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

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

Development of Mammography Computer Aided Diagnosis (CAD)

-      Image enhancement

 

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

 

1. Introduction

l  Recent clinical studies have shown that computer-aided detection (CAD) systems could play an important role in increasing the breast cancer detection rate in mammography.

l  The detection of breast masses on mammograms (especially, in case of dense breast tissue) is far from being mature stage as masses generally have similar intensity with their surroundings.

l  Mass detection in dense mammograms is critical because several studies have shown that tissue types are related with breast cancer risks.

l  We propose a novel mammogram enhancement for improving mass detection accuracy. The proposed enhancement method based on two observations on masses.

l  Masses are hyper-dense or uniform density with respect to their background.

l  The core parts of masses have high intensity while intensities are decreased as the distance to core parts is increased.

 

2. Image enhancement

2.1. Purpose

l  Enhancing regions which have aforementioned both mass characteristics simultaneously.

 

2.2. Method

Fig. 1. Block diagram of the proposed enhancement method

 

l  Enhancing aforementioned mass characteristics separately, then combining as follows:

l  ISTAT, ISBF : Filter responses of the statistics based enhancement and the sliding band filtering, whose values are normalized to [0, 1].

l  α1, α2 : Weights of each filter response.

l  : Pixel-wise multiplication operator.

l  Statistics based enhancement

n  Enhancing bright and smooth regions and suppressing backgrounds.

l  Sliding band filtering

n  Enhancing the regions where their surrounding gradients are converging regardless of the contrast of the regions.

 

3. Experiments

3.1. Experimental setup

l  89 mammograms collected from mini-MIAS DB were used.

l  Contour-based detection algorithm was adopted for the detection.

l  The correct detection was recorded for a segmented region when the region included the centroid of a mass.

 

3.2. Effectiveness of the proposed enhancement

l  The proposed enhancement increased the overall mass detection accuracy. In particular, the detection accuracy is significantly increased in dense parenchyme.

 

Table 1. Mass detection sensitivity of all abnormalities

Mass detection method

Mass detection sensitivity

Contour-based detection

without the proposed enhancement

78.3%

Contour-based detection

with the proposed enhancement

92.4%

 

 

 

Fig. 2. Mass detection accuracy, with respect to the three different types of breast tissue (up)

and to the five different types of abnormality (down)

 

 

Fig. 3. Examples of the original mammograms and mammograms enhanced

by the proposed method (breast tissues of both mammograms are dense-glandular)

 

4. Conclusions

l  The proposed enhancement is designed for increasing contrast between mass and backgrounds.

l  The results demonstrate that the proposed enhancement can significantly improves the detection accuracy of the mass detection, especially detection accuracy of masses in dense mammogram.

 

 

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

“Mammographic enhancement with combining local statistical measures and sliding band filter for improved mass segmentation in mammograms,” Dae Hoe Kim, Jae Young Choi, Seon Hyeong Choi, and Yong Man Ro, SPIE Medical Imaging, February 2012, San Diego, California (USA)