VMTK - vessel segmentation from FLAIR images

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

VMTK - vessel segmentation from FLAIR images

Pauline Roca
Dear all,

I am trying to segment vessels from FLAIR images (just after AVC, some collateral vessels appears as hyperintense on FLAIR MR images, there are very thin vessels with very slow flow, not visible in Time Of Flight sequences).
I tried the VMTK Vascular Enhancement module, but I didn't get any satisfaying results.

Do you think it is possible ? (see the image below) An what method/tool would be the best ?
The spatial resolution is very thin in the plane (0.45x0.45 mm) but thick in the 3rd dimension (6mm).

 snapshot2.jpg

Thank you in advance for your help,

Best regards,

Pauline
Reply | Threaded
Open this post in threaded view
|

Re: VMTK - vessel segmentation from FLAIR images

Christopher Mullins
Unfortunately there is no support in Slicer 4 for the VMTK.  However, in Slicer 4 there is the TubeTK extension.  Check out the TubeTK Interactive PDF Segmenter module documentation.  Please let us know if this is useful for you!


On Mon, Feb 18, 2013 at 1:05 PM, Pauline Roca <[hidden email]> wrote:
Dear all,

I am trying to segment vessels from FLAIR images (just after AVC, some
collateral vessels appears as hyperintense on FLAIR MR images, there are
very thin vessels with very slow flow, not visible in Time Of Flight
sequences).
I tried the VMTK Vascular Enhancement module, but I didn't get any
satisfaying results.

Do you think it is possible ? (see the image below) An what method/tool
would be the best ?
The spatial resolution is very thin in the plane (0.45x0.45 mm) but thick in
the 3rd dimension (6mm).

  snapshot2.jpg
<http://slicer-users.65878.n3.nabble.com/file/n4025826/snapshot2.jpg>

Thank you in advance for your help,

Best regards,

Pauline



--
View this message in context: http://slicer-users.65878.n3.nabble.com/VMTK-vessel-segmentation-from-FLAIR-images-tp4025826.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



--
Christopher Mullins
R&D Engineer
Kitware Inc.,
919.869.8871

_______________________________________________
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: VMTK - vessel segmentation from FLAIR images

madanrao
Hello,

There is good Slicer documentation by Daniel Haehn. Apart from this there are also guidelines on how to segment brain by
Pohl.

I think you just need to segment the frontal or parietal lobes (? or their sub segments)  before you can apply VMTK for these
vessels.

I hope this helps.

AM Mohan Rao

On Tue, Feb 19, 2013 at 1:05 AM, Christopher Mullins <[hidden email]> wrote:
Unfortunately there is no support in Slicer 4 for the VMTK.  However, in Slicer 4 there is the TubeTK extension.  Check out the TubeTK Interactive PDF Segmenter module documentation.  Please let us know if this is useful for you!


On Mon, Feb 18, 2013 at 1:05 PM, Pauline Roca <[hidden email]> wrote:
Dear all,

I am trying to segment vessels from FLAIR images (just after AVC, some
collateral vessels appears as hyperintense on FLAIR MR images, there are
very thin vessels with very slow flow, not visible in Time Of Flight
sequences).
I tried the VMTK Vascular Enhancement module, but I didn't get any
satisfaying results.

Do you think it is possible ? (see the image below) An what method/tool
would be the best ?
The spatial resolution is very thin in the plane (0.45x0.45 mm) but thick in
the 3rd dimension (6mm).

  snapshot2.jpg
<http://slicer-users.65878.n3.nabble.com/file/n4025826/snapshot2.jpg>

Thank you in advance for your help,

Best regards,

Pauline



--
View this message in context: http://slicer-users.65878.n3.nabble.com/VMTK-vessel-segmentation-from-FLAIR-images-tp4025826.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



--
Christopher Mullins
R&D Engineer
Kitware Inc.,
919.869.8871

_______________________________________________
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: VMTK - vessel segmentation from FLAIR images

Pauline Roca
In reply to this post by Christopher Mullins
Thank you for your answer.
I didn't mention this, but I tried in Slicer 3.6 and not Slicer 4.
In any case, what version do you advice for vessel segmentation ?

