Table 3 Performance of classification tree model for classification of neoplasia, non-neoplasia, and individual histologic types of breast neoplasia in confocal fluorescence images
From: Micro-anatomical quantitative optical imaging: toward automated assessment of breast tissues
| Sensitivity | Specificity | |
|---|---|---|
| Classification tree model | 81 % (65/80) | 93 % (167/179) |
| Cross-validated model | 75 % (60/80) | 93 % (167/179) |
| Correctly classified | ||
| All sites | 90 % (232/259) | |
| Ductal carcinoma in situ (DCIS) | 96 % (25/26) | |
| Invasive ductal cancer (IDC) | 92 % (34/37) | |
| Invasive lobular carcinoma (ILC) | 35 % (6/17) |