Automated Melanoma Screening: A Machine Learning Pipeline for Mole Detection, Boundary Segmentation, and ABCD(E) Feature Extraction

Early detection of suspicious moles remains the most effective means of reducing mortality from skin cancer, yet systematic screening is constrained by the time and expertise required for manual mole assessment. This paper presents an end-to-end computational pipeline that utilizes wide-angle skin photographs (including consumer-grade smartphone images) and produces quantitative ABCD (Asymmetry, Border irregularity, Color variegation, Diameter) feature scores for every detected mole. The pipeline operates in four stages: mole detection via adaptive thresholding and blob analysis, super-resolution enhancement using EDSR, false-positive filtering using a brightness-based statistical criterion, and lesion segmentation using the Boundary Attention Mapper (BAM). BAM generates high-resolution segmentation masks by fusing early-layer activations with GradCAM heatmaps from a trained EfficientNet-B7 classifier, achieving 90.45% accuracy on the ISIC2017 dataset, outperforming both conventional GradCAM (87.78%) and dedicated segmentation architectures, including DeepLabv3 and SAM v2 by more than 5 percentage points in Dice score. The EfficientNet-B7 backbone achieves a micro-average AUC of 0.97 across eight lesion classes, with a melanoma AUC of 0.99. Color quantification uses K-means clustering with a threshold calibrated on the PH2 dataset (MSE = 1.425). Applied to 87 wide-angle images, the mole detection module achieved an F1 score of 86%. The system outputs a structured CSV of per-lesion ABCD scores suitable for clinical triage and longitudinal tracking. A clinical validation study with dermatologists and surgeons is underway to assess concordance between automated and expert assessments.