Unlock instant, AI-driven research and patent intelligence for your innovation.

System and method for diagnosing gastrointestinal neoplasm

A technology of tumor, inspection system, applied in the field of endoscopic inspection

Pending Publication Date: 2020-12-04
AI SKOPY INC
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Conventional image analysis methods for diagnosing early gastric cancer using predetermined image f

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
  • System and method for diagnosing gastrointestinal neoplasm
  • System and method for diagnosing gastrointestinal neoplasm
  • System and method for diagnosing gastrointestinal neoplasm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The following detailed description of certain illustrative embodiments presents various descriptions of specific embodiments of the invention. However, the invention can be implemented in many different ways.

[0030]The terminology used in the description presented herein is used only for its use in connection with the detailed description of certain specific embodiments of the invention and is not intended to be construed in any restrictive or restrictive manner. Furthermore, embodiments of the invention may contain several novel features, no single one of which is solely responsible for its desirable attributes or is essential to practicing the invention described herein.

[0031] A model (such as a function, algorithm, system, etc.) that represents relationships and patterns in data takes inputs (sometimes called input vectors) and produces outputs corresponding to the inputs in some way (sometimes called output vectors). For example, a model can be implemented as ...

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

A system and method of diagnosing gastrointestinal neoplasm or pathologies in an endoscopy system including an endoscopy system display for displaying an image enhanced endoscopy (IEE) image. The method includes randomly generating training image samples with or without cancer region(s) by an adversarial network (AN) including collecting endoscopic training images (T1) and automatically generatinga realistic IEE image as a new training image sample (T2) using a generator network in the AN from a generated segmentation map; using a prediction network (L1PN) to learn a level 1 prediction resultbeing a cancerous probability of an IEE image from the collected T1 and T2; using a prediction network (L2PN) to learn a level 2 prediction result being detected cancerous region(s) of an IEE image;and predicting the level 1 result and the level 2 result for an IEE image using the L1PN and the L2PN and without using the AN.

Description

[0001] related application [0002] This application claims priority to U.S. Patent Provisional Application No. 62 / 629,600, filed February 12, 2018, which is incorporated herein by reference in its entirety. technical field [0003] The disclosed technology relates to endoscopy, and more specifically, to early diagnosis and detection of early gastric cancer (and other gastrointestinal cancers) by endoscopy. Background technique [0004] The need for endoscopy to diagnose gastrointestinal (GI) cancers is increasing, but only a limited number of experienced endoscopists can detect and not miss lesions, especially early-stage cancers. Thus, computer-aided diagnosis, via advances in deep learning, significantly improves accuracy / sensitivity / specificity performance (up to 95% of level), which can help doctors to perform endoscopy to diagnose and detect early gastrointestinal cancer. [0005] It has been found that conventional image analysis methods for diagnosing early gastric...

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
IPC IPC(8): G09B23/28G16H50/20G06N3/04
CPCG06N3/08G09B23/285G16H50/20G16H30/40G06N3/047G06N3/045G06T7/0012G06T2207/30028A61B1/2736G06T2207/10068A61B1/000096
Inventor 许志仲李宗錞
Owner AI SKOPY INC