Table 2 Results of persistent homology application combined with supervised algorithms with different k-fold cross-validation value for the classification of Gleason score 4 of cancerous prostate gland images
From: Machine learning techniques on homological persistence features for prostate cancer diagnosis
k-fold/method | LDA | NBC | SVM | DTC | RF | |||||
|---|---|---|---|---|---|---|---|---|---|---|
Accuracy (%) | AUC | Accuracy (%) | AUC | Accuracy (%) | AUC | Accuracy (%) | AUC | Accuracy (%) | AUC | |
K = 2 fold (\({\raise0.7ex\hbox{$1$} \!\mathord{\left/ {\vphantom {1 2}}\right.\kern-\nulldelimiterspace} \!\lower0.7ex\hbox{$2$}}\) training \({\raise0.7ex\hbox{$1$} \!\mathord{\left/ {\vphantom {1 2}}\right.\kern-\nulldelimiterspace} \!\lower0.7ex\hbox{$2$}}\) testing) | 43.4 | 0.4781 | 42.4 | 0.4346 | 61.6 | 0.8117 | 97.8 | 0.9871 | 76.6 | 0.8445 |
K = 3 fold (\({\raise0.7ex\hbox{$2$} \!\mathord{\left/ {\vphantom {2 3}}\right.\kern-\nulldelimiterspace} \!\lower0.7ex\hbox{$3$}}\) training \({\raise0.7ex\hbox{$1$} \!\mathord{\left/ {\vphantom {1 3}}\right.\kern-\nulldelimiterspace} \!\lower0.7ex\hbox{$3$}}\) testing) | 43.6 | 0.4782 | 42.8 | 0.4410 | 63.4 | 0.8152 | 97. 4 | 0.9821 | 77.8 | 0.8493 |
K = 4 fold (\({\raise0.7ex\hbox{$3$} \!\mathord{\left/ {\vphantom {3 4}}\right.\kern-\nulldelimiterspace} \!\lower0.7ex\hbox{$4$}}\) training \({\raise0.7ex\hbox{$1$} \!\mathord{\left/ {\vphantom {1 4}}\right.\kern-\nulldelimiterspace} \!\lower0.7ex\hbox{$4$}}\) testing) | 45.1 | 0.4884 | 43.5 | 0.4431 | 67.1 | 0.8233 | 97.9 | 0.9867 | 76.8 | 0.8353 |
K = 5 fold (\({\raise0.7ex\hbox{$4$} \!\mathord{\left/ {\vphantom {4 5}}\right.\kern-\nulldelimiterspace} \!\lower0.7ex\hbox{$5$}}\) training \({\raise0.7ex\hbox{$1$} \!\mathord{\left/ {\vphantom {1 5}}\right.\kern-\nulldelimiterspace} \!\lower0.7ex\hbox{$5$}}\) testing) | 46.3 | 0.4921 | 44.8 | 0.4780 | 67.5 | 0.8291 | 97.1 | 0.9819 | 76.5 | 0.8348 |