Automatic quality checks for radiotherapy contouring
Systems, devices, methods, and computer processing products for automatically checking for errors in segmentation (contouring) using heuristic and/or statistical evaluation methods.
1. A non-transitory computer readable medium containing program instructions for automatically evaluating a segment, wherein execution of the program instructions by a computer processing device causes the computer processing device to carry out the following steps:
generate a plurality of binary images for the segment;
combine the binary images of the segment using at least one of a plurality of Boolean operators to obtain a resulting binary image;
count the pixels/voxels in the resulting binary image;
determine whether the number of pixels/voxels is within a predetermined range; and
generate a signal to indicate that a segmentation error is present if the number of pixels/voxels is not within the predetermined range.
2. The non-transitory computer readable medium of claim 1 , further comprising evaluating the segment using a statistical evaluation method.
3. The non-transitory computer readable medium of claim 2 , wherein the evaluating comprises evaluating a shape of the segment and determining whether the shape of the segment is within a predetermined range of known shapes for the segment.
4. The non-transitory computer readable medium of claim 3 , further comprising generating a shape model based on a probabilistic distribution of shape variations found in the range of known shapes for the segment, and performing a statistical test to check if the shape of the segment is within the predetermined range.
5. The non-transitory computer readable medium of claim 4 , wherein the probabilistic distribution includes a multivariate normal distribution (μ, Σ).
6. The non-transitory computer readable medium of claim 5 , wherein the performing of the statistical check comprises evaluating how well the shape fits within the multivariate normal distribution using a probabilistic principal component analysis (PPCA).
7. The non-transitory computer readable medium of claim 4 , wherein if the shape of the segment does not fit within the multivariate normal distribution within a predetermined value, it is determined that a segmentation error is present.
8. The non-transitory computer readable medium of claim 1 , wherein the evaluating is automatic and in real-time.