[Insight-developers] CannySegmentationLevelSetImageFilter

Joshua Cates cates at sci . utah . edu
Mon, 24 Nov 2003 11:51:12 -0700 (MST) 

This interpretation is correct. When a function object is an ivar of a
filter object, its state is the responsibility of the filter that owns it,
not the user.  Because only the pde solver (filter) has all of the
necessary information to configure a function object properly, its
complexity is not generally exposed to the user.

The source of your confusion, 
SegmentationLevelSetFunction::ReverseExpansionDirection(), is poorly named 
and not really even necessary.

The problem that remains is that the function object may be left in an
incorrect state after recovery from an exception.  I can either fix this
or remove ReverseExpansionDirectionOn/Off.  As you point out, the same
effect can be achieved by manually reversing the signs of both the
advection and propagation (but *not* the curvature) coefficients.  My
intention was to hide this complexity from users, who likely do not fully
understand the level set pde's.

Josh.

______________________________
 Josh Cates			
 Scientific Computing and Imaging Institute
 University of Utah
 Email: cates at sci . utah . edu
 Phone: (801) 587-7697
 URL:   http://www . sci . utah . edu/~cates


On Mon, 24 Nov 2003, Miller, James V (Research) wrote:

> I see my confusion wrt to ReverseDirection On.
> 
> There is a mode on the SegmentationLevelSetImageFilter for the reverse
> direction.  However, in GenerateData() if ReverseDirection is on, then it
> calls ReverseDirection() on the SegmentationLevelSetFunction which does NOT
> have a mode.  This is what we saw on Friday and had us shaking in our boots.
> However, at the end of GenerateData(), ReverseDirection() is called again on
> the SegmentationLevelSetFunction so everything "should" be reset to proper
> state.  I guess the only that could go wrong is if an exception gets thrown
> between the two calls to ReverseDirection() on the LevelSetFunction.
> 
> Jim 
> 
> 
> 
> -----Original Message-----
> From: Miller, James V (Research) 
> Sent: Monday, November 24, 2003 8:27 AM
> To: 'Joshua Cates'; Bill Lorensen
> Cc: Miller, James V (Research); Insight-developers (E-mail)
> Subject: RE: [Insight-developers] CannySegmentationLevelSetImageFilter
> 
> 
> Hey Josh, 
> 
> I think Bill is saying it is not setting a mode since it actually changes
> the coefficients.  It is impossible to query the filter and determine
> whether someone called ReverseExpansionDirection since the caller would have
> to know whether the coefficients were initially positive or negative.
> 
> A safer way to do this is to have a ivar that keeps track of whether someone
> wants the expansion direction reversed and keep the coefficients the
> original values.  Then when the coefficients get used, you multiply by -1 if
> neccessary.
> 
> Jim
> 
> -----Original Message-----
> From: Joshua Cates [mailto:cates at sci . utah . edu]
> Sent: Friday, November 21, 2003 5:41 PM
> To: Bill Lorensen
> Cc: Miller, James V (Research); Insight-developers (E-mail)
> Subject: Re: [Insight-developers] CannySegmentationLevelSetImageFilter
> 
> 
> Yes I agree the best thing is always more documentation.
> 
> Note that as implemented in the SegmentationLevelSetImageFilter class, the
> ReverseExpansionDirection does in fact set a mode flag.  So you can call
> ReverseExp...On to enable and ReverseExp..Off to disable.  It's a
> convenience function that flips the signs of the coefficients before
> execution (through a call to
> SegmentationLevelSetFunction::ReverseExpansionDirection, hence the
> confusion).
> 
>  Josh.
> 
> ______________________________
>  Josh Cates			
>  Scientific Computing and Imaging Institute
>  University of Utah
>  Email: cates at sci . utah . edu
>  Phone: (801) 587-7697
>  URL:   http://www . sci . utah . edu/~cates
> 
> 
> On Fri, 21 Nov 2003, Bill Lorensen wrote:
> 
> > Josh,
> > The ReverseExpansionDirection is dangerous since it acts when it is called
> 
> > and does not set a mode. If you call it twice, it reverse itself. You can 
> > change the behavior by changing the signs of the coefficients. I think the
> 
> > best thing is clear documentation.
> > 
> > Bill
> > 
> > At 04:22 PM 11/21/2003, Joshua Cates wrote:
> > >Hi all,
> > >
> > >Sorry I missed this discussion on the TCON.  When the level-set section
> in
> > >the SoftwareGuide was first written there was still some inconsistency
> > >among level-set filters, so we left the description of inside/outside to
> > >up to documentation in specific classes.  Now everything is standardized
