<br>Well, the volume contains the knee within the boundaries. This means that at least<br>the outer slices have "no knee" bits in them. If a seed would be placed there, then<br>also "no knee" bits would be segmented as being "knee".<br>
<br>I'm considering in making an interactive seed placing window that places seeds down<br>all axes though, and give the user the option to remove seeds on the outer slices, <br>so it was a good suggestion you gave.<br>
<br>Michael<br><br><div class="gmail_quote">On Thu, Jan 14, 2010 at 2:11 PM, Mark Roden <span dir="ltr"><<a href="mailto:mmroden@gmail.com">mmroden@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
Hi Michael,<br>
<br>
Why not try seeding down some central axis in 3D? Why do everything<br>
one plane at a time, when you have a 3D volume already, and can just<br>
use that?<br>
<br>
Mark<br>
<br>
On Thu, Jan 14, 2010 at 2:59 AM, michiel mentink<br>
<div><div></div><div class="h5"><<a href="mailto:michael.mentink@st-hughs.ox.ac.uk">michael.mentink@st-hughs.ox.ac.uk</a>> wrote:<br>
> I was playing around yesterday with the slice I posted to this thread.<br>
><br>
> When placing one single seed, you can find the bone rather well, but there<br>
> is a big risk that the region spills over into the tissue surrounding the<br>
> bone.<br>
> I haven't experimented yet with placing multiple seeds.<br>
><br>
> If you look at the picture, you can see that the area surrounding the<br>
> cartilage is delimiting the bone very well, but the side of the bone does<br>
> not produce<br>
> sharp edges in the edge detect filter bit of this segmentation algorithm.<br>
><br>
> Also, I only tried one slice, and actually, I'd like to segment a complete<br>
> 3D volume of the bone. That means I have to place multiple seeds along the<br>
> bone and figure out some set of parameters that produces good results for<br>
> every slice.<br>
><br>
> I'm a bit weary about this type of segmentation but I'll continue<br>
> experimenting with it. Please let me know if you have<br>
> hints/tips/suggestions/experiences<br>
> regarding this.<br>
><br>
> Michael<br>
><br>
><br>
><br>
> On Wed, Jan 13, 2010 at 4:30 PM, marco giordano <<a href="mailto:marco.giord@gmail.com">marco.giord@gmail.com</a>><br>
> wrote:<br>
>><br>
>> Hi michiel,<br>
>><br>
>> I am also involved in solving a similar problem so I am interested in any<br>
>> possible solution.<br>
>><br>
>> I did not look at the values but it seems that the bones are well<br>
>> delimited and also quite homogeneous.<br>
>> If you can specify a seed easily (e.g by looking at the histogram) I would<br>
>> try with region growing first. The problem might be that the segmented<br>
>> region overgrows if the borders are not sharp.<br>
>><br>
>> Also watersheds should work but It will give you a complete segmentation,<br>
>> then you should select the region by yourself.<br>
>><br>
>> Level sets may also be an option but it might be too much for this case.<br>
>><br>
>> I would be curious to see the results, please share any experience.<br>
>><br>
>> Regards<br>
>><br>
>><br>
>> 2010/1/12 michiel mentink <<a href="mailto:michael.mentink@st-hughs.ox.ac.uk">michael.mentink@st-hughs.ox.ac.uk</a>><br>
>>>>><br>
>>>>> The images are made with MRI.<br>
>>>>> You can see the two bones in the middle.<br>
>>>>><br>
>>>>> Michael<br>
>>>>><br>
>>>>><br>
>>>>> On Tue, Jan 12, 2010 at 3:10 PM, siqi chen <<a href="mailto:siqichensc@gmail.com">siqichensc@gmail.com</a>><br>
>>>>> wrote:<br>
>>>>>><br>
>>>>>> If you can post one sample image, that would be helpful to determine<br>
>>>>>> which filter is the appropriate one.<br>
>>>>>><br>
>>>>>> Siqi<br>
>>>>>><br>
>>>>>> On Tue, Jan 12, 2010 at 10:08 AM, michiel mentink<br>
>>>>>> <<a href="mailto:michael.mentink@st-hughs.ox.ac.uk">michael.mentink@st-hughs.ox.ac.uk</a>> wrote:<br>
>>>>>>><br>
>>>>>>> Does anyone have experience with or know which segmentation algorithm<br>
>>>>>>> can be used<br>
>>>>>>> best for segmenting bones in a knee?<br>
>>>>>>><br>
>>>>>>> There are about 100 pages of segmentation algorithms in the ITK<br>
>>>>>>> software guide..<br>
