Table 4 Classification results for osteoarthritis severity of each knee compartment using support vector machine classifier with sigmoid kernel.

From: Using magnetic resonance imaging-based subregional texture analysis models to classify knee osteoarthritis severity by compartment

 

Accuracy

Sensitivity

Specificity

Precision

F-measure

ROC AUC

Medial compartment

 FS-PDWI

0.735

0.550

0.784

0.554

0.538

0.739

 PDWI

0.772

0.599

0.810

0.570

0.557

0.743

 Combination of FS-PDWI and PDWI

0.777

0.609

0.818

0.584

0.581

0.791

Lateral compartment

 FS-PDWI

0.620

0.587

0.655

0.621

0.611

0.633

 PDWI

0.595

0.629

0.559

0.595

0.612

0.560

 Combination of FS-PDWI and PDWI

0.599

0.591

0.607

0.600

0.599

0.643

P-FT compartment

 FS-PDWI

0.562

0.534

0.592

0.562

0.553

0.527

 PDWI

0.624

0.612

0.637

0.626

0.623

0.646

 Combination of FS-PDWI and PDWI

0.673

0.675

0.670

0.675

0.677

0.695

  1. FS-PDWI fat-suppressed proton density-weighted imaging, PDWI proton density-weighted imaging, P-FT articulation between patella and femoral trochlea.
Back to article page