[vtkusers] Medical examples

[David Gobbi]

Yes, there are statistical methods that you can use to automatically
find the best thresholds between different tissue types in an image.
For example, K-means clustering.  ITK has several of these clustering
algorithms.  Or you can use vtkImageHistogramStatistics and set your
thresholds based on percentiles, if you know the approximate
proportions of the various tissue types that make up the image.

 - David

On Mon, Mar 4, 2013 at 7:43 AM, José M. Rodriguez Bacallao
<jmrbcu at gmail.com> wrote:
> there is an automated way to find those values?
>
>
> On Thu, Jun 2, 2011 at 1:10 PM, David Gobbi <david.gobbi at gmail.com> wrote:
>>
>> Hi Dora,
>>
>> The isovalues and color transfer functions in the medical examples are all
>> hard-coded for the intensity values of the example data.  You will have to
>> find out what values to use for your own data.
>>
>>  - David
>>
>>
>> On Wed, Jun 1, 2011 at 7:05 AM, Dora Szasz <dora.szasz at yahoo.com> wrote:
>> > Hello all,
>> > I have tried to use Medical examples with another set of Dicom images,
>> > but
>> > not works ok. Instead of seeing for example a skin, I see a strange
>> > volume.
>> > Can anyone tell me why and what should I change?
>> > Thank you!
>> > Dora