binding

binding ¶

DCE binding adapter for the shared fitting infrastructure.

BoundDCEModel wraps a BasePerfusionModel together with time and AIF arrays, producing a FittableModel that the shared fitter can use without knowing about DCE-specific context.

BoundDCEModel ¶

BoundDCEModel(model, t, aif, fixed=None)

Bases: BaseBoundModel

DCE model with time and AIF bound.

Wraps a BasePerfusionModel so the fitter only sees predict_array_batch(free_params) -> output.

PARAMETER	DESCRIPTION
`model`	DCE pharmacokinetic model. TYPE: `BasePerfusionModel`
`t`	Time points in seconds. TYPE: `NDArray`
`aif`	Arterial input function concentration. TYPE: `NDArray`
`fixed`	Parameters to fix at constant values during fitting. TYPE: `dict[str, float] \| None` DEFAULT: `None`

ensure_device ¶

ensure_device(xp)

Transfer time and AIF arrays to the target device.

predict_array_batch ¶

predict_array_batch(free_params_batch, xp)

Predict tissue concentration for a batch of voxels.

PARAMETER	DESCRIPTION
`free_params_batch`	Free parameter values, shape `(n_free, n_voxels)`. TYPE: `NDArray`
`xp`	Array module. TYPE: `module`

RETURNS	DESCRIPTION
`NDArray`	Predicted concentrations, shape `(n_time, n_voxels)`.

get_initial_guess_batch ¶

get_initial_guess_batch(observed_batch, xp)

Get initial parameter guesses for a batch of voxels.

Delegates to the DCE model's get_initial_guess_batch and filters out fixed parameters.

PARAMETER	DESCRIPTION
`observed_batch`	Observed data, shape `(n_time, n_voxels)`. TYPE: `NDArray`
`xp`	Array module. TYPE: `module`

RETURNS	DESCRIPTION
`NDArray`	Initial guesses, shape `(n_free, n_voxels)`.

compute_jacobian_batch ¶

compute_jacobian_batch(params_batch, predicted, xp)

DCE uses numerical Jacobian (convolution models).