Table 5 Illustrates the performance of the proposed model compared to existing pre-trained state-of-the-art architectures.

From: Intelligent diagnostic model for malaria parasite detection and classification using imperative inception-based capsule neural networks

Models

Accuracy

Sensitivity

Specificity

AUC-ROC

F1-score

VGG16

0.9603

0.9567

0.9640

0.9920

0.9560

VGG19

0.9597

0.9560

0.9632

0.9910

0.9550

Inception V3

0.9280

0.9250

0.9302

0.9760

0.9251

ResNet50 V2

0.9390

0.9356

0.9408

0.9410

0.9820

Xception

0.9470

0.9420

0.9480

0.9792

0.9439

DenseNet121

0.9562

0.9482

0.9650

0.9901

0.9480

MobileNetV2

0.9483

0.9420

0.9552

0.9880

0.9478

Capsule net

0.9518

0.9500

0.9514

0.9900

0.9498

Proposed

0.9935

0.9957

0.9912

0.9973

0.9936

Back to article page