This class of cost functions evaluates the cost resulting from the use of a certain transformation. This may include a penalty term that ensures the smoothness of a transformation or the evaluation of a similarity measure between a transformed study data set and a reference data set. These cost functions can be combined and weighted.
image labelimage maskedimage taggedssd
Generalized image similarity cost function that also handles multi-resolution processing. The actual similarity measure is given es extra parameter.. Supported parameters are:
| Name | Type | Default | Description |
|---|---|---|---|
| cost | factory | ssd | Cost function kernel. For supported plug-ins see Plugin type: 3dimage/cost |
| debug | bool | 0 | Save intermediate resuts for debugging |
| ref | io | (input) | Reference image. For supported file types see Plugin type: 3dimage/io |
| src | io | (input) | Study image. For supported file types see Plugin type: 3dimage/io |
| weight | float | 1 | weight of cost function in [-1e+10, 1e+10] |
Similarity cost function that maps labels of two images and handles label-preserving multi-resolution processing.. Supported parameters are:
| Name | Type | Default | Description |
|---|---|---|---|
| maxlabel | int | 256 | maximum number of labels to consider in [2, 32000] |
| ref | io | (input) | Reference image. For supported file types see Plugin type: 3dimage/io |
| src | io | (input) | Study image. For supported file types see Plugin type: 3dimage/io |
| weight | float | 1 | weight of cost function in [-1e+10, 1e+10] |
Generalized masked image similarity cost function that also handles multi-resolution processing. The provided masks should be densly filled regions in multi-resolution procesing because otherwise the mask information may get lost when downscaling the image. The mask may be pre-filtered - after pre-filtering the masks must be of bit-type.The reference mask and the transformed mask of the study image are combined by binary AND. The actual similarity measure is given es extra parameter.. Supported parameters are:
| Name | Type | Default | Description |
|---|---|---|---|
| cost | factory | ssd | Cost function kernel. For supported plug-ins see Plugin type: 3dimage/maskedcost |
| ref | io | (input) | Reference image. For supported file types see Plugin type: 3dimage/io |
| ref-mask | io | (input) | Reference image mask (binary). For supported file types see Plugin type: 3dimage/io |
| ref-mask-filter | factory | Filter to prepare the reference mask image, the output must be a binary image.. For supported plug-ins see Plugin type: 3dimage/filter | |
| src | io | (input) | Study image. For supported file types see Plugin type: 3dimage/io |
| src-mask | io | (input) | Study image mask (binary). For supported file types see Plugin type: 3dimage/io |
| src-mask-filter | factory | Filter to prepare the study mask image, the output must be a binary image.. For supported plug-ins see Plugin type: 3dimage/filter | |
| weight | float | 1 | weight of cost function in [-1e+10, 1e+10] |
Evaluates the Sum of Squared Differences similarity measure by using three tagged image pairs. The cost function value is evaluated based on all image pairs, but the gradient is composed by composing its component based on the tag direction.. Supported parameters are:
| Name | Type | Default | Description |
|---|---|---|---|
| refx | io | (input) | Reference image X-tag. For supported file types see Plugin type: 3dimage/io |
| refy | io | (input) | Reference image Y-tag. For supported file types see Plugin type: 3dimage/io |
| refz | io | (input) | Reference image Z-tag. For supported file types see Plugin type: 3dimage/io |
| srcx | io | (input) | Study image X-tag. For supported file types see Plugin type: 3dimage/io |
| srcy | io | (input) | Study image Y-tag. For supported file types see Plugin type: 3dimage/io |
| srcz | io | (input) | Study image Z-tag. For supported file types see Plugin type: 3dimage/io |
| weight | float | 1 | weight of cost function in [-1e+10, 1e+10] |
mia-3dcost mia-3dmany2one-nonrigid mia-3dnonrigidreg mia-3dnonrigidreg-alt mia-3dprealign-nonrigid mia-3dserial-nonrigid