Table 7 The provide confusion matrix outline the classification outcomes for DME, CNV, DRUSEN, and NORMAL achieved by utilizing a reinforcement-based approach along with INCEPTIONRESNETV2 in the above experiment.

From: Reinforcement-based leveraging transfer learning for multiclass optical coherence tomography images classification

Ground Truth

 

Normal

CNV

DME

Drusen

Precision

F1-(Score)

Average (specificity and recall)

Output Classes

       

Normal

248

0

0

2

1.0000

0.9912

 

CNV

0

247

3

0

0.9913

0.9918

 

DME

1

1

248

0

1.0000

0.9921

 

Drusen

0

3

0

247

0.9929

0.9930

 

Recall

0.9910

0.9901

1.0000

0.9976

  

0.9946

Specificity

1.0000

0.9914

1.0000

0.9822

  

0.9934

Average F1(Score) and Precision

    

0.9960

0.9920

 

Accuracy

0.9920

      
Back to article page