Table 1 LSP vs. DS based texture homogeneity feature extraction and classification of lesions with various classifiers: multi-layer perceptron, fully connected multi-hidden layer NN, and SVM. 10-fold cross-validation is used. Results listed here are means of 10 random executions
From: Texture based skin lesion abruptness quantification to detect malignancy
Feature Extraction- Classification | Precision | Recall | Sensitivity | F1-Score |
|---|---|---|---|---|
LSP-Multilayer Perceptron NN | 0.82 | 0.81 | 0.75 | 0.8 |
DS-Multi Layer Perceptron NN | 0.77 | 0.76 | 0.56 | 0.74 |
LSP-SVM | 0.69 | 0.64 | 0.66 | 0.66 |
DS-SVM | 0.62 | 0.61 | 0.61 | 0.61 |
LSP-Fully-connected multi-layer NN | 0.86 | 0.87 | 0.78 | 0.87 |
DS-Fully-connected multi-hidden layer NN | 0.76 | 0.75 | 0.61 | 0.75 |