> > >and correctly described in the doxygen pages for
> > >SegmentationLevelSetImageFilter.
> > >
> > >Let me see if I understand correctly: The confusion on the initialization
> > >is that you expected "inside" to correspond to the intuitive notion of
> the
> > >region enclosed by the implicit surface, when actually "inside" is
> > >determined using values relative (lt) the isosurface you describe in the
> > >input?  So using a binary initialization 0, 255 and choosing isosurface
> > >value 127, for example, results in negative values external to the region
> > >enclosed by the surface.
> > >
> > >Note that the opposite sign convention (positive-outside) produces your
> > >intuitive result from a binary initialization.  A perfectly valid way to
> > >work with these filters is to turn on "ReverseExpansionDirection" which
> > >effectively reverses the convention during calculations and gives the
> > >expansion/contraction of the opposite sign convention.
> > >
> > >There may also be some use in another method that allows you to flip the
> > >sign of the values in your initialization?
> > >
> > >I'll add some clarifications to the SoftwareGuide on these points.
> > >Probably be a week or so before I can get to it.  Let me know if there
> are
> > >other points that need clarification.
> > >
> > >Josh.
> > >
> > >______________________________
> > >  Josh Cates
> > >  Scientific Computing and Imaging Institute
> > >  University of Utah
> > >  Email: cates at sci . utah . edu
> > >  Phone: (801) 587-7697
> > >  URL:   http://www . sci . utah . edu/~cates
> > >
> > >
> > >On Fri, 21 Nov 2003, Miller, James V (Research) wrote:
> > >
> > > > I mentioned on the tcon this afternoon that we were having some
> problems
> > > > with the CannySegmentationLevelSetImageFilter.  If we used a positive 
> > > weight
> > > > for the advection weight, our segmentations would contract whereas if
> we
> > > > used a negative weight for the advection weight our segmentations
> would
> > > > expand (like we wanted).
> > > >
> > > > Lydia mentioned that it may be due to how the seed image is being
> used.
> > > > Once again, Lydia is right. We were passing in a binary image (the 
> > > output of
> > > > another segmentation algorithm) as the seed image.  The seed image had
> 255
> > > > for the object and 0 for the background.  The 
> > > SparseFieldLevelSetImageFilter
> > > > takes this seed image and generates an initial level set by assigning 
> > > pixels
> > > > above a specified IsoValue as being outside the object and pixels
> below a
> > > > specified IsoValue as being inside the object.  So while I thought my
> > > > segmentation was shrinking, it was actually growing.  It was just that
> my
> > > > "object" was actually my background.
> > > >
> > > > So.  Here are my suggestions.  One, we should be very clear that the
> inside
> > > > of objects have negative level set values and the outside of objects
> have
> > > > positive level set values.  Two, we should change the documentation
> for
> > > > *SegmentationLevelSetFilters so that it is clear that the seed image 
> > > follows
> > > > the same conventions for objectness as the levelsets, i.e. values less
> than
> > > > the specified IsoValue are interior to the object, values greater than
> the
> > > > specified IsoValue are exterior to the object.  I am not sure whether
> we
> > > > want to go so far as to say the seed image is an initial level set
> (which
> > > > does not really have to be) or whether we can just say that it follows
> the
> > > > same conventions as level sets.
> > > >
> > > > Finally, I am not sure when we changed the levelsets to be consistent
> with
> > > > negative interiors and positive exteriors but I regardless of when it
> was
> > > > done, it looks like the User Guide is out of date.  We'll need to
> propagate
> > > > this into the User Guide and perhaps put out a list of "errata" on the
> web
> > > > site.
> > > >
> > > > Any comments?
> > > >
> > > >
> > > >
> > > > Jim Miller
> > > > _____________________________________
> > > > Visualization & Computer Vision
> > > > GE Research
> > > > Bldg. KW, Room C218B
> > > > P.O. Box 8, Schenectady NY 12301
> > > >
> > > > millerjv at research . ge . com <mailto:millerjv at research . ge . com>
> > > >
> > > > james . miller at research . ge . com
> > > > (518) 387-4005, Dial Comm: 8*833-4005,
> > > > Cell: (518) 505-7065, Fax: (518) 387-6981
> > > >
> > > >
> > > >
> > >
> > >_______________________________________________
> > >Insight-developers mailing list
> > >Insight-developers at itk . org
> > >http://www . itk . org/mailman/listinfo/insight-developers
> > 
> > 
>