Methods and systems for characterizing tissue of a subject utilizing a machine learning
Methods and systems for characterizing tissue of a subject include acquiring and receiving data for a plurality of time series of fluorescence images, identifying one or more attributes of the data relevant to a clinical characterization of the tissue, and categorizing the data into clusters based on the attributes such that the data in the same cluster are more similar to each other than the data in different clusters, wherein the clusters characterize the tissue. The methods and systems further include receiving data for a subject time series of fluorescence images, associating a respective cluster with each of a plurality of subregions in the subject time series of fluorescence images, and generating a subject spatial map based on the clusters for the plurality of subregions in the subject time series of fluorescence images. The generated spatial maps may then be used as input for tissue diagnostics using supervised machine learning.
1. A method for characterizing tissue of a subject, the method comprising,
at a computer system having one or more processors and a display:
receiving data for a time series of fluorescence images of the tissue of the subject, the time series of fluorescence images being or having been captured by an image capture system;
identifying one or more attributes of the data that are relevant to a clinical characterization of the tissue;
determining a number of clusters for categorization of the data into a plurality of clusters, wherein determining the number of clusters comprises comparing performance of a plurality of clusterings, wherein comparing performance of the plurality of clusterings comprises assessing respective distortions for the plurality of clusterings;
categorizing the data into the determined number of clusters based on the one or more attributes of the data such that data in the same cluster are more similar to each other than the data are to data in other clusters, wherein the clusters characterize the tissue;
generating a spatial map representing clinical characterization of the tissue, wherein the spatial map comprises a plurality of spatial values associated with spatial regions of the tissue and each spatial value is generated based on a cluster of the plurality of clusters; and
displaying an image based on the spatial map.
2. The method of claim 1 , wherein the data for the plurality of time series of fluorescence images of the subject comprises raw data, pre-processed data, or a combination thereof.
3. The method of claim 2 , wherein the pre-processed data is pre-processed by applying data compression, principal component analysis, autoencoding, or a combination thereof.
4. The method of claim 1 , wherein the one or more attributes of the data relevant to the clinical characterization of the tissue are identified for a plurality of subregions in the time series of fluorescence images of the subject.
5. The method of claim 4 , wherein at least one of the subregions is a pixel or a voxel in the time series of fluorescence images.
6. The method of claim 4 , wherein at least one of the subregions is a group of pixels or a group of voxels in the time series of fluorescence images of the subject.
7. The method of claim 1 , wherein the one or more attributes of the data for the time series of fluorescence images of the subject comprise a time-intensity curve, a coefficient, spatial position, onset time, time to blush, maximum fluorescence intensity, ingress of blood, egress of blood, or a combination thereof.
8. The method of claim 1 , wherein the clusters characterize the tissue based on spatial distribution of the clusters, properties of the clusters, cluster data, or a combination thereof.
9. The method of claim 8 , wherein properties of the clusters comprise shape of the clusters.
10. The method of claim 1 , wherein each cluster is represented by a centroid.
11. The method of claim 10 , wherein a centroid of a cluster is indicative of which of the one or more attributes of the data for the time series of fluorescence images of the subject contributes to data categorization.
12. The method of claim 1 , wherein categorizing the data for the time series of fluorescence images of the subject into the plurality of clusters comprises categorizing the data into ten or fewer clusters.
13. The method of claim 1 , wherein categorizing the data for the time series of fluorescence images of the subject comprises applying an unsupervised clustering algorithm.
14. The method of claim 13 , wherein the clustering algorithm is a K-means algorithm.
15. The method of claim 1 , wherein the spatial map represents differences in blood flow, perfusion patterns, or a combination thereof among the spatial regions of the tissue.
16. The method of claim 1 , further comprising training a machine learning model based on the categorized data.
17. The method of claim 16 , wherein the machine learning model is trained in a supervised machine learning algorithm.
18. The method of claim 1 , further comprising:
receiving data for a subject time series of fluorescence images of the tissue of the subject;
associating a respective cluster of the plurality of clusters with each of a plurality of subregions in the subject time series of fluorescence images;
generating a subject spatial map based on the associated clusters for the plurality of subregions in the subject time series of fluorescence images; and
displaying the subject spatial map.
19. The method of claim 18 , wherein generating the subject spatial map comprises assigning at least one of an intensity value and a color to each subregion in the subject time series of fluorescence images based on the associated cluster.
20. The method of claim 1 , wherein comparing performance of the plurality of clusterings comprises calculating a cumulative distortion for the plurality of clusterings.
21. A system comprising:
a display;
one or more processors;
memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for:
receiving data for a time series of fluorescence images of the tissue of the subject, the time series of fluorescence images being or having been captured by an image capture system;
identifying one or more attributes of the data that are relevant to a clinical characterization of the tissue;
determining a number of clusters for categorization of the data into a plurality of clusters, wherein determining the number of clusters comprises comparing performance of a plurality of clusterings, wherein comparing performance of the plurality of clusterings comprises assessing respective distortions for the plurality of clusterings;
categorizing the data into the determined number of clusters based on the one or more attributes of the data such that data in the same cluster are more similar to each other than the data are to data in other clusters, wherein the clusters characterize the tissue;
generating a spatial map representing clinical characterization of the tissue, wherein the spatial map comprises a plurality of spatial values associated with spatial regions of the tissue and each spatial value is generated based on a cluster of the plurality of clusters; and
displaying an image based on the spatial map.
22. The system of claim 21 , wherein the one or more programs include instructions for superimposing the image on an anatomical image of the tissue.
23. The system of claim 21 , further comprising a light source that provides an excitation light to induce fluorescence emission from a fluorescence imaging agent in the tissue.
24. The system of claim 23 , further comprising an image acquisition assembly configured to generate the time series of fluorescence images based on the fluorescence emission.
25. A non-transitory computer-readable storage medium storing one or more programs for execution by a computing system with one or more processors and a display, the one or more programs comprising instructions for:
receiving data for a time series of fluorescence images of the tissue of the subject, the time series of fluorescence images being or having been captured by an image capture system;
identifying one or more attributes of the data that are relevant to a clinical characterization of the tissue;
determining a number of clusters for categorization of the data into a plurality of clusters, wherein determining the number of clusters comprises comparing performance of a plurality of clusterings, wherein comparing performance of the plurality of clusterings comprises assessing respective distortions for the plurality of clusterings;
categorizing the data into the determined number of clusters based on the one or more attributes of the data such that data in the same cluster are more similar to each other than the data are to data in other clusters, wherein the clusters characterize the tissue;
generating a spatial map representing clinical characterization of the tissue, wherein the spatial map comprises a plurality of spatial values associated with spatial regions of the tissue and each spatial value is generated based on a cluster of the plurality of clusters; and
displaying an image based on the spatial map.
26. A method for characterizing tissue of a subject, the method comprising:
receiving data for a subject time series of fluorescence images of the subject, the subject time series of fluorescence images of the subject being or having been acquired by an image acquisition device;
determining a number of subregions for association of the data with a plurality of subregions, wherein determining the number of subregions comprises comparing performance of a plurality of clusterings, wherein comparing performance of the plurality of clusterings comprises assessing respective distortions for the plurality of clusterings;
associating a respective category of a predetermined plurality of categories with each of the determined number of subregions in the subject time series of fluorescence images, wherein the categories characterize tissue and are based on one or more attributes relevant to a clinical characterization of tissue, such that a subregion associated with a given category is more similar to other subregions associated with the given category than subregions associated with other categories;
generating a spatial map representing the tissue based on the associated categories for the plurality of subregions in the subject time series of fluorescence images; and
displaying the spatial map as an image.