Table 1.
The number of CT samples used for training for each class collected by four different hospitals A, B, C, and D. Besides, details of the CC-CCII dataset are also listed, which was used in the independent testing stage. The ratio of positive and negative samples in training set is approximately 1:1, and 2:1 in test dataset.
| Dataset | Number of patients |
Number of CT images |
Subset | ||||
|---|---|---|---|---|---|---|---|
| Total | Positive | Negative | Total | Positive | Negative | ||
| Hospital A | 424 | 0 | 424 | 24,670 | 0 | 24,670 | Train |
| Hospital B | 58 | 58 | 0 | 5,512 | 5,512 | 0 | Train |
| Hospital C | 17 | 17 | 0 | 2,611 | 2,611 | 0 | Train |
| Hospital D | 305 | 305 | 0 | 12,374 | 12,374 | 0 | Train |
| CC-CCII [8] | 2,034 | 1,320 | 714 | 130,511 | 84,629 | 45,882 | Test |