After long-term clinical trials, MRI has been proven to be used in humans harmlessly, and it is popularly used in medical diagnosis. Although MR is highly sensitive, it provides abundant organization information. Therefore, how to transform the multi-spectral images which is easier to be used for doctor’s clinical diagnosis. In this thesis, the fuzzy bidirectional edge detection method is used to solve conventional SRG problem of growing order in the initial seed stages. In order to overcome the problems of the different regions, although it is the same Euclidean distance for region growing and merging process stages, we present the peak detection method to improve them. The standard deviation target generation process (SDTGP) is applied to guarantee the regions merging process does not cause over- or undersegmentation. Experimental results reveal that FISRG segments a multispectral MR image much more effectively than FAST and
Currently there are several common detection technologies like digitized X-ray photography (digital radiography, DR), fine needle aspiration cytology (fine needle aspiration cytology, FNAC), ultrasound testing (ultrasonic testing, UT), computed tomography scan (computed tomography, CT), magnetic resonance imaging techniques (magnetic resonance imaging, MRI), and so forth. In 1977, a brand new and has no medical radiation damage detection techniques (magnetic resonance imaging) in response born. MRI (magnetic resonance imaging) is not required under the developer and has been able to show a clearer tissue contrast image, with no ionizing radiation, noninvasiveness, and other characteristics, and is widely used in medical diagnosis and follow-up. Currently the use of MRI in the medical is very broad, such as tumor component analysis, stroke diagnosis, drawing blood, and spinal magnetic resonance diagrams. With advances in technology and medical knowledge accumulated experience, radiology medical research led to clinical diagnosis towards the era of digital technology, the medical image processing and compression techniques, in addition to reducing the burden of health care for pathologic interpretation and also enhancing the clinical diagnosis accuracy and objectivity, so the medical imaging related research not only improves quality of care, but also reflects its overall social value.
Currently, there are five methods adopted for segmentation: cluster-based segmentation, using common classification approaches to separate similar image data into clusters [
Seeded region growing (SRG) is a hybrid-based segmentation algorithm put forward by Adams and Bischof in 1994 [
MRI has coronal, sagittal, and axial sections of three scan directions. In this paper we use the coronal section images, as shown in Figure
Three plane images of a real brain: (a) coronal plane, (b) sagittal plane, and (c) axial plane.
Real brain MR images. (a) Band1, (b) Band2, (c) Band3, (d) Band4, and (e) Band5.
Distribution of three main brain tissues.
We use fuzzy edge detection and fuzzy similarity computation to calculate and select appropriate initial seeds [
Arrangement of the selected pixel and neighboring pixels under mask.
Directional edge can be broadly divided into four (90, 0, 45, 135), as calculated for each pixel is the edge of the extent; if there is no way considered borderline cases, subsequent connections will result in slight misjudgment occurred degree edge. Therefore, we have established eight masks in Figure 90 degrees (forward)
90 degrees (reverse)
0 degrees (forward)
0 degrees (reverse)
45 degrees (forward)
45 degrees (reverse)
135 degrees (forward)
135 degrees (reverse)
Four possible edge directions and their direction mask contrasts.
After defining the edge directions, formula (
If
After calculating all the pixels connected into edges, the edge magnitude
In the first half of Section
The initial seed should meet the requirement that its pixel point and the neighboring pixel points are highly similar [
If the similarity
The similarity of the pixel vectors of all the neighboring seeded regions is calculated with formula (
After the fuzzy similarity computation is completed, it is impossible to determine which of the many seeded regions should be given priority to grow. We therefore extract the smallest similarity value resulting from the calculation using formulas (
According to the spectrum, the histogram
The histogram
Next, we figure out the peak value
The range of
When using conventional SRG, region merging is conducted when the shortest distance (difference) between the pixel mean values of the regions is smaller than a certain threshold value. As a result, the final number of regions segmented is unknown. To prevent excessive merging of regions, we use the standard deviation target generation process [
Supposing the target is to merge the content of the entire image into
The standard deviation
Next, it is supposed that the distribution of factual data is normal and high standard deviation should exist between the pixel information of different tissue regions (GM, WM, and CSF). formula (
After completion of the SDTGP, formula (
GM, WM, and CSF tissues selected with SDTGP from elliptical simulated brain images under different signal-to-noise ratios.
