Skip to main content
European Radiology Experimental

Table 1 Proportions of each class label in the Kaggle and CQ500 datasets

From: Evaluation of techniques to improve a deep learning algorithm for the automatic detection of intracranial haemorrhage on CT head imaging

 

Training (Kaggle dataset)

Test (CQ500 dataset)

No haemorrhage

12,862 (59.2%)

286 (58.2%)

Intracranial haemorrhage

8,882 (40.8%)

205 (41.8%)

EDH

354 (1.6%)

13 (2.6%)

ICH

5,321 (24.5%)

134 (27.3%)

IVH

3,692 (17.0%)

28 (5.7%)

SAH

3,932 (18.1%)

60 (12.2%)

SDH

3,812 (17.5%)

53 (10.8%)

  1. Data is provided in n volumetric scans (%)
  2. EDH Extradural haemorrhage, ICH Intracerebral haemorrhage, IVH Intraventricular haemorrhage, SAH Subarachnoid haemorrhage, SDH Subdural haemorrhage
Back to article page