Table 1 Dataset distribution of the image-level annotated TMAs cores and SICAPv2 WSIs used, and the patches with patch-level annotations used for each of the datasets.
From: Enhanced hierarchical attention mechanism for mixed MIL in automatic Gleason grading and scoring
Image-level annotated | ||||||
|---|---|---|---|---|---|---|
Dataset | Benign | GS6 | GS7 | GS8 | GS9-10 | Total |
TMAs Cores | 115 | 272 | 141 | 218 | 140 | 886 |
SICAPv2 WSIs | 36 | 14 | 45 | 18 | 42 | 155 |
Patch-level annotated | ||||||
|---|---|---|---|---|---|---|
Dataset | Benign | GG3 | GG4 | GG5 | Total | |
TMAs | 3487 | 8946 | 7424 | 3610 | 23,467 | |
SICAPv2 | 11,069 | 10,784 | 2979 | 2767 | 27,599 | |