2013/2/18 Christopher Mullins <[hidden email]>
Unfortunately there is no support in Slicer 4 for the VMTK.  However, in Slicer 4 there is the TubeTK extension.  Check out the TubeTK Interactive PDF Segmenter module documentation.  Please let us know if this is useful for you!


On Mon, Feb 18, 2013 at 1:05 PM, Pauline Roca <[hidden email]> wrote:
Dear all,

I am trying to segment vessels from FLAIR images (just after AVC, some
collateral vessels appears as hyperintense on FLAIR MR images, there are
very thin vessels with very slow flow, not visible in Time Of Flight
sequences).
I tried the VMTK Vascular Enhancement module, but I didn't get any
satisfaying results.

Do you think it is possible ? (see the image below) An what method/tool
would be the best ?
The spatial resolution is very thin in the plane (0.45x0.45 mm) but thick in
the 3rd dimension (6mm).

  snapshot2.jpg
<http://slicer-users.65878.n3.nabble.com/file/n4025826/snapshot2.jpg>

Thank you in advance for your help,

Best regards,

Pauline



--
View this message in context: http://slicer-users.65878.n3.nabble.com/VMTK-vessel-segmentation-from-FLAIR-images-tp4025826.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



--
Christopher Mullins
R&D Engineer
Kitware Inc.,
<a href="tel:919.869.8871" value="+19198698871" target="_blank">919.869.8871


_______________________________________________
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: VMTK - vessel segmentation from FLAIR images

madanrao
Hi,

I guess Slicer 3.6 should be OK.

AM Mohan Rao

On Tue, Feb 19, 2013 at 8:11 PM, Pauline ROCA <[hidden email]> wrote:
Thank you for your answer.
I didn't mention this, but I tried in Slicer 3.6 and not Slicer 4.
In any case, what version do you advice for vessel segmentation ?


2013/2/18 Christopher Mullins <[hidden email]>
Unfortunately there is no support in Slicer 4 for the VMTK.  However, in Slicer 4 there is the TubeTK extension.  Check out the TubeTK Interactive PDF Segmenter module documentation.  Please let us know if this is useful for you!


On Mon, Feb 18, 2013 at 1:05 PM, Pauline Roca <[hidden email]> wrote:
Dear all,

I am trying to segment vessels from FLAIR images (just after AVC, some
collateral vessels appears as hyperintense on FLAIR MR images, there are
very thin vessels with very slow flow, not visible in Time Of Flight
sequences).
I tried the VMTK Vascular Enhancement module, but I didn't get any
satisfaying results.

Do you think it is possible ? (see the image below) An what method/tool
would be the best ?
The spatial resolution is very thin in the plane (0.45x0.45 mm) but thick in
the 3rd dimension (6mm).

  snapshot2.jpg
<http://slicer-users.65878.n3.nabble.com/file/n4025826/snapshot2.jpg>

Thank you in advance for your help,

Best regards,

Pauline



--
View this message in context: http://slicer-users.65878.n3.nabble.com/VMTK-vessel-segmentation-from-FLAIR-images-tp4025826.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



--
Christopher Mullins
R&D Engineer
Kitware Inc.,
<a href="tel:919.869.8871" value="+19198698871" target="_blank">919.869.8871


_______________________________________________
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: VMTK - vessel segmentation from FLAIR images

Pauline Roca
Ok, thanks.
For the VMTKVesselEnhancement process, I tried the 3 different procedures, with parameters according to the vessels I want to segment.

Ex for Sato Vesselness:
steps between min. and max. Diameter :10
Diameter spec.:Physical Unit
Min. Diameter of the Tube: 0.5
Max. Diameter of the Tube: 2
Sensitivity Threshold (I kept default parameters)
Plate-like and line-like structure: 0.5
Blob-like structures: 2.0

I didn't get any satisfaying results.
If someone has advices on what parameters I should use, it will be of great help !

Thank you in advance,
Best regards,

Pauline

2013/2/19 Madan Rao <[hidden email]>
Hi,

I guess Slicer 3.6 should be OK.

AM Mohan Rao


On Tue, Feb 19, 2013 at 8:11 PM, Pauline ROCA <[hidden email]> wrote:
Thank you for your answer.
I didn't mention this, but I tried in Slicer 3.6 and not Slicer 4.
In any case, what version do you advice for vessel segmentation ?


