[Insight-users] registration non-convergence?

[Luis Ibanez]

Hi Carolyn,

When the optimizer is set to MinimizeOn() it should
walk towards lower values of the metric. Occassionaly
it may happens that the optimizer walks uphill if the
step length is too large and the function to optimize
have tortuose passages, but this should only happen
in an isolated step, and the next step should continue
going downhill.

However in your case, the optmizer is walking in a
straight line and the metric values are still going
up-hill after iteration 78...
Something is definetly going wrong there....

Could you please send me the entire file with the
iterations output (not only the iterations that you
posted). Plotting this traces (as we do in the Software
Guide) sometimes help to figure out the source of
miss-behavior.

If you could also post the parameters of the optimizer
that will be great. (In particular the maximum
and mimimum step lengths)


Thanks


   Luis


------------------------
Carolyn Johnston wrote:
> Hi Luis et al,
> 
> I actually do have another question (I guess this is just my day).
> 
> I am performing a standard registration with the mean squares metric and 
> the reg step gradient descent optimizer. I have set my fixed image 
> region to be 1000 by 1000 for speed (on a 3600 by 3600 fixed image). My 
> moving image is just the same as the fixed image with a translation I've 
> added.
> 
> I begin with initial parameters 0,0.
> 
> 0 = 2185.867696: [0.000052, -0.000019]
> 
> 1 = 2123.551007: [0.000104, -0.000039]
> 
> 2 = 2072.931500: [0.000156, -0.000058]
> 
> 3 = 2033.078306: [0.000209, -0.000077]
> 
> 4 = 2003.966331: [0.000261, -0.000097]
> 
> ... <snip> ...
> 
> 
> Now right about here, I pass through a metric minimum and keep on going 
> for some reason...
> 
> 
> 76 = 467.887291: [0.003999, -0.001529]
> 
> 77 = 467.045557: [0.004051, -0.001549]
> 
> 78 = 466.963944: [0.004103, -0.001569]
> 
> 79 = 467.642714: [0.004154, -0.001589]
> 
> 80 = 469.093127: [0.004206, -0.001609]
> 
> ... <snip> ...
> 
> 
> and I end up here, with a metric value significantly higher than the 
> lowest one I achieved during the registration. Any idea what might be 
> causing this? I thought the registration would try to converge around 
> the minimum by reducing the stepsize.
> 
> 95 = 502.706704: [0.004986, -0.001905]
> 
> 96 = 508.162350: [0.005038, -0.001925]
> 
> 97 = 512.621524: [0.005090, -0.001944]
> 
> 98 = 517.175693: [0.005142, -0.001964]
> 
> 99 = 520.728025: [0.005194, -0.001984]
> 
> 
> *** Report for registration of dem 1 ***
> Translation parameter along X: 0.005194
> Translation parameter along Y: -0.001984
> Iterations to reach optimal value of metric: 100
> Optimal value of metric: 520.728025
> 
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk . org
> http://www . itk . org/mailman/listinfo/insight-users
>