Systems and methods for accelerated online adaptive radiation therapy
Systems and methods for accelerated online adaptive radiation therapy (“ART”) are described. The improvements to online ART are generally provided based on the use of textural analysis and machine learning algorithms implemented with a hardware processor and a memory. The described systems and methods enable more efficient and accurate online adaptive replanning (“OLAR”), which can also be implemented in clinically acceptable timeframes. For example, OLAR can be reduced from taking 10-30 minutes down to 5-10 minutes.
1 . A method for generating corrected radiation treatment plan contour data, the method comprising:
(a) accessing with a computer system, previously generated contour data comprising contours associated with a radiation treatment plan for a subject;
(b) accessing with the computer system, an image of the subject;
(c) computing with the computer system, image feature data for a region-of-interest (ROI) in the image, wherein the ROI is defined by a contour in the contour data;
(d) generating with the computer system, an image feature map from the image feature data, wherein the image feature map depicts image feature values in the ROI; and
(e) generating corrected contour data by inputting the image feature map and the contour data to an active contour algorithm, generating output as the corrected contour data, wherein the image feature map is used by the active contour algorithm as an external force that guides an active curve to find a corrected boundary for the contour data.
2 . The method as recited in claim 1 , wherein the ROI is defined by adding a margin to the contour in the contour data.
3 . The method as recited in claim 2 , wherein the margin is 10 mm.
4 . The method as recited in claim 1 , wherein the active contour algorithm includes a deformation phase in which a snake model is implemented to move contour points by minimizing an energy function having an internal energy term and an external energy term, wherein the image feature map is used as the external force in the external energy term.
5 . The method as recited in claim 4 , wherein the external force is applied to contour points corresponding to image feature values lower than a threshold value.
6 . The method as recited in claim 1 , wherein the image feature data comprise intensity histogram-based image features.
7 . The method as recited in claim 6 , wherein the intensity histogram-based image features comprise at least one of mean, standard deviation, range, skewness, and kurtosis.
8 . The method as recited in claim 1 , wherein the image feature data comprise texture features computed based on a gray-level co-occurrence matrix (GLCM).
9 . The method as recited in claim 8 , wherein the image feature map comprises a GLCM cluster shade feature map.
10 . The method as recited in claim 1 , wherein the image feature data comprise texture features computed based on a gray-level run-length matrix.