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

A hierarchical processing technique for lesion detection, classification, and segmentation on microscopy images

A microscopic image and image analysis technology, which is applied in image data processing, image analysis, image enhancement, etc., can solve problems such as limiting the accuracy of CAD systems

Pending Publication Date: 2022-01-28
TENCENT AMERICA LLC
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the accuracy of current CAD systems may be limited by only processing images of high magnitude

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
  • A hierarchical processing technique for lesion detection, classification, and segmentation on microscopy images
  • A hierarchical processing technique for lesion detection, classification, and segmentation on microscopy images
  • A hierarchical processing technique for lesion detection, classification, and segmentation on microscopy images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The present disclosure provides a hierarchical image processing technique to speed up lesion detection on microscopic images. The system takes as input a magnified tissue image, such as a microscopic image (MSI, microscope image) (e.g., an image acquired under a microscope) or a whole-slide image (WSI, whole-slide image) (e.g., obtained from a whole-slide image). images acquired by slide imaging scanners). The system then automatically processes the images to identify lesions or abnormal tissue, such as cancer cells, on the images. The system can segment lesion areas and classify lesions into subtypes. To speed up calculations compared to previous techniques, the system is configured to first process images at a coarse level. Based on the lower certainty of determining the coarse level, the system is configured to switch to the fine level. To improve prediction accuracy, the system is also configured to fuse information from different scales.

[0019] The present di...

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 method and apparatus include performing a first image analysis at a first resolution of an input tissue image. An uncertainty map is generated based on performing the first image analysis. A set of uncertain regions of the input tissue image are identified based on the uncertainty map. A second image analysis of the set of uncertain regions is performed at a second resolution of the tissue image that is greater than the first resolution. An analysis result is generated based on the first image analysis and the second image analysis.

Description

[0001] Cross References to Related Applications [0002] This application claims priority to U.S. Patent Application Serial No. 16 / 669,881 filed with the U.S. Patent and Trademark Office on October 31, 2019, the disclosure of which is incorporated herein by reference in its entirety. Background technique [0003] So far, different computer-aided diagnosis (CAD) systems have been proposed for automatically or semi-automatically classifying, detecting, and segmenting lesions from microscopic images. Such a system could help doctors and pathologists increase their throughput and improve the quality of diagnosis. Some fully automated systems can also work alone to perform a pre-diagnosis or provide a second opinion. A good CAD system can also reduce costs and ultimately improve patient health. [0004] Additional CAD systems are currently integrating machine learning models such as convolutional neural networks (CNN) or other deep learning methods. Machine learning models requi...

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): G06T7/00A61B5/05G06N3/04G06N3/08
CPCG16H50/20G16H30/40G06T2207/10056G06T2207/30024G06T7/11G06T7/0012G06T2207/20084G06T2207/20016G06T3/40G06T2207/30096
Inventor 陈翰博
Owner TENCENT AMERICA LLC