20 dB
15 dB
10 dB
5 dB
GM, WM, and CSF tissues selected with the SDTGP from BrainWeb’s brain images under different signal-to-noise ratios.
20 dB
15 dB
10 dB
5 dB
GM, WM, and CSF tissues selected with the SDTGP from real brain images under different signal-to-noise ratios.
To evaluate the quality of the classification results, we adopt a receiver operating characteristic (ROC) [
FISRG segmentation results of elliptical simulated brain MR images (
|
|
|
|
|
|
| |
---|---|---|---|---|---|---|---|
GM | 9040 | 9040 | 0 | 1 | 0 | 1 | 0 |
WM | 8745 | 8745 | 0 | 1 | 0 | ||
CSF | 3282 | 3282 | 0 | 1 | 0 |
FISRG segmentation results of elliptical simulated brain MR images (
|
|
|
|
|
|
| |
---|---|---|---|---|---|---|---|
GM | 9111 | 8564 | 379 | 0.9400 | 0.0265 | 0.9604 | 0.0322 |
WM | 2968 | 2968 | 0 | 1 | 0 | ||
CSF | 11319 | 10940 | 547 | 0.9665 | 0.0453 |
FISRG segmentation results of brain images from BrainWeb (20 dB).
|
|
|
|
|
|
| |
---|---|---|---|---|---|---|---|
GM | 6552 | 6448 | 280 | 0.9841 | 0.0229 | 0.9796 | 0.0129 |
WM | 2868 | 2708 | 14 | 0.9442 | 0.0087 | ||
CSF | 9367 | 9247 | 90 | 0.9872 | 0.0096 |
FISRG segmentation results of brain images from BrainWeb (5 dB).
|
|
|
|
|
|
| |
---|---|---|---|---|---|---|---|
GM | 6552 | 5448 | 918 | 0.8315 | 0.0750 | 0.8924 | 0.0722 |
WM | 2868 | 2671 | 225 | 0.9313 | 0.0141 | ||
CSF | 9367 | 8646 | 879 | 0.9230 | 0.0933 |
FISRG classification results of elliptical simulated brain MR images (
GM
WM
CSF
FISRG segmentation results of elliptical simulated brain MR images (
GM
WM
CSF
FISRG segmentation results of brain images from BrainWeb (
GM
WM
CSF
FISRG segmentation results of brain images from BrainWeb (
GM
WM
CSF
FISRG classification results of real brain MR images.
GM
WM
CSF
The total detection rates in Tables
Total detection rates of segmentation with FISRG, FAST, and
|
|
|
|
|
---|---|---|---|---|
FISRG | 100% | 100% | 99.96% | 96.04% |
FAST | 100% | 99.99% | 99.98% | 72.48% |
|
100% | 92.90% | 92.02% | 82.86% |
Total detection rates of segmentation with FISRG, FAST, and
|
|
|
|
|
---|---|---|---|---|
FISRG | 97.96% | 97.25% | 95.68% | 89.24% |
FAST | 96.24% | 95.38% | 84.85% | 74.22% |
|
94.44% | 92.17% | 88.60% | 82.47% |
This paper focuses on the application of FISRG to conduct tissue segmentation research on brain MRI. Fuzzy edge detection is used to calculate the magnitude of pixel points connected into edges and apply this information to overcome problems in sequencing in region growing to make the region growing process more stable. When the same difference occurs between a pixel used for growing and a number of neighboring seeded regions during the growing and merging stages, peak detection is added to find out where in a seeded region the number of pixels is larger to establish the new similarity characteristic of the region and the pixel used for growing. During the merging stage, the standard deviation target generation process is adopted to generate the correct information about the quantity of tissues merged (GM, WM, and CSF) to overcome the inability to find out how many regions merged will lead to excessive merging or segmentation when using conventional SRG. The averages of the experimental results are extracted 100 times for analysis. FISRG proves superior to
The authors declare that there is no conflict of interests regarding the publication of this paper.