Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Systems and methods for treating, diagnosing and predicting the occurrence of a medical condition

A technology for measuring values ​​and patients, applied in the fields of medical automation diagnosis, medical informatics, informatics, etc., which can solve the problems of insufficient cancer image analysis system and complex tissue images.

Inactive Publication Date: 2010-03-31
AUREON LAB INC
View PDF13 Cites 51 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Conventional cancer image analysis systems are all the more deficient due to the fact that tissue images are often more complex than cell images and require comprehensive domain expert knowledge

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Systems and methods for treating, diagnosing and predicting the occurrence of a medical condition
  • Systems and methods for treating, diagnosing and predicting the occurrence of a medical condition
  • Systems and methods for treating, diagnosing and predicting the occurrence of a medical condition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0133] Example 1: Prediction of prostate cancer recurrence

[0134] Clinical and Morphometric Data

[0135]A number of raw morphometric features initially up to 500 were extracted from each prostate tissue image using the MAGIC tissue image analysis system based on Definiens Cellenger software. The original feature corpus is selected agnostically to avoid ignoring potentially useful features. However, it is impossible for all these morphometric features to provide the same amount of information, and the predictive model constructed based on the full set of features is likely to have poor predictive performance due to the "curse of dimensionality" [13]. Therefore, a dimensionality reduction method was employed, and finally a set of 8 morphometric features was selected.

[0136] The study was conducted on a subset of 153 patients in the cohort of prostate cancer patients undergoing radical prostatectomy. Prostate cancer recurrence (also known as biochemical recurrence (BCR)) ...

Embodiment 2

[0144] Example 2: Prediction of Prostate Cancer Recurrence and Overall Survival

[0145] Clinical, Morphometric and Molecular Data

[0146] Two studies were conducted that successfully predicted prostate-specific antigen (PSA) recurrence with prediction accuracy of 88% and 87%, respectively. Combining clinical, molecular, and morphometric features with machine learning creates a powerful platform with broad applications in patient diagnosis, treatment management, and prognosis. A third study was conducted to predict overall survival in prostate cancer patients, where the target outcome was death from any cause.

[0147] A cohort of 539 patients who underwent radical prostatectomy was studied in conjunction with high-density tissue microarrays (TMA) constructed from prostatectomy samples. Morphometric studies were performed using hematoxylin and eosin (H&E) stained tissue sections, and molecular biological determinants were assessed by immunohistochemistry (IHC). Predictive ...

Embodiment 3

[0264] Example 3: Prediction of Aggressive Disease Secondary to Prostatectomy

[0265] Clinical and Morphometric Data

[0266] This study was conducted to predict secondary aggressive disease (ie, clinical failure, confirmed by positive bone scans indicative of bone metastases from prostate cancer) in patients undergoing prostatectomy. Prior to the present invention, accurate analytical tools to provide such predictions did not exist. As noted above, the systems pathology approach of the present invention has been shown to accurately predict PSA recurrence. This study demonstrates that the invention can also be used to accurately predict distal bone metastases following prostatectomy.

[0267] A cohort of 119 patients who underwent radical prostatectomy was studied in conjunction with tissue microarrays (TMA) constructed from prostatectomy samples. Morphometric (i.e., image analysis) studies were performed using hematoxylin and eosin (H&E)-stained tissue sections, using a p...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

Methods and systems are provided that use clinical information, molecular information and computer-generated morphometric information in a predictive model for predicting the occurrence (e.g., recurrence) of a medical condition, for example, cancer. In an embodiment, a model that predicts prostate cancer recurrence is provided, where the model is based on features including one or more (e.g., all)of biopsy Gleason score, seminal vesicle invasion, extracapsular extension, preoperative PSA, dominant prostatectomy Gleason grade, the relative area of AR+ epithelial nuclei, a morphometric measurement of epithelial nuclei, and a morphometric measurement of epithelial cytoplasm. In another embodiment, a model that predicts clinical failure post-prostatectomy is provided, wherein the model is based on features including one or more (e.g., all) of dominant prostatectomy Gleason grade, lymph node invasion status, one or more morphometric measurements of lumen, a morphometric measurement of cytoplasm, and average intensity of AR in AR+ / AMACR- epithelial nuclei.

Description

[0001] related application [0002] This application is a continuation-in-part of U.S. Patent Application No. 11 / 581,052, filed October 13, 2006, which claims priority to U.S. Provisional Patent Application No. 60 / 726,809, filed October 13, 2005 and is a continuation-in-part of U.S. Patent Application No. 11 / 080,360, filed March 14, 2005, which is a continuation-in-part of U.S. Patent Application No. 11 / 080,360, filed February 25, 2005 Serial No. 11 / 067,066 (now U.S. Patent No. 7,321,881, issued January 22, 2008), which claims U.S. Provisional Patent Application No. 60, filed February 27, 2004 / 548,322 and the priority of 60 / 577,051, filed June 4, 2004; a continuation-in-part of U.S. Patent Application No. 10 / 991,897, filed November 17, 2004, which claims the Nov. 2003 Priority to U.S. Provisional Patent Application No. 60 / 520,815, filed July 17; U.S. Patent Application No. 10 / 624,233, filed July 21, 2003 (now U.S. Patent No. 6,995,020, issued February 7, 2006) Continuation-in...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F19/00
CPCG06F19/345G16H50/20
Inventor M·特弗罗夫斯基D·A·韦贝O·赛义迪
Owner AUREON LAB INC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products