The team of Professor Frédérique Capron, head of the Pathology Department at Pitié-Salpêtrière Hospital in Paris, France, has selected and annotated a set of breast cancer biopsy slides for this contest. The slides are stained with standard hematoxylin and eosin (H&E) dyes and they have been scanned by two slide scanners: Aperio Scanscope XT and Hamamatsu Nanozoomer 2.0-HT.
In each slide, the pathologists selected several frames at X20 magnification located inside tumours. These X20 frames are used for scoring nuclear atypia. The X20 frames have been subdivided into four frames at X40 magnification. The X40 frames are used to annotate mitosis and to give a score to six criteria related to nuclear atypia. Dimensions of frames are given in table 1.
| Scanner | Aperio Scanscope XT | Hamamatsu Nanozoomer 2.0-HT |
| Resolution at X40 | 0.2455 µm per pixel |
0.227299 µm per pixel (horizontal) 0.227531 µm per pixel (vertical) |
| Dimensions of a X20 frame |
1539 × 1376 pixels 755.649 × 675.616 µm2 |
1663 × 1485 pixels 755.996474 × 675.76707 µm2 |
| Dimensions of a X40 frame |
1539 × 1376 pixels 377.8245 × 337.808 µm2 |
1663 × 1485 pixels 377.998237 × 337.883535 µm2 |
The number of frames is variable from slide to slide. In the training data set there are 284 frames at X20 magnification and 1,136 frames at X40 magnification. The frames are RGB bitmap images in TIFF format. For X20 magnification frames, we provide the nuclear atypia score as a number 1, 2 or 3. Score 1 denotes a low grade atypia, score 2 a moderate grade atypia, and score 3 a high grade atypia. This score has been given independently by two different senior pathologists. There are some frames for which the pathologists disagree and gave a different score.
For the X40 magnification frames, we provide the following data:
- List of mitosis given by two different pathologists. The pathologists have annotated mitosis as true mitosis, probably a mitosis, or not a mitosis. In case of disagreement between the pathologists, a third pathologist gave his opinion and the object has been marked as mitosis or not mitosis according to the majority.
- Six criteria given by three junior pathologists to evaluate the nuclear atypia. The criteria for nuclear atypia are provided as a number 1, 2 or 3. Only the consensus value among the three pathologists is given for each criterion. The six criteria are described in table 2. They are provided as a guideline to help contestants for designing their algorithm for nuclear atypia scoring. Contestants are free to use one or more of these criteria, or to design and use their own criteria for nuclear atypia scoring.
| Criterion | Score | Description |
| Size of nuclei |
1 2 3 |
0 to 30% of tumour nuclei are bigger than normal nuclei 30 to 60% of tumour nuclei are bigger than normal nuclei more than 60% of tumour nuclei are bigger than normal nuclei |
| Size of nucleoli |
1 2 3 |
0 to 30% of tumour cells have nucleoli size bigger than nucleoli of normal cells 30 to 60% of tumour cells have nucleoli size bigger than nucleoli of normal cells more than 60% of tumour cells have nucleoli size bigger than nucleoli of normal cells |
| Density of chromatin |
1 2 3 |
0 to 30% of tumour cells have chromatin density higher than normal cells 30 to 60% of tumour cells have chromatin density higher than normal cells more than 60% of tumour cells have chromatin density higher than normal cells |
|
Thickness of nuclear membrane |
1 2 3 |
0 to 30% of tumour cells have nuclear membrane thickness higher than normal cells 30 to 60% of tumour cells have nuclear membrane thickness higher than normal cells more than 60% of tumour cells have nuclear membrane thickness higher than normal cells |
|
Regularity of nuclear contour |
1 2 3 |
0 to 30% of tumour cells have nuclear contour more irregular than normal cells 30 to 60% of tumour cells have nuclear contour more irregular than normal cells more than 60% of tumour cells have nuclear contour more irregular than normal cells |
|
Anisonucleosis
(size variation within |
1 2 3 |
within the population of tumour cells, all nuclei are regular and/or nuclei size is not bigger than twice the size of normal epithelial cell nuclei for cases that are not fitting neither with case 1 nor with case 3 within the population of tumour cells, either nuclei size are irregular or nuclei size is bigger than 3 times the size of normal epithelial cell nuclei |