Pulmonary Vasculature Segmentation

classic Classic list List threaded Threaded
9 messages Options
Reply | Threaded
Open this post in threaded view
|

Pulmonary Vasculature Segmentation

Sirajul Salekin
Hi,

I am trying to segment the pulmonary arteries and veins from the Lung CT images (DICOM fromat) using Slicer 4.1.1. Is it possible to do? If it is possible, I would earnestly request you to let me know the procedure.

Regards,

Sirajul Salekin

_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject
Reply | Threaded
Open this post in threaded view
|

Re: Pulmonary Vasculature Segmentation

Sirajul Salekin
Hi all,

I am badly in need to solve the segmentation problem mentioned below. If anyone has any idea, please share. It will be a great help.

Regards,
Sirajul Salekin
Reply | Threaded
Open this post in threaded view
|

Re: Pulmonary Vasculature Segmentation

Steve Pieper
Hi Sirajul -

Segmenting those vessels can be very difficult - a lot depends on the
specifics of contrast injections that highlight the vessels and when
the scan was performed with respect to the injection.  You might be
able to use VMTK [1] in slicer3 [2] or TubeTK [3] which is an
extension to slicer4.

-Steve

[1] http://www.vmtk.org/

[2] http://oldsite.vmtk.org/Main/VmtkIn3DSlicer

[3] http://public.kitware.com/Wiki/TubeTK

On Mon, Nov 5, 2012 at 11:04 AM, Sirajul Salekin <[hidden email]> wrote:

> Hi all,
>
> I am badly in need to solve the segmentation problem mentioned below. If
> anyone has any idea, please share. It will be a great help.
>
> Regards,
> Sirajul Salekin
>
>
>
> --
> View this message in context: http://slicer-users.65878.n3.nabble.com/Pulmonary-Vasculature-Segmentation-tp4025513p4025518.html
> Sent from the slicer-users mailing list archive at Nabble.com.
> _______________________________________________
> slicer-users mailing list
> [hidden email]
> http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
> To unsubscribe: send email to [hidden email] with unsubscribe as the subject
_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject
Reply | Threaded
Open this post in threaded view
|

Re: Pulmonary Vasculature Segmentation

madanrao
Hello Sirajul,

If you are taking 3D-CT-angio and can correctly identify pulmonary vasculature in it,

I guess you can segment them using slicer VMTK module. For this you need to

adopt method described for coronaries. If you can successfully segment coronaries,

you can do so for others like cerebral etc.

I hope this helps.

AM Mohan Rao

On Tue, Nov 6, 2012 at 2:23 AM, Steve Pieper <[hidden email]> wrote:
Hi Sirajul -

Segmenting those vessels can be very difficult - a lot depends on the
specifics of contrast injections that highlight the vessels and when
the scan was performed with respect to the injection.  You might be
able to use VMTK [1] in slicer3 [2] or TubeTK [3] which is an
extension to slicer4.

-Steve

[1] http://www.vmtk.org/

[2] http://oldsite.vmtk.org/Main/VmtkIn3DSlicer

[3] http://public.kitware.com/Wiki/TubeTK

On Mon, Nov 5, 2012 at 11:04 AM, Sirajul Salekin <[hidden email]> wrote:
> Hi all,
>
> I am badly in need to solve the segmentation problem mentioned below. If
> anyone has any idea, please share. It will be a great help.
>
> Regards,
> Sirajul Salekin
>
>
>
> --
> View this message in context: http://slicer-users.65878.n3.nabble.com/Pulmonary-Vasculature-Segmentation-tp4025513p4025518.html
> Sent from the slicer-users mailing list archive at Nabble.com.
> _______________________________________________
> slicer-users mailing list
> [hidden email]
> http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
> To unsubscribe: send email to [hidden email] with unsubscribe as the subject
_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject


_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject
Reply | Threaded
Open this post in threaded view
|

Re: Pulmonary Vasculature Segmentation

Sirajul Salekin
Hi Mr. Steve and Mr. Mohan Rao,

Thanks a lot for your valuable suggestions. I am going to explore now based on your guidelines. In case of any problem, I'll knock back to you.

Regards,
Sirajul Salekin
Reply | Threaded
Open this post in threaded view
|

Re: Pulmonary Vasculature Segmentation

Sirajul Salekin
Mr. Mohan Rao,

Good day. I was just wondering if you have any tutorial or guiding document for performing the segmenting task of coronaries using VMTK module. 

Thanks for your time and looking forward to you.

