Systems and methods for automated screening and prognosis of cancer from whole-slide biopsy images

Abstract

The invention provides systems and methods for detection, grading, scoring and tele-screening of cancerous lesions. A complete scheme for automated quantitative analysis and assessment of human and animal tissue images of several types of cancers is presented. Various aspects of the invention are directed to the detection, grading, prediction and staging of prostate cancer on serial sections/slides of prostate core images, or biopsy images. Accordingly, the invention includes a variety of sub-systems, which could be used separately or in conjunction to automatically grade cancerous regions. Each system utilizes a different approach with a different feature set. For instance, in the quantitative analysis, textural-based and morphology-based features may be extracted at image- and (or) object-levels from regions of interest. Additionally, the invention provides sub-systems and methods for accurate detection and mapping of disease in whole slide digitized images by extracting new features through integration of one or more of the above-mentioned classification systems. The invention also addresses the modeling, qualitative analysis and assessment of 3-D histopathology images which assist pathologists in visualization, evaluation and diagnosis of diseased tissue. Moreover, the invention includes systems and methods for the development of a tele-screening system in which the proposed computer-aided diagnosis (CAD) systems. In some embodiments, novel methods for image analysis (including edge detection, color mapping characterization and others) are provided for use prior to feature extraction in the proposed CAD systems.

Description

BACKGROUND OF THE INVENTION[0001]1. Field of the Invention[0002]The invention generally relates to diagnostic procedures for the detection, analysis, assessment, classification, and grading of cancer from digitized histopathological images. More particularly, the invention relates to the use of computer analysis of biopsy samples to detect and classify / grade and score prostate cancer.[0003]2. Description of the Relevant Art[0004]Prostate cancer is the second killer of American men. Current statistics indicate that 1 in 6 men will suffer from prostate cancer, 1 in 32 men will die from prostate cancer. Although prostate cancer can be diagnosed at early stages, 80% of men diagnosed with prostate carcinoma are above 65 years old.[0005]The risk of developing prostate cancer is commonly attached with the patient's age. In general, doctors recommend males of age 50 or higher to screen for prostate cancer. However, screening could be recommended for males who are at a higher risk of develop...

AI Technical Summary

Benefits of technology

[0022]The large number of disparate, differently-scaled Gleason scoring methods can lead to a variety of misinterpretations of reading actual cancer aggressiveness. We propose generalized scoring methods which simultaneously covers all previous scoring methods by relieving the dependency on only two or three of the most dominant patterns, extending the range of measured patterns to all possible Gleason patterns, and combining all observed Gleason pattern grades into one, continuous-scale Gleason score which is bounded by the traditional Gleason Grade limits, 1 through 5. These novel scores provide a more accurate, unambiguous measure of prostate cancer aggressiveness.

Problems solved by technology

The large number of disparate, differently-scaled Gleason scoring methods can lead to a variety of misinterpretations of reading actual cancer aggressiveness.

Only few systems have addressed the biopsy whole slide processing.

While some of the systems and methods mentioned above are able to classify predefined regions of interest, they do not apply to a biopsy image as a whole.

Images