Skip to main navigation Skip to search Skip to main content

Ultrasonic classification of breast tumors based on multi-instance learning

  • School of Computer Science and Technology, Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Currently, locating the tumor ROI is the prerequisite of feature extraction. However, due to the low contrast and complex background of ultrasound images it is hard to obtain the accurate tumor ROI. Other organizations often been wrongly extracted as a tumor region, result in multi-ROI (non-tumor, tumor) in one image. As the result, the performance of tumor classification algorithms will be poor. In such case, ability to discriminate non-tumor and tumor area of classifier is of the most important. This paper proposed bag structure constructor on the basis of multi-ROI and multiple instance learning (MIL) classification algorithm is introduced to solve the above problem that has ability to discriminate nontumor and tumor area to some extent. Experiments show that accuracy of the proposed method in such problems is 10% more than the traditional ultrasonic classification of breast tumor.

Original languageEnglish
Title of host publicationMIPPR 2011
Subtitle of host publicationParallel Processing of Images and Optimization and Medical Imaging Processing
DOIs
StatePublished - 2011
Externally publishedYes
EventMIPPR 2011: Parallel Processing of Images and Optimization and Medical Imaging Processing - Guilin, China
Duration: 4 Nov 20116 Nov 2011

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume8005
ISSN (Print)0277-786X

Conference

ConferenceMIPPR 2011: Parallel Processing of Images and Optimization and Medical Imaging Processing
Country/TerritoryChina
CityGuilin
Period4/11/116/11/11

Keywords

  • Breast ultrasound
  • Classification
  • Multiple instance learning
  • Texture

Fingerprint

Dive into the research topics of 'Ultrasonic classification of breast tumors based on multi-instance learning'. Together they form a unique fingerprint.

Cite this