SlideShare a Scribd company logo
1 of 12
Ultrasound Image Enhancement Using
Structure-Based Filtering
Ultrasonics in Medicine (BMEG – 6316)
Journal Name: Hindawi Publishing Corporation
Computational and Mathematical Methods in
Medicine
Publishing Date: June 19, 2014
Authors: Shyh-Kuang Ueng, Guan-Zhi Chen &
Cho-Li Yen
December 2022
Center of Biomedical Engineering
Addis Ababa Institute of Technology (AAiT)
Addis Ababa University , Ethiopia
Reviewers:
Sakata Abera , Solomon Assefa &
Obseni Legesse
Paper Review
Course Instructor: Gizeaddis L. (Ph.D.)
Introduction
• Explained as ultrasound images are susceptible to noises
produced by echoes from a homogeneous structures in a
tissue during scanning.
• Interference produces speckle pattern in the ultrasound
image.
• Speckles deteriorate tissue boundary and make tissue
boundaries rough – Loss in information.
• Proposed procedures and technique used to get speckle
free image.
2
Sakata Abera ,Solomon Assefa & Obseni Legesse
Methods
• Proposed procedures and techniques used to get
speckle free image .
• Detailed experimental studies
• Statistical & Mathematical Computation – several
despeckling stages.
• Reduces noises produced by homogeneous tissue boundaries.
• Gives a better noise reduction and preserve edge.
• Developed different techniques to smooth noises and preserve
image features.
3
Sakata Abera ,Solomon Assefa & Obseni Legesse
Methods
• Referred different papers and methodologies to solve the
problem
• Gaussian Filters – Suppress speckle, but blurs edge
• Adaptive Gaussian filters
• Adaptive Median filters – produce unnatural
patterns on image
• They proposed structure-based despeckling method for
ultrasound data.
• Divided despeckle method in to several stages of pixel sizes.
4
Sakata Abera ,Solomon Assefa & Obseni Legesse
Methods
• Used different mathematical and statistical computations.
• They used Eigen system of a Hessian matrix to measure the
strength and orientation of specific image sections.
• Classify the image structures based on their pixel size.
• Feasible filters are adaptively selected to suppress speckle.
• Heterogeneous despeckling strategy - Pixels of different
types are smoothed by using different filters so that
speckles in uniform regions are reduced and tissue
boundaries and edges are preserved.
5
Sakata Abera ,Solomon Assefa & Obseni Legesse
Methods
6
The flowchart of the proposed despeckle method
Sakata Abera ,Solomon Assefa & Obseni Legesse
Result
• The final result employs combination of the
following filters.
• 2D median filter
• 1D Gaussian filter and
• 2D Gaussian filter
• Test results show that the despeckle method used
reduces speckles in uniform areas and enhances
tissue boundaries and spots.
7
Sakata Abera ,Solomon Assefa & Obseni Legesse
Discussion
• Six test images, two ultrasound image and four grey scale
images are filtered.
• The resulted images filtered are compared visually,
computed and corrected with developed mathematical
correction parameters.
• Peak signal-to-noise ratio (PSNR) and structural similarity
index measure (SSIM) values are used to evaluate the
filtered results.
8
Sakata Abera ,Solomon Assefa & Obseni Legesse
Discussion
• The proposed method produces the best PSNR
values in most cases.
• Compared with the other filters, the proposed
method usually produces better SSIM values.
9
Sakata Abera ,Solomon Assefa & Obseni Legesse
Conclusion
• In this paper, they presented procedures of
despeckling ultrasound data.
• Their method is capable of reducing speckles in
homogeneous tissue regions.
• Preserving edges, enhancing region boundaries in
heterogeneous regions and removes multiplicative
noises for grey-level images based on the proposed
statistical mathematical results presented.
10
Sakata Abera ,Solomon Assefa & Obseni Legesse
Gap Analysis
• If all of the tests fail, it cannot identify the structure
type, and thus the pixel is classified as unknown
typed.
• Three passes of the despeckling pipeline are
required to reduce speckles.
• Extra filtering methods are required for some
images with a different noise level.
11
Sakata Abera ,Solomon Assefa & Obseni Legesse
☺
Sakata Abera ,Solomon Assefa & Obseni Legesse
12

