Euclidean Distance Skin Lesion

Hello everyone !!! I'm trying to evaluate the diameter of a skin lesion by evaluate the euclidean distances between all the pixels of the border and averaging it. How can i do it ?

Answer 1

[Walter Roberson]

You could regionprops and ask for MajorAxesLength to get "equivalent" diameter (an ellipse would be fitted to the data.)

I suspect that might be accurate enough for your purpose. If not then bwtraceboundary(), or regionprops pixellist . Then pdist(). And do not average the distances: take the maximum distance to get the diameter.

[ingeln91]

what do you mean for "equivalent" diameter ?

[Walter Roberson]

https://www.mathworks.com/help/images/ref/regionprops.html

'MajorAxisLength' Returns a scalar that specifies the length (in pixels) of the major axis of the ellipse that has the same normalized second central moments as the region.

Or, as I posted earlier "an ellipse would be fitted to the data"