Method and system for automated brain tumor diagnosis using image classification

Abstract

A method and system for classifying tissue endomicroscopy images are disclosed. Local feature descriptors are extracted from an endomicroscopy image. Each of the local feature descriptors is encoded using a learnt discriminative dictionary. The learnt discriminative dictionary includes class-specific sub-dictionaries and penalizes correlation between bases of sub-dictionaries associated with different classes. Tissue in the endomicroscopy image is classified using a trained machine learning based classifier based on the coded local feature descriptors encoded using a learnt discriminative dictionary.

Description

[0001] This application claims the benefit of US Provisional Application 62 / 139,016, filed March 27, 2015, the disclosure of which is incorporated herein by reference. technical field [0002] The present invention relates to classifying different types of tissue in medical image data using machine learning based image classification, and more particularly to automated brain tumor diagnosis using machine learning based image classification. Background technique [0003] Cancer is a major health problem around the world. Early diagnosis of cancer is critical to the success of cancer treatment. Traditionally, pathologists obtain histopathological images of biopsies sampled from patients, examine the histopathological images under a microscope, and make judgments about the diagnosis based on their knowledge and experience. Unfortunately, intraoperative rapid histopathology is often insufficient to provide pathologists with accurate diagnostic information. Biopsies are often n...

AI Technical Summary

Problems solved by technology

However, manual judgment for diagnosis can be subjective and variable for different pathologists

In addition, optical biopsy-based diagnostic tasks can be a significant burden for pathologists due to the large amount of image data acquired

Images