Synthetic data-driven hemodynamic determination in medical imaging
In hemodynamic determination in medical imaging, the classifier is trained from synthetic data rather than relying on training data from other patients. A computer model (in silico) may be perturbed in many different ways to generate many different examples. The flow is calculated for each resulting example. A bench model (in vitro) may similarly be altered in many different ways. The flow is measured for each resulting example. The machine-learnt classifier uses features from medical scan data for a particular patient to estimate the blood flow based on mapping of features to flow learned from the synthetic data. Perturbations or alterations may account for therapy so that the machine-trained classifier may estimate the results of therapeutically altering a patient-specific input feature. Uncertainty may be handled by training the classifier to predict a distribution of possibilities given uncertain input distribution. Combinations of one or more of uncertainty, use of synthetic training data, and therapy prediction may be provided.
1. A method for hemodynamic determination in medical imaging, the method comprising:
acquiring medical scan data representing an anatomical structure of a patient;
extracting a set of features from the medical scan data;
inputting, by a processor, the features to a machine-trained classifier, the machine trained classifier trained from synthetic data not specific to any patients; and
outputting, by the processor with application of the machine-trained classifier to the features, a hemodynamic metric.
2. The method of claim 1 wherein acquiring comprises acquiring angiography data.
3. The method of claim 1 wherein acquiring comprises acquiring with the medical scan data comprising a two or three-dimensional representation of the anatomical structure.
4. The method of claim 1 wherein extracting the set of the features comprises:
extracting geometrical features of the anatomical structure; and
extracting the features of one or more abnormalities of the anatomical structure.
5. The method of claim 1 wherein extracting the set of the features comprises extracting functional features representing operation of the anatomical structure, wherein the machine-trained classifier is trained from virtual representations of the operation of the anatomical structure.
6. The method of claim 1 wherein extracting the set of the features comprises extracting an ischemic weight and an ischemic contribution score, the ischemic contribution score being a function of the ischemic weight.
7. The method of claim 6 wherein extracting the ischemic weight comprises computing branch ischemic weights as a function of a global ischemic weight.
8. The method of claim 6 wherein extracting the ischemic contribution score comprises computing the ischemic contribution score as a function of the ischemic weight and a radius.
9. The method of claim 1 wherein extracting the set of the features comprises extracting branch interaction features.
10. The method of claim 1 wherein inputting comprises inputting to the machine-trained classifier trained from the synthetic data, the synthetic data comprising an in vitro model with a ground truth of the hemodynamic metric measured form the in vitro model.
11. The method of claim 1 wherein inputting comprises inputting to the machine-trained classifier trained from the synthetic data, the synthetic data comprising an in silico model with a ground truth of the hemodynamic metric computed with computation fluid dynamics.
12. The method of claim 1 wherein inputting comprises inputting a sub-set of the set of features, the sub-set for a sub-part of the anatomical structure, and wherein outputting comprises outputting the hemodynamic metric for the sub-part of the anatomical structure; and
further comprising subsequently repeating the inputting and outputting for remaining features of the set for another part of the anatomical structure.
13. The method of claim 1 wherein outputting comprises outputting a value of the hemodynamic metric on a display with an image of the anatomical structure generated from the medical scan data.
14. The method of claim 1 further comprising predicting another value of the hemodynamic metric with another machine-trained classifier using at least one of the different values and patient characteristics as input features.
15. The method of claim 1 wherein inputting comprises inputting to the machine-trained classifier trained from the synthetic data, the synthetic data comprising examples generated by regular variation of an in vitro model, in silico model, or both in vitro and in silico models.
16. The method of claim 1 wherein outputting the hemodynamic metric comprises outputting fractional flow reserve.
17. The method of claim 1 wherein outputting the hemodynamic metric comprises outputting wall stress.
18. A method for hemodynamic determination in medical imaging, the method comprising:
generating a plurality of examples of anatomical arrangements not representing any particular patient with synthetic data;
storing a value for a flow characteristic for each of the examples of the anatomical arrangements; and
training, with machine learning, using the stored value for the flow characteristic for each of the examples of the anatomical arrangements, a classifier for predicting the flow characteristics for different anatomical arrangements.
19. The method of claim 18 wherein generating with synthetic data comprises perturbing computer modeling, physical modeling, or both in a systematic pattern.
20. A system for hemodynamic determination in medical imaging, the system comprising:
a scanner configured to scan a vessel of a patient;
a memory configured to store a plurality of features of the vessel of the patient, the features determined from the scan of the vessel;
a processor configured to apply the features to a machine-trained predictor trained with training data of synthetic examples of vessels not specific to any particular patient and other examples, and to output a prediction of a value of a hemodynamic variable based on the application of the features to the machine-trained predictor; and
a display configured to indicate the value of the hemodynamic variable.
21. The system of claim 20 wherein one of the features comprises an ischemic value and wherein the application is repeated multiple times for different modifications of the ischemic value associated with different therapeutically corrected states.