Machine Learning Model Development for Malignant Prostate Lesion Prediction Using Texture Analysis Features from Ultrasound Shear-Wave Elastography

Keyphrases

• Prostate Lesions 100%
• Shear Wave Elastography 100%
• Texture Analysis 100%
• Model-driven Development 100%
• Malignant Tissue 100%
• Machine Learning Models 100%
• Lesion Prediction 100%
• Region of Interest 75%
• Texture Features 75%
• First-order 50%
• Reconstructed Image 50%
• Support Vector Machine 50%
• Machine Learning 50%
• Shear Wave Imaging 50%
• Random Forest 50%
• Gray Level 50%
• Prediction Accuracy 25%
• Learning Development 25%
• High Sensitivity 25%
• High Specificity 25%
• Prostate Cancer 25%
• Diagnostic Accuracy 25%
• Detection Accuracy 25%
• Cancer Tissue 25%
• Model Support 25%
• Prostate Tissue 25%
• High Performance 25%
• Classification Performance 25%
• Machine Learning Techniques 25%
• Artificial Intelligence 25%
• Gray-level Co-occurrence 25%
• Level Dependence 25%
• Machine Learning Algorithms 25%
• Condition-dependent 25%
• B-mode Image 25%
• B-mode 25%
• Benign Prostate Disease 25%
• Higher Classification 25%
• Grayscale 25%
• US Imaging 25%
• 5-fold Cross Validation 25%
• Enhanced Detection 25%
• Second-order Features 25%
• GLRLM 25%
• Naïve Bayes 25%
• Nave Bayes 25%
• Quantitative Texture 25%
• Ultrasound B-mode 25%
• Pure Shear 25%
• Texture Feature Analysis 25%

Engineering

• Texture Analysis 100%
• Shear Wave 100%
• Learning System 100%
• Grey Level 66%
• Texture Feature 66%
• Region of Interest 50%
• Reconstructed Image 33%
• Random Forest 33%
• Support Vector Machine 33%
• Statistically Significant Difference 16%
• Classification Performance 16%
• Grayscale 16%
• Run Length 16%
• Cooccurrence Matrix 16%
• Machine Learning Technique 16%
• Machine Learning Algorithm 16%
• Artificial Intelligence 16%
• Pure Shear 16%