Skip to main content

Table 2 Results of the confusion matrix analysis of the four convolutional neural network models for overall healthy and benign cases

From: Convolutional neural network-based vocal cord tumor classification technique for home-based self-prescreening purpose

 

TP

FP

FN

TN

Acc

Pre

Rec

Spe

F1

Mask-50

359

181

80

1324

0.8657

0.6648

0.8178

0.8797

0.7334

Mask-101

357

318

95

1251

0.7956

0.5289

0.7898

0.7973

0.6335

Yolo-4

317

42

70

1423

0.9395

0.8830

0.8191

0.9713

0.8499

SSD-MN

233

45

151

1419

0.8939

0.8381

0.6068

0.9693

0.7039

  1. Bold values in the table represent the cases of the lowest error (lowest in false negative) and the best performance (highest in F1-score) among the four models
  2. TP true-positive, FP false-positive, FN false-negative, TN true-negative, Acc accuracy, Pre precision, Rec recall, Spe specificity F1 F1-score
Back to article page

BioMedical Engineering OnLine

ISSN: 1475-925X

Contact us