Table 4 Results for the classification of abnormal images using GLCM and LBP features.

From: Lung cancer detection with machine learning classifiers with multi-attribute decision-making system and deep learning model

Classifier

Confusion Matrix

Sensitivity

Specificity

Precision

FI Score

Value

Accuracy

Training Loss

Testing Loss

KNN

\(\:\left[\begin{array}{cc}\begin{array}{cc}147&\:52\\\:81&\:142\end{array}&\:\begin{array}{cc}57&\:1\\\:62&\:0\end{array}\\\:\begin{array}{cc}47&\:41\\\:0&\:0\end{array}&\:\begin{array}{cc}73&\:4\\\:0&\:286\end{array}\end{array}\right]\)

0.6249

0.8846

0.6217

0.6217

0.8245

0

0.3953

Weighted KNN with k = 5

\(\:\left[\begin{array}{cc}\begin{array}{cc}167&\:73\\\:114&\:133\end{array}&\:\begin{array}{cc}36&\:1\\\:38&\:0\end{array}\\\:\begin{array}{cc}69&\:48\\\:0&\:0\end{array}&\:\begin{array}{cc}48&\:0\\\:0&\:286\end{array}\end{array}\right]\)

0.6318

0.8865

0.6421

0.6328

0.8305

0.2568

0.3792

SVM with RBF

\(\:\left[\begin{array}{cc}\begin{array}{cc}149&\:65\\\:8&\:159\end{array}&\:\begin{array}{cc}36&\:1\\\:43&\:2\end{array}\\\:\begin{array}{cc}36&\:45\\\:0&\:0\end{array}&\:\begin{array}{cc}81&\:3\\\:0&\:286\end{array}\end{array}\right]\)

0.6814

0.9020

0.6800

0.6796

0.8525

0

0.3702

Decision Tree

\(\:\left[\begin{array}{cc}\begin{array}{cc}165&\:45\\\:92&\:134\end{array}&\:\begin{array}{cc}50&\:3\\\:57&\:2\end{array}\\\:\begin{array}{cc}34&\:54\\\:2&\:2\end{array}&\:\begin{array}{cc}78&\:2\\\:1&\:281\end{array}\end{array}\right]\)

0.6337

0.8865

0.6297

0.6298

0.8280

0.0775

0.3943

Pruned Tree

\(\:\left[\begin{array}{cc}\begin{array}{cc}156&\:64\\\:91&\:136\end{array}&\:\begin{array}{cc}42&\:1\\\:56&\:2\end{array}\\\:\begin{array}{cc}3&\:54\\\:1&\:2\end{array}&\:\begin{array}{cc}72&\:2\\\:1&\:282\end{array}\end{array}\right]\)

0.6232

0.8829

0.6206

0.6212

0.8235

0.0805

0.3933

Decision Tree (all predictors)

\(\:\left[\begin{array}{cc}\begin{array}{cc}161&\:61\\\:71&\:169\end{array}&\:\begin{array}{cc}37&\:4\\\:41&\:4\end{array}\\\:\begin{array}{cc}32&\:58\\\:2&\:0\end{array}&\:\begin{array}{cc}75&\:0\\\:0&\:284\end{array}\end{array}\right]\)

0.6632

0.8966

0.6637

0.6632

0.8450

0.2233

0.3712

Naïve Bayes

\(\:\left[\begin{array}{cc}\begin{array}{cc}159&\:45\\\:85&\:131\end{array}&\:\begin{array}{cc}55&\:4\\\:64&\:5\end{array}\\\:\begin{array}{cc}27&\:24\\\:0&\:4\end{array}&\:\begin{array}{cc}112&\:2\\\:2&\:280\end{array}\end{array}\right]\)

0.6805

0.8964

0.6679

0.6662

0.8415

0.3970

0.3843

Naïve Bayse using Kernal

\(\:\left[\begin{array}{cc}\begin{array}{cc}161&\:47\\\:69&\:148\end{array}&\:\begin{array}{cc}54&\:1\\\:64&\:4\end{array}\\\:\begin{array}{cc}22&\:31\\\:2&\:4\end{array}&\:\begin{array}{cc}111&\:1\\\:0&\:280\end{array}\end{array}\right]\)

0.6958

0.9024

0.6853

0.6850

0.8505

0.3885

0.3823

Back to article page