PFP-LHCINCA: Pyramidal Fixed-Size Patch-Based Feature Extraction and Chi-Square Iterative Neighborhood Component Analysis for Automated Fetal Sex Classification on Ultrasound Images

<div>Receiver operating characteristic curves of the classifiers used in the model. AUC: area under curve; kNN: k-nearest neighbor; LD: linear discriminant; NB: naïve Bayes; SVM: support vector machine; DT: decision tree. (a) kNN, 0.99, (b) LD. (c) NB, 0.89. (d) SVM, 0.98. (e) DT, 0.88.</div>

Contrast Media & Molecular Imaging

fig4

Figure 4

Figure 4: PFP-LHCINCA: Pyramidal Fixed-Size Patch-Based Feature Extraction and Chi-Square Iterative Neighborhood Component Analysis for Automated Fetal Sex Classification on Ultrasound Images 

Figure 4 | PFP-LHCINCA: Pyramidal Fixed-Size Patch-Based Feature Extraction and Chi-Square Iterative Neighborhood Component Analysis for Automated Fetal Sex Classification on Ultrasound Images 