106) and the trunk (n = 173), the threshold was at 16.2 mm and 17.1 mm, respectively. When considering non-naevus-associated and naevus-associated SSMs together (n = 834) a threshold for the diameter was found at 16.8 mm. For the lower limb (n = 248) the threshold was at 11.7 mm, whereas for the upper limb (n = 146) at 16.4 mm. For the back (n = 170) and the trunk (n = 236), the threshold was at 18.6 mm and 14.1 mm, respectively. Thresholds for various anatomic locations and for each gender were defined. They were based on the diameter of the melanoma and computed to suggest a transition from RGP to VGP. The transition from a radial to a more invasive vertical phase is detected by an increase of tumor size with a numeric cutoff. Besides the anamnestic, clinical and dermatoscopic findings, our proposed approach may have practical relevance in vivo during clinical presurgical inspections.