Systems and Methods for Automated Diagnosis and Decision Support for Breast Imaging

Abstract

CAD (computer-aided diagnosis) systems and applications for breast imaging are provided, which implement methods to automatically extract and analyze features from a collection of patient information (including image data and/or non-image data) of a subject patient, to provide decision support for various aspects of physician workflow including, for example, automated diagnosis of breast cancer other automated decision support functions that enable decision support for, e.g., screening and staging for breast cancer. The CAD systems implement machine-learning techniques that use a set of training data obtained (learned) from a database of labeled patient cases in one or more relevant clinical domains and/or expert interpretations of such data to enable the CAD systems to “learn” to analyze patient data and make proper diagnostic assessments and decisions for assisting physician workflow.

1 . A system for providing automatic diagnosis and decision support, comprising:
 an image acquisition device for obtaining information from image data of a subject patient;   a phase spotting unit for receiving non-image data records of the subject patient, extracting an unstructured free-text source from the non-image data records, and identifying phrases of interest from the free-text source;   a rules database including a list of rules for providing inferences drawn from the identified phrases of interest; and   an automatic diagnosis unit for providing diagnosis using the information from the image data and the inferences drawn from the identified phrases of interest.   
   
   
       2 . The system of  claim 1 , wherein the image data includes a breast of the subject patient and the automatic diagnosis unit provides diagnosis pertaining to abnormal breast tissue. 
   
   
       3 . The system of  claim 1 , further comprising a patient management module for recommending therapies to the patient based on the provided diagnosis. 
   
   
       4 . The system of  claim 1 , wherein the image data is ultrasound image data and wherein the automatic diagnosis unit automatically extracts one or more features from the ultrasound data in providing diagnosis. 
   
   
       5 . The system of  claim 1 , wherein the image data is acquired using an ultrasound medical imaging device. 
   
   
       6 . The system of  claim 5 , wherein the ultrasound medical imaging device is a three-dimensional ultrasound. 
   
   
       7 . The system of  claim 1  wherein the automatic diagnosis unit is a computer aided diagnosis system. 
   
   
       8 . The system of  claim 1 , wherein the image data is acquired using an X-ray mammography scanner, an MRI scanner, an ultrasound imager or a combination thereof. 
   
   
       9 . A method for providing automatic diagnosis and decision support, comprising:
 obtaining information from image data of a subject patient;   receiving non-image data records of the subject patient, extracting an unstructured free-text source from the non-image data records, and identifying phrases of interest from the free-text source;   referencing a rules database to provide inferences drawn from the identified phrases of interest; and   automatically providing diagnosis using the information from the image data and the inferences drawn from the identified phrases of interest,   where in the above steps are performed using a computer assisted diagnosis system.   
   
   
       10 . The method of  claim 9 , wherein the image data includes a breast of the subject patient and the automatic diagnosis comprises diagnosis pertaining to abnormal breast tissue. 
   
   
       11 . The method of  claim 9 , wherein one or more therapies are recommended to the patient based on the provided diagnosis. 
   
   
       12 . The method of  claim 11 , wherein the recommending of the one or more therapies is influenced using user criteria provided through a user interface. 
   
   
       13 . The method of  claim 11 , wherein the recommending of the one or more therapies is influenced clinical knowledge provided through a clinical knowledge database. 
   
   
       14 . The method of  claim 11 , wherein the recommending of the one or more therapies utilizes an interactive diagnostic workflow assistance module. 
   
   
       15 . The method of  claim 9 , wherein automatically providing the diagnosis is influenced by user criteria provided through a user interface. 
   
   
       16 . The method of  claim 9 , wherein automatically providing the diagnosis is influenced by clinical knowledge provided through a clinical knowledge database. 
   
   
       17 . The method of  claim 9 , wherein automatically providing the diagnosis utilizes an interactive diagnostic workflow assistance module. 
   
   
       18 . A method for providing automatic diagnosis and decision support, comprising:
 obtaining information from image data of a subject patient;   receiving non-image data records of the subject patient, extracting an unstructured free-text source from the non-image data records, and identifying phrases of interest from the free-text source;   automatically providing diagnosis using the information from the image data and the identified phrases of interest; and   recommending one or more therapies based on the provided diagnosis and user criteria,   where in the above steps are performed using a computer assisted diagnosis system.   
   
   
       19 . The method of  claim 18 , wherein the image data includes a breast of the subject patient and the automatic diagnosis comprises diagnosis pertaining to abnormal breast tissue. 
   
   
       20 . The method of  claim 18 , wherein the image data is ultrasound image data, X-ray mammography image data, MRI data, or a combination thereof.