Automated spectroscopic tissue classification in colorectal surgery Table 8.2 Classification performance of selected Si‐detector features LOO CV TP TN Sensitivity Specificity PPV NPV Accuracy Ureter – Adipose tissue 7/7 9/9 100 (56‐100) 100 (63‐100) 100 (56‐100) 100 (63‐100) 100 Artery – Adipose tissue 9/10 9/9 90 (54‐99) 100 (63‐100) 100 (63‐100) 90 (54‐99) 95 TP = true positive; TN = true negative numbers indicate identified tissue spots. A positive test is defined as the tissue observed being either ureter or artery; a negative test is defined as the tissue observed being adipose tissue. Sensitivity; specificity; PPV = positive predictive value; NPV = negative predictive value; accuracy numbers are percentages; numbers in parentheses indicate 95% confidence interval. LOO CV = leave‐one‐out cross–validation. Figure 8.6 A) Box plots of selected features within InGaAs‐range. 119 A B Ureter versus adipose tissue: box plot showing selected feature, amplitude difference Ft35. B) Box plots of selected features within InGaAs‐range. Artery versus adipose tissue: box plot showing selected feature, gradients Ft13. Table 8.3 Classification performance of selected InGaAs‐detector features LOO CV TP TN Sensitivity Specificity PPV NPV Accuracy Ureter – Adipose tissue 7/7 9/9 100 (56‐100) 100 (63‐100) 100 (56‐100) 100 (63‐100) 100 Artery – Adipose tissue 9/10 8/9 90 (54‐99) 89 (51‐99) 90 (54‐99) 89 (51‐99) 89 TP = true positive; TN = true negative numbers indicate identified tissue spots. A positive test is defined as the tissue observed being either ureter or artery; a negative test is defined as the tissue observed being adipose tissue. Sensitivity; specificity; PPV = positive predictive value; NPV = negative predictive value; accuracy numbers are percentages; numbers in parentheses indicate 95% confidence interval. LOO CV = leave‐one‐out cross–validation.
proefschrift_Schols_SLV
To see the actual publication please follow the link above