[Insight-users] Re: Tumor Measurements..

[Lino Ramirez]

Luis and Simon,

Thank you very much for your advice and recommended readings.

I guess that I will have a nice reading and thinking time with the papers
about VALMET and STAPLE. I will keep you posted on how everything
progresses.

Have a nice day

Lino

> Luis Ibanez wrote:
>
>>
>> Hi Lino,
>>
>> The main two aspects that you may want to evaluate of a
>> segmentation method are:
>>
>> 1) Is it "at least" as repeatable as a human rater ?
>>
>> 2) Are its differences with a human rater smaller or
>> equal to the differences between two different raters ?
>>
>>>
>>>
>>> 4.- Do you know of any paper in which the authors present a
>>> comprehensive
>>> comparison of expert-made measurements with computer-generated
>>> measurements? I want to produce a tool that could be used in clinical
>>> practice and I think that the best way of convincing clinicians of the
>>> validity of the tool is providing a sound statistical analysis.
>>
>
> I think comparison to expert rater performance is an excellent way to
> determine if an algorithm is an acceptable replacement for an operator.
> There is some question as to exactly how such a comparison should be done.
>  I like the method described in the paper by Warfield, Zou and Wells
> 2004 IEEE TMI here:
> http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=pubmed&dopt=Abstract&list_uids=15250643
>
> http://splweb.bwh.harvard.edu:8000/~warfield/papers/2004/warfield-staple-tmi-in-press.pdf
>
>
> --
> Simon Warfield
>