More Related Content

Similar to Paper review final.pptx

IRJET- An Efficient Brain Tumor Detection System using Automatic Segmenta...
IRJET-  	  An Efficient Brain Tumor Detection System using Automatic Segmenta...IRJET-  	  An Efficient Brain Tumor Detection System using Automatic Segmenta...
IRJET- An Efficient Brain Tumor Detection System using Automatic Segmenta...IRJET Journal
 
Automatic detection of optic disc and blood vessels from retinal images using...
Automatic detection of optic disc and blood vessels from retinal images using...Automatic detection of optic disc and blood vessels from retinal images using...
Automatic detection of optic disc and blood vessels from retinal images using...eSAT Publishing House
 
Automatic detection of optic disc and blood vessels from retinal images using...
Automatic detection of optic disc and blood vessels from retinal images using...Automatic detection of optic disc and blood vessels from retinal images using...
Automatic detection of optic disc and blood vessels from retinal images using...eSAT Journals
 
Vessels delineation in retinal 
images using COSFIRE filters
Vessels delineation in retinal 
images using COSFIRE filtersVessels delineation in retinal 
images using COSFIRE filters
Vessels delineation in retinal 
images using COSFIRE filtersNicola Strisciuglio
 
Histogram Equalization for Improving Quality of Low-Resolution Ultrasonograph...
Histogram Equalization for Improving Quality of Low-Resolution Ultrasonograph...Histogram Equalization for Improving Quality of Low-Resolution Ultrasonograph...
Histogram Equalization for Improving Quality of Low-Resolution Ultrasonograph...TELKOMNIKA JOURNAL
 
International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)ijceronline
 
IRJET- A Novel Algorithm for Detection of Papilledema in Luminosity and C...
IRJET-  	  A Novel Algorithm for Detection of Papilledema in Luminosity and C...IRJET-  	  A Novel Algorithm for Detection of Papilledema in Luminosity and C...
IRJET- A Novel Algorithm for Detection of Papilledema in Luminosity and C...IRJET Journal
 
A hybrid de-noising method for mammogram images
A hybrid de-noising method for mammogram imagesA hybrid de-noising method for mammogram images
A hybrid de-noising method for mammogram imagesnooriasukmaningtyas
 
Classification_of_heart_sounds_using_fra.pdf
Classification_of_heart_sounds_using_fra.pdfClassification_of_heart_sounds_using_fra.pdf
Classification_of_heart_sounds_using_fra.pdfPoojaSK23
 
Ultrasound image denoising using generative adversarial networks with residua...
Ultrasound image denoising using generative adversarial networks with residua...Ultrasound image denoising using generative adversarial networks with residua...
Ultrasound image denoising using generative adversarial networks with residua...Daniel983829
 
Biometric Ear Recognition System
Biometric Ear Recognition SystemBiometric Ear Recognition System
Biometric Ear Recognition SystemIRJET Journal
 
Feature Extraction Techniques for Ear Biometrics: A Survey
Feature Extraction Techniques for Ear Biometrics: A SurveyFeature Extraction Techniques for Ear Biometrics: A Survey
Feature Extraction Techniques for Ear Biometrics: A SurveyShashank Dhariwal
 
An Efficient Image Denoising Approach for the Recovery of Impulse Noise
An Efficient Image Denoising Approach for the Recovery of Impulse NoiseAn Efficient Image Denoising Approach for the Recovery of Impulse Noise
An Efficient Image Denoising Approach for the Recovery of Impulse NoisejournalBEEI
 
twofold processing for denoising ultrasound medical images
twofold processing for denoising ultrasound medical imagestwofold processing for denoising ultrasound medical images
twofold processing for denoising ultrasound medical imagesanil kumar
 
Hybrid Multilevel Thresholding and Improved Harmony Search Algorithm for Segm...
Hybrid Multilevel Thresholding and Improved Harmony Search Algorithm for Segm...Hybrid Multilevel Thresholding and Improved Harmony Search Algorithm for Segm...
Hybrid Multilevel Thresholding and Improved Harmony Search Algorithm for Segm...IJECEIAES
 

Similar to Paper review final.pptx (20)

IRJET- An Efficient Brain Tumor Detection System using Automatic Segmenta...
IRJET-  	  An Efficient Brain Tumor Detection System using Automatic Segmenta...IRJET-  	  An Efficient Brain Tumor Detection System using Automatic Segmenta...
IRJET- An Efficient Brain Tumor Detection System using Automatic Segmenta...
 
