Computer vision for cancerous tissue recognition
A system includes an imager, a processor, and an output module. The imager is configured to provide a plurality of tissue images. The processor is coupled to the imager and is configured to receive the plurality of images. The processor is coupled to a memory. The memory has instructions for determining classification of a region of tissue associated with the plurality of tissue images. Determining classification includes fusing discriminator outputs from a region covariance descriptor and from a normalized color histogram discriminator. The output module is coupled to the processor. The output module is configured to provide a three dimensional representation of the tissue.
1. A system comprising:
an imager configured to provide a plurality of histopathological images for a region of a tissue sample;
a processor coupled to the imager and configured to receive the plurality of histopathological images, the processor coupled to a memory, the memory having instructions for determining classification of the region of tissue associated with the plurality of histopathological images, wherein determining classification includes fusing discriminator outputs from a region covariance descriptor and from a normalized color histogram discriminator; and
an output module coupled to the processor, the output, module configured to provide a three dimensional representation of the region of the tissue.
2. The system of claim 1 wherein the processor is configured to fuse discriminator output from the region covariance descriptor with a positive definite kernel matrix generated from color histograms.
3. The system of claim 1 wherein the processor is configured to receive an output from the normalized color histogram discriminator corresponds to a normalized histogram.
4. The system of claim 1 wherein the processor is configured to receive an output from the region covariance descriptor in which the region covariance descriptor provides covariance matrix of five dimensions.
5. The system of claim 1 wherein the processor is configured to determine a classification based on a sparse code and a dictionary matrix.
6. The system of claim 1 wherein the processor is configured to determine a classification based on at least one of a bank of Gabor filters, a histogram of oriented gradients, a plurality of Fisher vectors, and a convoluted neural network model.
7. The system of claim 1 wherein the processor is configured to determine a classification based on a covariance-kernel descriptor.
8. The system of claim 7 wherein the processor is configured to determine a classification based on a bag of visual words representation and based on scale invariant feature transform descriptors.
9. The system of claim 1 wherein the imager includes a graphical user interface.
10. The system of claim 9 wherein the graphical user interface is configured to allow user selection of magnification of an image.
11. The system of claim 9 wherein the graphical user interface is configured to allow user selection of the region.