2013/2/18 Christopher Mullins <[hidden email]>
Unfortunately there is no support in Slicer 4 for the VMTK.  However, in Slicer 4 there is the TubeTK extension.  Check out the TubeTK Interactive PDF Segmenter module documentation.  Please let us know if this is useful for you!


On Mon, Feb 18, 2013 at 1:05 PM, Pauline Roca <[hidden email]> wrote:
Dear all,

I am trying to segment vessels from FLAIR images (just after AVC, some
collateral vessels appears as hyperintense on FLAIR MR images, there are
very thin vessels with very slow flow, not visible in Time Of Flight
sequences).
I tried the VMTK Vascular Enhancement module, but I didn't get any
satisfaying results.

Do you think it is possible ? (see the image below) An what method/tool
would be the best ?
The spatial resolution is very thin in the plane (0.45x0.45 mm) but thick in
the 3rd dimension (6mm).

  snapshot2.jpg
<http://slicer-users.65878.n3.nabble.com/file/n4025826/snapshot2.jpg>

Thank you in advance for your help,

Best regards,

Pauline



--
View this message in context: http://slicer-users.65878.n3.nabble.com/VMTK-vessel-segmentation-from-FLAIR-images-tp4025826.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



--
Christopher Mullins
R&D Engineer
Kitware Inc.,
<a href="tel:919.869.8871" value="+19198698871" target="_blank">919.869.8871


_______________________________________________
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: VMTK - vessel segmentation from FLAIR images

Daniel Haehn
Hi Pauline,

can you share your data set? The Slicer VMTK4 extensions are almost there and I can try them on your data right now.

The new extensions have some mechanism to detect the parameters automatically.

Thanks,
Daniel


On Tue, Feb 19, 2013 at 11:57 AM, Pauline ROCA <[hidden email]> wrote:
Ok, thanks.
For the VMTKVesselEnhancement process, I tried the 3 different procedures, with parameters according to the vessels I want to segment.

Ex for Sato Vesselness:
steps between min. and max. Diameter :10
Diameter spec.:Physical Unit
Min. Diameter of the Tube: 0.5
Max. Diameter of the Tube: 2
Sensitivity Threshold (I kept default parameters)
Plate-like and line-like structure: 0.5
Blob-like structures: 2.0


I didn't get any satisfaying results.
If someone has advices on what parameters I should use, it will be of great help !

Thank you in advance,
Best regards,

Pauline


2013/2/19 Madan Rao <[hidden email]>
Hi,

I guess Slicer 3.6 should be OK.

AM Mohan Rao


On Tue, Feb 19, 2013 at 8:11 PM, Pauline ROCA <[hidden email]> wrote:
Thank you for your answer.
I didn't mention this, but I tried in Slicer 3.6 and not Slicer 4.
In any case, what version do you advice for vessel segmentation ?


2013/2/18 Christopher Mullins <[hidden email]>
Unfortunately there is no support in Slicer 4 for the VMTK.  However, in Slicer 4 there is the TubeTK extension.  Check out the TubeTK Interactive PDF Segmenter module documentation.  Please let us know if this is useful for you!


On Mon, Feb 18, 2013 at 1:05 PM, Pauline Roca <[hidden email]> wrote:
Dear all,

I am trying to segment vessels from FLAIR images (just after AVC, some
collateral vessels appears as hyperintense on FLAIR MR images, there are
very thin vessels with very slow flow, not visible in Time Of Flight
sequences).
I tried the VMTK Vascular Enhancement module, but I didn't get any
satisfaying results.

Do you think it is possible ? (see the image below) An what method/tool
would be the best ?
The spatial resolution is very thin in the plane (0.45x0.45 mm) but thick in
the 3rd dimension (6mm).

  snapshot2.jpg
<http://slicer-users.65878.n3.nabble.com/file/n4025826/snapshot2.jpg>

Thank you in advance for your help,

Best regards,

Pauline



--
View this message in context: http://slicer-users.65878.n3.nabble.com/VMTK-vessel-segmentation-from-FLAIR-images-tp4025826.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



--
Christopher Mullins
R&D Engineer
Kitware Inc.,
<a href="tel:919.869.8871" value="+19198698871" target="_blank">919.869.8871


_______________________________________________
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


_______________________________________________
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