Methods and systems for characterizing tissue of a subject utilizing machine learning

Abstract

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.

What is claimed is: 
     
         1 . A method for classifying tissue of a subject, the method comprising,
 at a computer system having one or more processors:   receiving time series data of fluorescence from tissue of the subject, the time series data related to perfusion of the tissue and the time series data being or having been captured by an image capture system; and   classifying a plurality of regions in the time series data, wherein the plurality of regions are classified using one or more machine learning models.   
     
     
         2 . The method of  claim 1 , wherein the regions are chosen based on one or more attributes of the data. 
     
     
         3 . The method of  claim 1 , wherein the regions are classified based on a predicted tissue condition of the region. 
     
     
         4 . The method of  claim 3 , wherein the predicted tissue condition comprises inflammation, malignancy, abnormality or disease. 
     
     
         5 . The method of  claim 1 , wherein classifying the plurality of regions in the time series data comprises providing a risk estimate for the plurality of regions. 
     
     
         6 . The method of  claim 1 , wherein the plurality of regions are classified by providing a numerical value representing a condition of the tissue. 
     
     
         7 . The method of  claim 1 , wherein the time series data comprises raw data, pre-processed data, or a combination thereof. 
     
     
         8 . The method of  claim 1 , wherein the time series data comprises pre-processed data that has been pre-processed by applying data compression, principal component analysis, autoencoding, or a combination thereof. 
     
     
         9 . The method of  claim 1 , wherein the plurality of regions are classified using an unsupervised clustering algorithm. 
     
     
         10 . The method of  claim 1 , wherein the time series data of fluorescence from tissue of the subject comprises fluorescence intensity data. 
     
     
         11 . 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 time series data of fluorescence from tissue of the subject, the time series data related to perfusion of the tissue and the time series data being or having been captured by an image capture system; and   classifying a plurality of regions in the time series data, wherein the plurality of regions are classified using one or more machine learning models.   
     
     
         12 . The system of  claim 11 , wherein the regions are chosen based on one or more attributes of the data. 
     
     
         13 . The system of  claim 11 , wherein the regions are classified based on a predicted tissue condition of the region. 
     
     
         14 . The system of  claim 13 , wherein the predicted tissue condition comprises inflammation, malignancy, abnormality or disease. 
     
     
         15 . The system of  claim 11 , wherein classifying the plurality of regions in the time series data comprises providing a risk estimate for the plurality of regions. 
     
     
         16 . The system of  claim 11 , wherein the plurality of regions are classified by providing a numerical value representing a condition of the tissue. 
     
     
         17 . The system of  claim 11 , wherein the time series data comprises raw data, pre-processed data, or a combination thereof. 
     
     
         18 . The system of  claim 11 , wherein the time series data comprises pre-processed data that has been pre-processed by applying data compression, principal component analysis, autoencoding, or a combination thereof. 
     
     
         19 . The system of  claim 11 , wherein the plurality of regions are classified using an unsupervised clustering algorithm. 
     
     
         20 . The system of  claim 11 , wherein the time series data of fluorescence from tissue of the subject comprises fluorescence intensity data. 
     
     
         21 . 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 time series data of fluorescence from tissue of the subject, the time series data related to perfusion of the tissue and the time series data being or having been captured by an image capture system; and   classifying a plurality of regions in the time series data, wherein the plurality of regions are classified using one or more machine learning models.   
     
     
         22 . The non-transitory computer-readable storage medium of  claim 21 , wherein the regions are chosen based on one or more attributes of the data. 
     
     
         23 . The non-transitory computer-readable storage medium of  claim 21 , wherein the regions are classified based on a predicted tissue condition of the region. 
     
     
         24 . The non-transitory computer-readable storage medium of  claim 23 , wherein the predicted tissue condition comprises inflammation, malignancy, abnormality or disease. 
     
     
         25 . The non-transitory computer-readable storage medium of  claim 21 , wherein classifying the plurality of regions in the time series data comprises providing a risk estimate for the plurality of regions. 
     
     
         26 . The non-transitory computer-readable storage medium of  claim 21 , wherein the plurality of regions are classified by providing a numerical value representing a condition of the tissue. 
     
     
         27 . The non-transitory computer-readable storage medium of  claim 21 , wherein the time series data comprises raw data, pre-processed data, or a combination thereof. 
     
     
         28 . The non-transitory computer-readable storage medium of  claim 21 , wherein the time series data comprises pre-processed data that has been pre-processed by applying data compression, principal component analysis, autoencoding, or a combination thereof. 
     
     
         29 . The non-transitory computer-readable storage medium of  claim 21 , wherein the plurality of regions are classified using an unsupervised clustering algorithm. 
     
     
         30 . The non-transitory computer-readable storage medium of  claim 21 , wherein the time series data of fluorescence from tissue of the subject comprises fluorescence intensity data.