Regards, 
Sirajul Salekin 


On Tue, Nov 6, 2012 at 9:46 AM, Sirajul Salekin [via slicer-users] <[hidden email]> wrote:
Hi Mr. Steve and Mr. Mohan Rao,

Thanks a lot for your valuable suggestions. I am going to explore now based on your guidelines. In case of any problem, I'll knock back to you.

Regards,
Sirajul Salekin


If you reply to this email, your message will be added to the discussion below:
http://slicer-users.65878.n3.nabble.com/Pulmonary-Vasculature-Segmentation-tp4025513p4025521.html
To unsubscribe from Pulmonary Vasculature Segmentation, click here.
NAML


_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject
Reply | Threaded
Open this post in threaded view
|

Re: Pulmonary Vasculature Segmentation

Daniel Haehn
Hi Sirajul,

there are some tutorials available at the VmtkIn3DSlicer page:


They are all based on Slicer version 3.6.

HTH,
Daniel


On Tue, Nov 13, 2012 at 3:53 PM, Sirajul Salekin <[hidden email]> wrote:
Mr. Mohan Rao,

Good day. I was just wondering if you have any tutorial or guiding document for performing the segmenting task of coronaries using VMTK module. 

Thanks for your time and looking forward to you.

Regards, 
Sirajul Salekin 


On Tue, Nov 6, 2012 at 9:46 AM, Sirajul Salekin [via slicer-users] <[hidden email]> wrote:
Hi Mr. Steve and Mr. Mohan Rao,

Thanks a lot for your valuable suggestions. I am going to explore now based on your guidelines. In case of any problem, I'll knock back to you.

Regards,
Sirajul Salekin


If you reply to this email, your message will be added to the discussion below:
http://slicer-users.65878.n3.nabble.com/Pulmonary-Vasculature-Segmentation-tp4025513p4025521.html
To unsubscribe from Pulmonary Vasculature Segmentation, click here.
NAML


_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject


_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject
Reply | Threaded
Open this post in threaded view
|

Re: Pulmonary Vasculature Segmentation

Sirajul Salekin
Hi Mr. Daniel,

Thank you for the response. I followed the procedure step by step as you mentioned in the tutorial slide. But at one stage I am having some problem because many branches segmented in my case instead of on the coronary arteries. The image is attached here for your better understanding.

However, after trying to proceed with whatever image I got, there was another problem that I did not find anything (example: slide no 61 in the tutorial) in the 3D rendering window for centerline computation.

Can you give me any hint where the problem may occur? Thanks again and waiting to hear from you.

//Sirajul Salekin


Reply | Threaded
Open this post in threaded view
|

Re: Pulmonary Vasculature Segmentation

Daniel Haehn
Hi Sirajul,

in my experience such oversegmentations usually occur when the contrast setting of the vesselness filter is not correct which then leads to many structures classified > 0. Try to play around to get a nice vesselness probability for tubular shapes while avoiding the background.

In the Slicer4 vmtk modules (which are currently only available after some CMake adjustments https://github.com/haehn/VMTK-in-3D-Slicer ), I calculate the contrast measure using a weighted difference between intensity in the largest vessel of the original image and some points double the diameter around this point as described here:
This gave good results on many cases.

Cheers,
Daniel


On Thu, Nov 15, 2012 at 6:32 PM, Sirajul Salekin <[hidden email]> wrote:
Hi Mr. Daniel,

Thank you for the response. I followed the procedure step by step as you
mentioned in the tutorial slide. But at one stage I am having some problem
because many branches segmented in my case instead of on the coronary
arteries. The image is attached here for your better understanding.

However, after trying to proceed with whatever image I got, there was
another problem that I did not find anything (example: slide no 61 in the
tutorial) in the 3D rendering window for centerline computation.

Can you give me any hint where the problem may occur? Thanks again and
waiting to hear from you.

//Sirajul Salekin

<http://slicer-users.65878.n3.nabble.com/file/n4025558/What_I_got.jpg>
<http://slicer-users.65878.n3.nabble.com/file/n4025558/In_original_slide.jpg>



--
View this message in context: http://slicer-users.65878.n3.nabble.com/Pulmonary-Vasculature-Segmentation-tp4025513p4025558.html
Sent from the slicer-users mailing list archive at Nabble.com.
_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject


_______________________________________________
slicer-users mailing list
[hidden email]
http://massmail.spl.harvard.edu/mailman/listinfo/slicer-users
To unsubscribe: send email to [hidden email] with unsubscribe as the subject