>>>>>>><br>
>>>>>>> I have a DICOM volume I want to segment into a binary (labeled)<br>
>>>>>>> volume and ultimately<br>
>>>>>>> convert to a surface mesh of the individual bones.<br>
>>>>>>><br>
>>>>>>> thanks, Michael<br>
>>>>>>><br>
>>>>>>> _____________________________________<br>
>>>>>>> Powered by <a href="http://www.kitware.com" target="_blank">www.kitware.com</a><br>
>>>>>>><br>
>>>>>>> Visit other Kitware open-source projects at<br>
>>>>>>> <a href="http://www.kitware.com/opensource/opensource.html" target="_blank">http://www.kitware.com/opensource/opensource.html</a><br>
>>>>>>><br>
>>>>>>> Kitware offers ITK Training Courses, for more information visit:<br>
>>>>>>> <a href="http://www.kitware.com/products/protraining.html" target="_blank">http://www.kitware.com/products/protraining.html</a><br>
>>>>>>><br>
>>>>>>> Please keep messages on-topic and check the ITK FAQ at:<br>
>>>>>>> <a href="http://www.itk.org/Wiki/ITK_FAQ" target="_blank">http://www.itk.org/Wiki/ITK_FAQ</a><br>
>>>>>>><br>
>>>>>>> Follow this link to subscribe/unsubscribe:<br>
>>>>>>> <a href="http://www.itk.org/mailman/listinfo/insight-users" target="_blank">http://www.itk.org/mailman/listinfo/insight-users</a><br>
>>>>>>><br>
>>>>>><br>
>>>>><br>
>>>>><br>
>>>><br>
>>><br>
>>><br>
>>> _____________________________________<br>
>>> Powered by <a href="http://www.kitware.com" target="_blank">www.kitware.com</a><br>
>>><br>
>>> Visit other Kitware open-source projects at<br>
>>> <a href="http://www.kitware.com/opensource/opensource.html" target="_blank">http://www.kitware.com/opensource/opensource.html</a><br>
>>><br>
>>> Kitware offers ITK Training Courses, for more information visit:<br>
>>> <a href="http://www.kitware.com/products/protraining.html" target="_blank">http://www.kitware.com/products/protraining.html</a><br>
>>><br>
>>> Please keep messages on-topic and check the ITK FAQ at:<br>
>>> <a href="http://www.itk.org/Wiki/ITK_FAQ" target="_blank">http://www.itk.org/Wiki/ITK_FAQ</a><br>
>>><br>
>>> Follow this link to subscribe/unsubscribe:<br>
>>> <a href="http://www.itk.org/mailman/listinfo/insight-users" target="_blank">http://www.itk.org/mailman/listinfo/insight-users</a><br>
>>><br>
>><br>
>><br>
>><br>
>> --<br>
>> Marco G.<br>
>><br>
>><br>
>> _____________________________________<br>
>> Powered by <a href="http://www.kitware.com" target="_blank">www.kitware.com</a><br>
>><br>
>> Visit other Kitware open-source projects at<br>
>> <a href="http://www.kitware.com/opensource/opensource.html" target="_blank">http://www.kitware.com/opensource/opensource.html</a><br>
>><br>
>> Kitware offers ITK Training Courses, for more information visit:<br>
>> <a href="http://www.kitware.com/products/protraining.html" target="_blank">http://www.kitware.com/products/protraining.html</a><br>
>><br>
>> Please keep messages on-topic and check the ITK FAQ at:<br>
>> <a href="http://www.itk.org/Wiki/ITK_FAQ" target="_blank">http://www.itk.org/Wiki/ITK_FAQ</a><br>
>><br>
>> Follow this link to subscribe/unsubscribe:<br>
>> <a href="http://www.itk.org/mailman/listinfo/insight-users" target="_blank">http://www.itk.org/mailman/listinfo/insight-users</a><br>
>><br>
><br>
><br>
> _____________________________________<br>
> Powered by <a href="http://www.kitware.com" target="_blank">www.kitware.com</a><br>
><br>
> Visit other Kitware open-source projects at<br>
> <a href="http://www.kitware.com/opensource/opensource.html" target="_blank">http://www.kitware.com/opensource/opensource.html</a><br>
><br>
> Kitware offers ITK Training Courses, for more information visit:<br>
> <a href="http://www.kitware.com/products/protraining.html" target="_blank">http://www.kitware.com/products/protraining.html</a><br>
><br>
> Please keep messages on-topic and check the ITK FAQ at:<br>
> <a href="http://www.itk.org/Wiki/ITK_FAQ" target="_blank">http://www.itk.org/Wiki/ITK_FAQ</a><br>
><br>
> Follow this link to subscribe/unsubscribe:<br>
> <a href="http://www.itk.org/mailman/listinfo/insight-users" target="_blank">http://www.itk.org/mailman/listinfo/insight-users</a><br>
><br>
><br>
</div></div></blockquote></div><br>