Skip to main content

Table 1 The classification results of manually and automatically segmented nodules

From: Distinguishing Adenocarcinomas from Granulomas in the CT scan of the chest: performance degradation evaluation in the automatic segmentation framework

Annotation

Feature Set

AUC

Manual

4 Selected Features (\(FS_{nv}\))

0.8874

Manual

2 Selected Texture Features (\(FS_n\)) by [9]

0.8595

Manual

2 Selected tortuosity Features by [8] (\(FS_v\))

0.7333

Manual

3 Selected Shape Features by [4] (\(FS_s\))

0.6342

The Automatic Framework [5]

\(FS_{nv}\)

0.7583

The Automatic Framework [5]

\(FS_n\)

0.7211

The Automatic Framework [5]

\(FS_v\)

0.6756

The Automatic Framework [5]

\(FS_s\)

0.5444