Stress prediction based on neural network
Disclosed herein are related to a system, a method, and a non-transitory computer readable medium for simulating, predicting, or estimating, based on machine learning neural networks, wall stress of a body part. In one approach, a first neural network automatically detects features in multiple images of a body part. For example, the first neural network may detect, for each image, a lumen and a wall of an aorta. According to the detected features, a second neural network may simulate, estimate, or predict wall stress of the body part in response to pressure applied to the body part. For example, a model generator can generate a three-dimensional model of the body part according to the detected features in the multiple images, and the second neural network can simulate, estimate, or predict wall stress of the body part according to the three-dimensional model.
1. A system comprising:
(a) a first neural network configured to:
detect, from a first image of a first cross section of a body part and its surrounding body part, a first outer boundary of the first cross section of the body part and a first inner boundary of the first cross section of the body part, and
detect, from a second image of a second cross section of the body part and the surrounding body part, a second outer boundary of the second cross section of the body part and a second inner boundary of the second cross section of the body part;
(b) a model generator configured to:
generate a three dimensional model of the body part by connecting points on the first outer boundary and the second outer boundary, and connecting points on the first inner boundary and the second inner boundary, wherein the three dimensional model comprises shape indices and location information of the shape indices;
(c) a second neural network configured to:
predict wall stress of the body part, according to the three dimensional model generated based on the first outer boundary, the first inner boundary, the second outer boundary, and the second inner boundary; and
(d) a risk determinator configured to:
compare, for each point of the three dimensional model, the wall stress to a threshold, and
provide an indication associated with the three dimensional model indicative of a risk of rupture according to the wall stress exceeding the threshold.
2. The system of claim 1 ,
wherein the model generator is coupled between the first neural network and the second neural network, and wherein the second neural network is configured to predict the wall stress of the body part according to geometry information comprising the three dimensional model derived from the first outer boundary, the first inner boundary, the second outer boundary, and the second inner boundary.
3. The system of claim 2 , wherein the model generator is configured to:
determine the shape indices from the generated three dimensional model, and
provide the shape indices as input to the second neural network to predict the wall stress of the body part.
4. The system of claim 2 , wherein the geometry information includes the shape indices and the location information of the shape indices.
5. The system of claim 4 , wherein the shape indices include at least one of: a z-height ratio, a distance to a centroid, an intraluminal thrombus thickness, a principal curvature of a neighboring node, tortuosity, or a wall to lumen vector.
6. The system of claim 2 , wherein in a training phase for the second neural network, the second neural network is configured to:
predict the wall stress of the body part;
compare the predicted wall stress with a target wall stress of the body part; and
update a configuration of the second neural network according to the comparison.
7. The system of claim 1 , wherein the body part has a tubular structure.
8. The system of claim 1 , wherein the body part is an artery, the first outer boundary and the second outer boundary corresponding to a wall of the artery, and the first inner boundary and the second inner boundary corresponding to a lumen of the artery.
9. The system of claim 1 , further comprising:
a geometric information generator coupled between the first neural network and the second neural network, the geometric information generator configured to determine geometry information according to the first outer boundary, the first inner boundary, the second outer boundary, and the second inner boundary, the geometry information comprising the shape indices.
10. The system of claim 1 , wherein the second neural network comprises a regression model.
11. The system of claim 1 , wherein the first neural network comprises a convolutional neural network.
12. The system of claim 1 , further comprising:
a risk determiner configured to determine a risk of an aneurysm according to the predicted wall stress of the body part.
13. The system of claim 1 , wherein during a training phase of the first neural network, the first neural network is configured to:
receive, as part of training data, a plurality of images each comprising a corresponding cross section of the body part and the surrounding body part; and
receive, as part of the training data, for each of the plurality of images, an outer boundary of the corresponding cross section of the body part, and an inner boundary of the corresponding cross section of the body part.
14. A method comprising:
(a) detecting, by a first neural network, from a first image of a first cross section of a body part of a subject and its surrounding body part, a first outer boundary of the first cross section of the body part and a first inner boundary of the first cross section of the body part;
(b) detecting, by the first neural network, from a second image of a second cross section of the body part and the surrounding body part, a second outer boundary of the second cross section of the body part and a second inner boundary of the second cross section of the body part;
(c) generating, by a model generator, a three dimensional model of the body part by connecting points on the first outer boundary and the second outer boundary, and connecting points on the first inner boundary and the second inner boundary, wherein the three dimensional model comprises a plurality of shape indices and location information of the plurality of shape indices;
(d) predicting, by a second neural network, wall stress of the body part of the subject, according to the three dimensional model generated based on the first outer boundary, the first inner boundary, the second outer boundary, and the second inner boundary;
(e) comparing, by a risk determinator, for each point of the three dimensional model, the wall stress to a threshold; and
(f) providing, by the risk determinator, an indication associated with the three dimensional model indicative of a risk of rupture according to the wall stress exceeding the threshold.
15. The method of claim 14 , further comprising:
evaluating a risk of an abdominal aortic aneurysm, a ventricular aneurysm, or a brain aneurysm, according to the predicted wall stress.
16. The method of claim 14 , wherein the body part has a tubular structure.
17. The method of claim 14 , wherein the body part is a human body part, the human body part including an aorta, artery, ureter, intestine, or heart.
18. A system comprising:
(a) a first neural network configured to:
detect, from a first image of a first cross section of a body part and its surrounding body part, a first outer boundary of the first cross section of the body part and a first inner boundary of the first cross section of the body part;
(b) a model generator configured to:
generate a three dimensional model of the body part by connecting points on the first outer boundary, and connecting points on the first inner boundary, wherein the three dimensional model comprises shape indices and location information of the shape indices;
(c) a second neural network configured to:
predict wall stress of the body part, according to the three dimensional model generated based on the first outer boundary and the first inner boundary; and
(d) a risk determinator configured to:
compare each point of the three dimensional model to a threshold, and
provide an indication of one or more points of the three dimensional model exceeding the threshold indicative of a risk of rupture.
19. The system of claim 18 ,
wherein the second neural network is configured to predict the wall stress of the body part according to geometry information including the shape indices and the location information of the shape indices, and
wherein the shape indices include at least one of: a z-height ratio, a distance to a centroid, an intraluminal thrombus thickness, a principal curvature of a neighboring node, tortuosity, or a wall to lumen vector.