MRFModel

MRFModel#

class torchsim.models.MRFModel(diff=None, chunk_size=None, device=None, *args, **kwargs)[source]#

Bases: AbstractModel

SSFP Magnetic Resonance Fingerprinting (MRF) Model.

This class models steady-state free precession (SSFP) MRF signals based on tissue properties, pulse sequence parameters, and experimental conditions. It uses Extended Phase Graph (EPG) formalism to compute the magnetization evolution over time.

Parameters:

  • diff (str | tuple[str] | None)

  • chunk_size (int | None)

  • device (str | device | None)

set_properties(T1, T2, M0=1.0, B1=1.0, inv_efficiency=1.0)[source]#

Sets tissue relaxation properties and experimental conditions.

Parameters:
set_sequence(flip, TR, TI=0.0, slice_prof=1.0, nstates=10, nreps=1)[source]#

Configures the pulse sequence parameters for the simulation.

Parameters:
_engine(T1, T2, flip, TR, TI=0.0, M0=1.0, B1=1.0, inv_efficiency=1.0,

slice_prof=1.0, nstates=10, nreps=1)

Computes the MRF signal for given tissue properties and sequence parameters.

Examples

import torch
from torchsim.models import MRFModel

model = MRFModel()
model.set_properties(T1=1000, T2=80, M0=1.0, B1=1.0, inv_efficiency=0.95)
model.set_sequence(flip=torch.linspace(5.0, 60.0, 1000), TR=10.0, nstates=20, nreps=1)
signal = model()

Methods

__init__

Initialize the model with automatic parameter segregation and engine setup.

forward

Get forward method.

jacobian

Get Jacobian method.

set_properties

Set tissue and system-specific properties for the MRF model.

set_sequence

Set sequence parameters for the SPGR model.
set_properties(T1, T2, M0=1.0, B1=1.0, inv_efficiency=1.0)[source]#

Set tissue and system-specific properties for the MRF model.

Parameters:

  • T1 (float | npt.ArrayLike) – Longitudinal relaxation time in milliseconds.

  • T2 (float | npt.ArrayLike) – Transverse relaxation time in milliseconds.

  • M0 (float or array-like, optional) – Proton density scaling factor, default is 1.0.

  • B1 (float | npt.ArrayLike, optional) – Flip angle scaling map, default is 1.0.

  • inv_efficiency (float | npt.ArrayLike, optional) – Inversion efficiency map, default is 1.0.

set_sequence(flip, TR, TI=0.0, slice_prof=1.0, nstates=10, nreps=1)[source]#

Set sequence parameters for the SPGR model.

Parameters:

  • flip (float | npt.ArrayLike) – Flip angle train in degrees.

  • TR (float | npt.ArrayLike) – Repetition time in milliseconds.

  • TI (float, optional) – Inversion time in milliseconds. The default is 0.0.

  • slice_prof (float | npt.ArrayLike, optional) – Flip angle scaling along slice profile. The default is 1.0.

  • nstates (int, optional) – Number of EPG states to be retained. The default is 10.

  • nreps (int, optional) – Number of simulation repetitions. The default is 1.

static _engine(T1, T2, flip, TR, TI=0.0, M0=1.0, B1=1.0, inv_efficiency=1.0, slice_prof=1.0, nstates=10, nreps=1)[source]#

Core computational function for the model.

Parameters: