Upload
oceana
View
25
Download
0
Embed Size (px)
DESCRIPTION
Density Correction of Peripheral Breast Tissue on Digital mammograms. Ulrich Bick, MD Maryellen L. Giger PhD Robert A. Schmidt, MD Robert M. Nishikawa, PhD Kunio Doi , PhD. 報告者 :劉治元. Outline. ABSTRACT INTRODUCTION DESCRIPTION OF THE ENHANCEMENT ALGORITHM EVALUATION OF THE ALGORITHM - PowerPoint PPT Presentation
Citation preview
Ulrich Bick, MDMaryellen L. Giger PhDRobert A. Schmidt, MD
Robert M. Nishikawa, PhDKunio Doi, PhD
Density Correction of Peripheral Breast Tissue on Digital mammograms
1
報告者:劉治元
ABSTRACTINTRODUCTIONDESCRIPTION OF THE
ENHANCEMENT ALGORITHMEVALUATION OF THE ALGORITHMADVANTAGES AND LIMITATIONS OF
USING THE ALGORITHMCONCLUSIONS
Outline
2
When digital mammograms are viewed on video displays, evaluation of the skin and subcutaneous tissue is often difficult and may require special window settings.
An algorithm has been developed for selective enhancement (ie, density correction) of the dark peripheral portions of the breast on mammograms.
Abstract
3
After enhancement, skin and breast parenchyma can be evaluated simultaneously without the need for different window settings.
When tested on a set of 400 digitized mammograms, the density correction algorithm significantly (P < .0001) increased the maximum area of breast tissue visualized simultaneously at window width settings of 0.5-2.0 △OD (optical density).
Abstract
4
The algorithm for correcting the density of peripheral breast tissue substantially facilitates and improves the display of digital mammograms and thus will be a valuable component of an integrated workstation for computer-aided diagnosis in mammography.
Abstract
5
Evaluation of the skin and subcutaneous tissue on mammograms is often difficult because of the high optical density (OD) of these areas.
visualization of these peripheral areas on soft-copy displays requires wide window settings, which result in loss of contrast in the center portion of the breast.
Special anatomic filters have been designed for x-ray beam equalization in mammography , but they may cause artifacts and have not been accepted in routine clinical practice because of difficulties in handling.
INTRODUCTION
6
Another approach is the use of scanning equalization mammography, which is performed with a modulated, segmented fan beam.
Although this technique may correct large differences in regional density in the center part of the breast, it usually cannot uniformly correct the rapid density slope along the semicircular periphery of the breast because of the rectangular design of the fan beam segments.
INTRODUCTION
7
we are developing an automated post-processing algorithm for digital mammograms that selectively enhances the dark peripheral portions of the breast to match the density of the center part of the breast.
INTRODUCTION
8
After an automated segmentation of the digital mammogram and identification of the skin line
DESCRIPTION OF THE ENHANCEMENT ALGORITHM
9
the distance from the skin is calculated for each pixel inside the breast by using a so-called Euclidean distance map .
This map codes the distance from the skin for each image point in the form of a gray value .
DESCRIPTION OF THE ENHANCEMENT ALGORITHM
10
DESCRIPTION OF THE ENHANCEMENT ALGORITHM
11
a fitted enhancement curve is created; this curve defines the necessary correction value for each breast pixel as a function of the distance from the skin.
DESCRIPTION OF THE ENHANCEMENT ALGORITHM
12
After application of the enhancement algorithm, skin, subcutaneous tissue, and breast parenchyma have similar average density values and can be evaluated simultaneously without the need for different window settings .
DESCRIPTION OF THE ENHANCEMENT ALGORITHM
13
The calculation time for the algorithm depends on the size of the breast and ranges between 30 and 50 seconds for a full-size 2,048 x 2,560 image (when performed on a Power station 590 [RISC 6000 series; IBM, Austin, Tex]).
More than 50% of this time is spent to create the Euclidean distance map, whereas image segmentation takes only about 2 seconds.
DESCRIPTION OF THE ENHANCEMENT ALGORITHM
14
MethodsThe algorithm for correcting peripheral density
was tested on the four-view screening mammographic studies of 100 consecutive patients in whom non-palpable breast cancer was diagnosed at the University of Chicago between 1987 and 1993.
The 400 mammograms were digitized with a laser scanner (Lumiscan 100; Lumisys, Sunnyvale, Calif) at 100 μm with a 10-bit gray scale and a dynamic range of 0-3.5 OD.
EVALUATION OF THE ALGORITHM
15
For evaluation, the original and density-corrected images were displayed back-to-back on a computer monitor.
Density correction results were subjectively rated by four expert mammographers (R.A.S., R.C. Haldemann, C.J. Vyborny, D.E. Wolverton) into the following five categories.
EVALUATION OF THE ALGORITHM
16
five categories:(a) optimal results, with uniform density along the
complete periphery of the breast(b) minor density irregularities, with smooth areas
of slightly higher or lower density(c) somewhat distracting density irregularities, but
with no interference with interpretation;(d) severe density deviations or artifacts that might
interfere with interpretation(e) complete failure of the density correction
algorithm.
EVALUATION OF THE ALGORITHM
17
As a quantitative measurement, the maximum fractions of the breast area visualized simultaneously at window width settings of 0.5, 1 .0, 1 .5, and 2.0 △OD (difference in ODs between upper and lower window limits) were calculated for both the original and density-corrected images.
These OD ranges correspond to 146, 293, 438, and 585 gray levels, respectively, in the digitized image (10-bit linear digitization from 0 to 3.5 OD).
EVALUATION OF THE ALGORITHM
18
For statistical analysis of the differences between the original and density-corrected images, the Wilcoxon signed-ranks test for matched pairs was used.
As a measure of the above-chance inter-observer agreement, the weighted k for ordered categorical data was calculated for each pair of observers .
EVALUATION OF THE ALGORITHM
19
Results
EVALUATION OF THE ALGORITHM
20
EVALUATION OF THE ALGORITHM
21
In 82% of cases with a discordant rating between two observers, the disagreement was between categories 1 and 2.
This may reflect the difficulties of the observers in consistently distinguishing between cases with minor irregularities (category 2) and cases with optimal results (category 1).
EVALUATION OF THE ALGORITHM
22
EVALUATION OF THE ALGORITHM
23
Improved Digital DisplayOne of the main limitations of current video
monitors for viewing radiographs and especially mammograms is the small dynamic range compared with that available when radiographic film is viewed on a conventional light box .
When the described density correction algorithm is used, a larger portion of the breast can be displayed at a narrow (high-contrast) window setting , thus compensating for the smaller dynamic range of the digital display.
ADVANTAGES AND LIMITATIONS OFUSING THE ALGORITHM
24
ADVANTAGES AND LIMITATIONS OFUSING THE ALGORITHM
25
Aid to Computer-assisted DetectionIn addition to improving the display of digital
mammograms, the density correction algorithm is used as part of a new single-image method for computer-assisted detection of mass lesions on mammograms .
Several of the feature extraction steps used in characterization of masses seen on mammograms are also gradient based and will benefit from use of a density-corrected image as input.
ADVANTAGES AND LIMITATIONS OFUSING THE ALGORITHM
26
Limitationsthe curve may not be optimally suited for the
entire circumfcrcnce of the breast.The density correction algorithm crucially
depends on the quality of the digitization process.
ADVANTAGES AND LIMITATIONS OFUSING THE ALGORITHM
27
ADVANTAGES AND LIMITATIONS OFUSING THE ALGORITHM
28
ADVANTAGES AND LIMITATIONS OFUSING THE ALGORITHM
29
The developed algorithm for correcting the density of peripheral breast tissue substantially facilitates and improves the display of digital mammograms.
On density-corrected mammograms, the skin, subcutaneous tissue, and breast parenchyma can be evaluated simultaneously at high contrast with use of the same window setting.
This algorithm will thus be a valuable component of an integrated workstation for computer-aided diagnosis in mammography.
CONCLUSIONS
30
Thank you~
31