Systems and methods for segmentation of intra-patient medical images
Embodiments disclose a method and system for segmenting medical images. In certain embodiments, the system comprises a database configured to store a plurality of medical images acquired by an image acquisition device. The plurality of images include at least one first medical image of an object, and a second medical image of the object, each first medical image associated with a first structure label map. The system further comprises a processor that is configured to register the at least one first medical image to the second medical image, determine a classifier model using the registered first medical image and the corresponding first structure label map, and determine a second structure label map associated with the second medical image using the classifier model.
1. A system for segmenting medical images, the system comprising:
a database configured to store a plurality of medical images acquired by an image acquisition device, including at least one first medical image of an object, and a second medical image of the object, each first medical image associated with a first structure label map; and
a processor, configured to:
register the at least one first medical image to the second medical image;
determine a convolutional neural network classifier model using the registered first medical image and the corresponding first structure label map; and
determine a second structure label map associated with the second medical image using the classifier model.
2. The system according to claim 1 , wherein the at least one first medical image includes a set of prior day images of the object.
3. The system according to claim 1 , wherein the second medical image is a current day image of the object.
4. The system according to claim 1 , wherein the first structure label map includes expert structure labels identified for the first medical image.
5. The system according to claim 1 , wherein the processor is further configured to determine the first structure label map for the first medical image using a population-trained classifier model.
6. The system according to claim 1 , wherein the processor is further configured to register the first structure label map to the second medical image using an atlas-based segmentation method, and determine a classifier model using the registered first medical image and the registered first structure label map.
7. The system according to claim 1 , wherein the classifier model is a Random Forests model.
8. The system according to claim 1 , wherein the processor is further configured to identify at least one feature in the second medical image, and apply the classifier model to the at least one feature.
9. The system according to claim 8 , wherein the at least one feature is computed using a pre-trained convolutional neural network.
10. The system according to claim 1 , wherein the at least one first medical image and the second medical image are acquired during serial radiotherapy treatment sessions of a patient.
11. The system according to claim 1 , wherein the processor is configured to determine the second structure label map prior to a radiotherapy treatment delivery.
12. A computer-implemented method for segmenting medical images, the method comprising the following operations performed by at least one processor:
receiving at least one first medical image of an object, and a second medical image of the object, from a database configured to store a plurality of medical images acquired by an image acquisition device, each first medical image associated with a first structure label map;
registering the at least one first medical image to the second medical image;
determining a convolutional neural network classifier model using the registered first medical image and the corresponding first structure label map; and
determining a second structure label map associated with the second medical image using the classifier model.
13. The method according to claim 12 , wherein the at least one first medical image includes a set of prior day images of the object.
14. The method according to claim 12 , wherein the second medical image is a current day image of the object.
15. The method according to claim 12 , further comprising determining the first structure label map for the first medical image using a population-trained classifier model.
16. The method according to claim 12 , the first structure label map is registered to the second medical image using an atlas-based segmentation method.
17. The method according to claim 12 , further comprising identifying at least one feature in the second medical image, and apply the classifier model to the at least one feature.
18. The method according to claim 12 , wherein the second structure label map is determined prior to a radiotherapy treatment delivery.
19. A non-transitory computer-readable medium containing instructions that, when executable by a processor, cause the processor to perform a method for segmenting medical images, the method comprising:
receiving at least one first medical image of an object, and a second medical image of the object, from a database configured to store a plurality of medical images acquired by an image acquisition device, each first medical image associated with a first structure label map;
registering the at least one first medical image to the second medical image;
determining a convolutional neural network classifier model using the registered first medical image and the corresponding first structure label map; and
determining a second structure label map associate with the second medical image using the classifier model.
20. The non-transitory computer-readable medium according to claim 19 , comprising, using the processor, identifying at least one feature in the second medical image, and apply the classifier model to the at least one feature, wherein the at least one feature is computed using a pre-trained convolutional neural network.