설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: F:\c_backup\바탕화면\연구실 관련\홈페이지ResearchField(CAD)\Project\image\demo\top_logo.gif

설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: F:\c_backup\바탕화면\연구실 관련\홈페이지ResearchField(CAD)\Project\image\demo\project_title.gif

설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: F:\c_backup\바탕화면\연구실 관련\홈페이지ResearchField(CAD)\Project\image\demo\project_profile.gif

 

설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: F:\c_backup\바탕화면\연구실 관련\홈페이지ResearchField(CAD)\Project\image\demo\profile_title.gif

Development of Mammography Computer Aided Diagnosis (CAD)

-      Multiresolution local texture features for mass classification

 

설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: F:\c_backup\바탕화면\연구실 관련\홈페이지ResearchField(CAD)\Project\image\demo\profile_period.gif

2010 . 11 ~ current

설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: F:\c_backup\바탕화면\연구실 관련\홈페이지ResearchField(CAD)\Project\image\demo\project_overview.gif

 

1. Introduction

l  Computer-aided Detection (CADe) for breast cancer screening using mammography

n  To help radiologists find cancer

n  To help radiologists avoid missing cancer

l  Main limitation of current CAD systems is high false-positive (FP) detection rates

n  Unnecessary biopsies

n  Financial expense to the health care system

n  Adding unnecessary workload to radiologists/pathologists/surgeons

l  We propose a new and novel approach for the extraction of texture features for FP reduction purpose

n  Using Local Binary Pattern (LBP) operation

n  Charactering regional texture patterns of mass subregions

n  Capturing spatial structure information of mass

n  Employing multiresolution analysis

 

2. LBP texture feature extraction

2.1. LBP operation

 

 

2.2. Region-of-interest (ROI) partition

l  Objective

n  To characterize texture patterns of the masses on a regional level

n  To capture spatial structure (global geometry) of the masses

l  Rationale

n  A mass ROI is likely to be have several subregions showing different texture statistics

 

 

2.3. Extracting LBP Patterns of Core and Ribbon Regions

 

2.4. Multiresolution Analysis

l  Exploiting additional discriminant information

l  Using LBP operation for any quantization of the angular space and for any spatial resolution

 

 

 

2.5. Hierarchical Encoding Structure

 

 

 

3. Experiments

3.1. Experimental setup

l  Mammographic Image Analysis Society (MIAS) dataset

l  89 case samples/1,693 ROIs (72 mass ROIs and 1,621 normal ROIs)

l  Support Vector Machine (SVM) classifier

 

 

 

3.2. Experimental result

 

 

4. Conclusions

l  LBP texture patterns extracted from both core and ribbon regions are effective for classification of mass and normal tissues

l  Incorporating multiresolution analysis is helpful for improving the classification

l  Studies are underway with a larger and more generalized dataset collected from a large number of patients undergoing routine mammography screening

 

설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: F:\c_backup\바탕화면\연구실 관련\홈페이지ResearchField(CAD)\Project\image\demo\project_overview.gif

      Contact Person: Prof. Yong Man Ro (ymro@kaist.ac.kr)

 

설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: 설명: F:\c_backup\바탕화면\연구실 관련\홈페이지ResearchField(CAD)\Project\image\demo\project_overview.gif 

“Multiresolution Local Binary Pattern texture analysis for false positive reduction in computerized detection of breast masses on mammograms,” Jae Young Choi, Dae Hoe Kim, Seon Hyeong Choi, and Yong Man Ro, SPIE Medical Imaging, February 2012, San Diego, California (USA)