Automated fetal measurement from three-dimensional ultrasound data

In a non-transitory computer readable storage medium having stored therein data representing instructions executable by a programmed processor for measuring a fetal parameter from three-dimensional ultrasound data, the storage medium comprising instructions for:

• obtaining the three-dimensional ultrasound data representing a patient;
• receiving user input requesting automatic measurement of a fetal head anatomy, the fetal parameter being for the fetal head anatomy;
• detecting the fetal head anatomy with a computer learnt classifier, the computer learnt classifier operable to detect from the three-dimensional ultrasound data without user indication of a position, the computer learnt classifier comprising both a joint classifier such that the fetal head anatomy is detected as a function of a location of other anatomy and a marginal space classifier including classification of a size of the fetal head anatomy, wherein each stage in a sequence of the marginal machine-trained classifier searches through multiple locations in the three-dimensional ultrasound data to identify locations with higher probabilities for the location of the fetal head anatomy and further removes false locations remaining from a previous stage in the sequence of the marginal machine trained classifier, wherein the fetal anatomy is detected by applying any numbers of degrees of freedom in the marginal machine-trained classifier for translation, rotation and scaling;
• and
• calculating a value for the fetal parameter.

A system for measuring a fetal parameter from three-dimensional ultrasound data, the system comprising:

• a memory operable to store ultrasound data representing a fetal volume;
• a processor operable to apply a probabilistic model to detect a first anatomy as a function of the ultrasound data and as a function of a position of a second anatomy, the detection of the first anatomy being performed sequentially in a sequence of stages of position of the first anatomy, orientation of the first anatomy, and scale of the first anatomy, the scale comprising a size of the first anatomy in the fetal volume, wherein each stage in the sequence searches through multiple locations in the ultrasound data to identify locations with higher probabilities for a location of the first anatomy and further removes false locations remaining from a previous stage in the sequence, wherein the first anatomy is detected by applying any numbers of degrees of freedom in the probabilistic model for position, orientation and scale;
• and
• a display operable to display an image of the first anatomy, a value representing a measurement of the first anatomy or combinations thereof.