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
| Â | Sensitivity | Specificity |
|---|---|---|
Classification tree model | 81Â % (65/80) | 93Â % (167/179) |
Cross-validated model | 75Â % (60/80) | 93Â % (167/179) |
| Â | Correctly classified | Â |
All sites | 90Â % (232/259) | Â |
Ductal carcinoma in situ (DCIS) | 96Â % (25/26) | Â |
Invasive ductal cancer (IDC) | 92Â % (34/37) | Â |
Invasive lobular carcinoma (ILC) | 35Â % (6/17) | Â |