Methods and systems for real-time image 3D segmentation regularization
Various methods and systems are provided for real-time image segmentation of medical image data. In one example, the real-time image segmentation of the medical image data may include updating an initial segmentation of the medical image data in real-time. The update may be based on a user input to a regularization brush applied to the medical image data, the user input to the regularization brush allowing modification of a volume of the initial segmentation.
1. A system for segmentation regularization of 3D medical image data, comprising:
a computerized tomography (CT) system configured to generate 3D medical image data of a patient;
a user interface (UI) configured to allow a user to implement a segmentation of the 3D medical image data, the UI comprising:
a graphical user interface (GUI) including one or more segmentation tools;
a regularization brush; and
a computing device communicatively coupled to the CT system and the UI, the computing device configured with instructions in non-transitory memory that when executed cause the computing device to:
render one or more views of the 3D medical image data generated by the CT system;
receive a first user input from the GUI, the first user input including a radius of a sphere of influence of the regularization brush, and an adjustment of a nudge capability of the regularization brush;
receive a second user input from the regularization brush applied to the rendered 3D medical image data, the second user input including a position of the regularization brush;
receive an initial segmentation of the 3D medical image data;
extract a region of interest (ROI) from the rendered 3D medical image data, the ROI being the sphere of influence of the regularization brush;
adaptively resample the rendered 3D medical image data within the ROI;
calculate a probability map for the initial segmentation;
apply thresholding to the probability map in order to generate a binary mask; and
output an updated segmentation of the 3D medical image data, the updated segmentation based on the first user input and the second user input to the regularization brush, the calculated probability map, and the thresholding applied to the probability map.
2. The system of claim 1 , wherein the calculating of the probability map for the initial segmentation is based on the first user input and the second user input to the regularization brush, and a function for applying a low-pass filter to the initial segmentation.
3. The system of claim 2 , wherein the adjustment of the nudge capability of the regularization brush includes expansion of the segmentation via application of the regularization brush, and reduction of the segmentation via application of the regularization brush.
4. The system of claim 2 , wherein the low-pass filter applied to the initial segmentation is implemented through machine learning.
5. The system of claim 4 , wherein machine learning used in the low-pass filter is implemented via a convolutional neural network (CNN).
6. The system of claim 1 , wherein, to apply thresholding to the probability map to generate the binary mask, the computing device is further configured with instructions that when executed cause the computing device to indicate a value of probability below which voxels of the probability map will not be included in the updated segmentation of the 3D medical image data.
7. The system of claim 5 , wherein the value is between 0 and 1.
8. A method for segmentation regularization of 3D medical image data, comprising:
a computerized tomography (CT) system configured to generate 3D medical image data of a patient;
a user interface (UI) configured to allow a user to implement a segmentation of the 3D medical image data, the UI comprising:
a graphical user interface (GUI) including one or more segmentation tools;
a regularization brush; and
a computing device communicatively coupled to the CT system and the UI, the computing device configured with instructions in non-transitory memory that when executed cause the computing device to:
render one or more views of the 3D medical image data generated by the CT system;
receive a first user input from the GUI, the first user input including a radius of a sphere of influence of the regularization brush, and an adjustment of a nudge capability of the regularization brush;
receive a second user input from the regularization brush applied to the rendered 3D medical image data, the second user input including a position of the regularization brush;
receive an initial segmentation of the 3D medical image data;
extract a region of interest (ROI) from the rendered 3D medical image data, the ROI being the sphere of influence of the regularization brush;
adaptively resample the rendered 3D medical image data within the ROI;
calculate a probability map for the initial segmentation;
apply thresholding to the probability map in order to generate a binary mask; and
output an updated segmentation of the 3D medical image data, the updated segmentation based on the first user input and the second user input to the regularization brush, the calculated probability map, and the thresholding applied to the probability map.
9. The method of claim 8 , wherein the calculating of the probability map for the initial segmentation is based on the first user input and the second user input to the regularization brush, and a function for applying a low-pass filter to the initial segmentation.
10. The method of claim 9 , wherein the adjustment of the nudge capability of the regularization brush includes expansion of the segmentation via application of the regularization brush, and reduction of the segmentation via application of the regularization brush.
11. The method of claim 9 , wherein the low-pass filter applied to the initial segmentation is implemented through machine learning.
12. The method of claim 11 , wherein machine learning used in the low-pass filter is implemented via a convolutional neural network (CNN).
13. The method of claim 8 , wherein, to apply thresholding to the probability map to generate the binary mask, the computing device is further configured with instructions that when executed cause the computing device to indicate a value of probability below which voxels of the probability map will not be included in the updated segmentation of the 3D medical image data.
14. The method of claim 12 , wherein the value is between 0 and 1.