Interactive and Automated Tissue Image Analysis with Global Training Database and Variable-Abstraction Processing in Cytological Specimen Classification and Laser Capture Microdissection Applications

Abstract

A system and method for performing tissue image analysis and region of interest identification for further processing applications such as laser capture microdissection is provided. The invention provides three-stage processing with flexible state transition that allows image recognition to be performed at an appropriate level of abstraction. The three stages include processing at one or more than one of the pixel, subimage and object levels of processing. Also, the invention provides both an interactive mode and a high-throughput batch mode which employs training files generated automatically.

1 - 18 . (canceled) 
     
     
         19 . A computer-implemented method for image analysis, the computer-implemented method comprising:
 capturing a first image of a tissue sample using laser capture microdissection;   transforming the first image into a feature space;   selecting a level of abstraction;   selecting a database containing parameters based on the selected level of abstraction;   classifying the first image into regions of interest employing the parameters from the database based on the selected level of abstraction;   updating the parameters of the database with data from the first image;   capturing a second image of a tissue sample using laser capture microdissection;   transforming the second image into a feature space;   classifying the second image into regions of interest employing the updated parameters from the database based on the selected level of abstraction; and   updating the parameters of the database with data from the second image.   
     
     
         20 . The computer-implemented method for image analysis of  claim 19  wherein selecting the level of abstraction includes selecting pixel processing. 
     
     
         21 . The computer-implemented method for image analysis of  claim 20  further including transmitting the regions of interest obtained from pixel processing for laser capture microdissection. 
     
     
         22 . The computer-implemented method for image analysis of  claim 19  wherein selecting the level of abstraction includes selecting subimage processing. 
     
     
         23 . The computer-implemented method for image analysis of  claim 22  wherein classifying the first image includes classifying the first image into regions of interest employing parameters from the database for pixel processing and classifying the first image into regions of interest employing parameters from the database for subimage processing; and wherein classifying the second image includes classifying the second image into regions of interest employing parameters from the database for pixel processing and classifying the second image into regions of interest employing parameters from the database for subimage processing. 
     
     
         24 . The computer-implemented method for image analysis of  claim 23  further including transmitting the regions of interest obtained from subimage processing for laser capture microdissection. 
     
     
         25 . The computer-implemented method for image analysis of  claim 19  wherein selecting the level of abstraction includes selecting object processing. 
     
     
         26 . The computer-implemented method for image analysis of  claim 25  wherein classifying the first image includes classifying the first image into regions of interest employing parameters from the database for pixel processing and classifying the first image into regions of interest employing parameters from the database for subimage processing and classifying the first image into regions of interest employing parameters from the database for object processing; and wherein classifying the second image includes classifying the second image into regions of interest employing parameters from the database for pixel processing and classifying the second image into regions of interest employing parameters from the database for subimage processing and classifying the second image into regions of interest employing parameters from the database for object processing. 
     
     
         27 . The computer-implemented method for image analysis of  claim 26  further including transmitting the regions of interest obtained from object processing for laser capture microdissection. 
     
     
         28 . The computer-implemented method for image analysis of  claim 25  wherein classifying the first image includes classifying the first image into regions of interest employing parameters from the database for pixel processing and classifying the first image into regions of interest employing parameters from the database for object processing; and wherein classifying the second image includes classifying the second image into regions of interest employing parameters from the database for pixel processing and classifying the second image into regions of interest employing parameters from the database for object processing. 
     
     
         29 . The computer-implemented method for image analysis of  claim 28  further including the step of transmitting the regions of interest obtained from object processing for laser capture microdissection. 
     
     
         30 . The computer-implemented method for image analysis of  claim 19  wherein receiving the first image comprises receiving color information and wherein transforming comprises transforming the first image into color features. 
     
     
         31 . The computer-implemented method for image analysis of  claim 19 , further comprising, classifying at least one of the first image or the second image into at least one non-region of interest employing the parameters from the database. 
     
     
         32 . The computer-implemented method for image analysis of  claim 19 , wherein the first image and the second image are captured from the same tissue sample. 
     
     
         33 . The computer-implemented method for image analysis of  claim 19 , wherein the first image and the second image are captured from the different tissue samples. 
     
     
         34 . A computer-implemented method for image analysis, the computer-implemented method comprising:
 receiving a first image of a first tissue sample using laser capture microdissection;   selecting a database containing parameters;   classifying the first image into at least one region of interest employing the parameters from the database;   updating the parameters of the database with data from the first image to produce updated parameters;   capturing a second image of a tissue sample using laser capture microdissection;   classifying the second image into regions of interest employing the updated parameters from the database based; and   updating the parameters of the database a second time with data from the second image.   
     
     
         35 . The computer-implemented method for image analysis of  claim 34 , further comprising, classifying at least one of the first image or the second image into at least one non-region of interest employing the parameters from the database. 
     
     
         36 . The computer-implemented method for image analysis of  claim 34 , wherein the first image and the second image are captured from the same tissue sample. 
     
     
         37 . The computer-implemented method for image analysis of  claim 34 , wherein the first image and the second image are captured from the different tissue samples.