Table 1 Number of different types of objects in the integrated dataset

From: A deep learning framework deploying segment anything to detect pan-cancer mitotic figures from haematoxylin and eosin-stained slides

Dataset

Tumour types

Number of images

Number of MFs

Number of MLFs

Non-MF objects

ICPR

Breast carcinoma

100

654

0

10,696

TUPAC

Breast carcinoma

73

1999

10,483

233,992

MIDOG++

Breast carcinoma

Lung carcinomaa

Lymphosarcomaa

Neuroendocrine tumoura

Mast cell tumoura

Melanoma

Soft tissue sarcomaa

392

9470

11,433

559,827

CMC

Breast carcinomaa

21b

13,907

36,379

2,428,456

CCMCT

Mast cell tumoura

32b

40,190

42,208

1,082,776

STMF

Soft tissue tumour

103b,c + 226d

8400

5035

395,670

Total

 

938

74,620

105,538

4,701,417

  1. aCanine Specimens.
  2. bWSIs rather than selected regions.
  3. cpHH3-immunohistochemistry was used for identifying MFs.
  4. dActive learning was used for annotating MFs.