MITOS Dataset
Prof. Frédérique Capron and Dr. Catherine Genestie, two experienced pathologists from the Pitié-Salpêtrière Hospital in Paris, France, provided for this contest a set of 5 breast cancer biopsy slides. The slides are stained with hematein and eosin (H&E). In each slide, the pathologists selected 10 high power fields (HPF) at 40X magnification. A HPF has a size of 512 × 512 μm2 (that is an area of 0.262 mm2 ), which is the equivalent of a microscope field diameter of 0.58 mm. These 50 HPFs contain more than 300 mitosis in total. As there are several possible shapes for mitosis, it is necessary to have a large dataset to be able to cover all the cases. Two-third of the HPFs will be used for training purpose, the remaining third being for testing.
The slides of MITOS dataset have been scanned by three different equipments:
- a scanner A;
- a scanner H;
- and a 10 bands multi-spectral microscope M. The spectral bands are all in the visible spectrum. In addition, for each spectral band, the digitization has been performed at 17 different focus planes (17 layers Z-stack), each plane being separated from the other by 500 nm.
Scanner A has a resolution of 0.2456 μm per pixel. Scanner H has a slightly better resolution of 0.2273 μm (horizontal) and 0.22753 μm (vertical) per pixel, so a pixel of scanner H is not exactly a square. At last, multispectral microscope M has the best resolution of 0.185 μm per pixel. Table 1 shows the resolutions of the different scanners and the microscope. For example, a mitosis having an area of 30 μm2 will cover about 500 pixels of the image produced by scanner A, about 580 pixels of the image produced by scanner H, and about 880 pixels of the image produced by multispectral microscope M.
| Equipment | Resolution | Dimension of HPF to cover |
| Scanner A | 0.2456 μm per pixel | 2084 × 2084 pixels |
| Scanner H | 0.2273 μm horizontal and 0.22753 μm vertical per pixel |
2252 × 2250 pixels |
| Microscope M | 0.185 μm per pixel | 2767 × 2767 pixels |
For each slide, there is one RGB image produced by scanner A, one RGB image produced by scanner H, and 170 grey scale images for the multi-spectral microscope M (10 spectral bands and 17 layers Z-stack for each spectral band).
The pathologists have annotated mitosis manually in each selected HPF on the images generated by the scanner A, the scanner H and the multi-spectral microscope M.
