Table 1 MatQuantify measures 19 properties of a segmented ROI
No. | Image property | Definition |
|---|---|---|
1 | Area | The number of pixels inside the region containing the ROI (mitotic spindle). |
2 | Convex area | The number of pixels inside the convex hull of an ROI. This is the smallest convex polygon that contains the region of interest. |
3 | Compactness | The degree to which a shape is compact, calculated using the formula: \( Compactness=\frac{Area}{Perimeter^2} \) |
4 | Eccentricity | An ROI can fit into an ellipse, and the roundness of the ellipse is identified by its eccentricity. The value ranges from 0 to 1. A value of 0 corresponds to a circle, while a line has an eccentricity of 1. |
5 | Entropy | A statistical measure of randomness characterises the texture of an image. It can be defined as: Entropy = − ∑ p. ∗ log 2(p) .* syntax means that an element in the first matrix is multiplied by the corresponding element in the second matrix. |
6 | Euler number | The number of objects in the region minus the number of holes in those objects, where holes are black pixels in the region of a binary image. |
7 | Fractal dimension | Returns the Haussdorf fractal dimension of an object represented by the binary image. Pixels with non-zero intensity belong to an object and pixels with zero intensity constitute the background. |
8 | Intensity (mean) | The mean intensity of all the grey-scale values in an ROI. |
9 | Intensity (median) | The median intensity of all the grey-scale values in an ROI. |
10 | Intensity (total) | The sum of all grey-scale values in an ROI. |
11 | Major axis length | The length (in pixels) of the major axis of the ellipse that completely encompasses the region. |
12 | Minor axis length | The length (in pixels) of the minor axis of the ellipse that completely encompasses the region. |
13 | Orientation | The angle between the x-axis and the major axis of the ellipse. The value ranges from −90° to 90°. |
14 | Percent density | The number of pixels that have an intensity value greater than 90% of the maximum pixel intensity value divided by the total area (in pixels). |
15 | Perimeter | The distance around the boundary of the region. |
16 | Solidity | The proportion of pixels in the convex hull that are also in the region. \( Solidity=\frac{Area}{Convex Area} \) |
17 | Standard deviation | The standard deviation of all the grey-scale values in an ROI. |
18 | Extent | The ratio of the total pixels in an ROI to the total pixels in the bounding box. \( Extent=\frac{AreaofROI}{AreaofBoundingBox} \) The bounding box is the smallest rectangle that encompasses the region. |
19 | Satellites | The number of satellite objects (additional poles) identified by the algorithm. |