Confer
ConferConfer
Confer
 
Automatic detection of optic disc and blood vessels from retinal images using...
Automatic detection of optic disc and blood vessels from retinal images using...Automatic detection of optic disc and blood vessels from retinal images using...
Automatic detection of optic disc and blood vessels from retinal images using...
 
Automatic detection of optic disc and blood vessels from retinal images using...
Automatic detection of optic disc and blood vessels from retinal images using...Automatic detection of optic disc and blood vessels from retinal images using...
Automatic detection of optic disc and blood vessels from retinal images using...
 
Vessels delineation in retinal 
images using COSFIRE filters
Vessels delineation in retinal 
images using COSFIRE filtersVessels delineation in retinal 
images using COSFIRE filters
Vessels delineation in retinal 
images using COSFIRE filters
 
Dj33662668
Dj33662668Dj33662668
Dj33662668
 
Dj33662668
Dj33662668Dj33662668
Dj33662668
 
Sd oct
Sd octSd oct
Sd oct
 
Histogram Equalization for Improving Quality of Low-Resolution Ultrasonograph...
Histogram Equalization for Improving Quality of Low-Resolution Ultrasonograph...Histogram Equalization for Improving Quality of Low-Resolution Ultrasonograph...
Histogram Equalization for Improving Quality of Low-Resolution Ultrasonograph...
 
International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)
 
IRJET- A Novel Algorithm for Detection of Papilledema in Luminosity and C...
IRJET-  	  A Novel Algorithm for Detection of Papilledema in Luminosity and C...IRJET-  	  A Novel Algorithm for Detection of Papilledema in Luminosity and C...
IRJET- A Novel Algorithm for Detection of Papilledema in Luminosity and C...
 
[IJCT-V3I2P37] Authors: Amritpal Singh, Prithvipal Singh
[IJCT-V3I2P37] Authors: Amritpal Singh, Prithvipal Singh[IJCT-V3I2P37] Authors: Amritpal Singh, Prithvipal Singh
[IJCT-V3I2P37] Authors: Amritpal Singh, Prithvipal Singh
 
A hybrid de-noising method for mammogram images
A hybrid de-noising method for mammogram imagesA hybrid de-noising method for mammogram images
A hybrid de-noising method for mammogram images
 
Classification_of_heart_sounds_using_fra.pdf
Classification_of_heart_sounds_using_fra.pdfClassification_of_heart_sounds_using_fra.pdf
Classification_of_heart_sounds_using_fra.pdf
 
Ultrasound image denoising using generative adversarial networks with residua...
Ultrasound image denoising using generative adversarial networks with residua...Ultrasound image denoising using generative adversarial networks with residua...
Ultrasound image denoising using generative adversarial networks with residua...
 
Biometric Ear Recognition System
Biometric Ear Recognition SystemBiometric Ear Recognition System
Biometric Ear Recognition System
 
Feature Extraction Techniques for Ear Biometrics: A Survey
Feature Extraction Techniques for Ear Biometrics: A SurveyFeature Extraction Techniques for Ear Biometrics: A Survey
Feature Extraction Techniques for Ear Biometrics: A Survey
 
An Efficient Image Denoising Approach for the Recovery of Impulse Noise
An Efficient Image Denoising Approach for the Recovery of Impulse NoiseAn Efficient Image Denoising Approach for the Recovery of Impulse Noise
An Efficient Image Denoising Approach for the Recovery of Impulse Noise
 
twofold processing for denoising ultrasound medical images
twofold processing for denoising ultrasound medical imagestwofold processing for denoising ultrasound medical images
twofold processing for denoising ultrasound medical images
 
Hybrid Multilevel Thresholding and Improved Harmony Search Algorithm for Segm...
Hybrid Multilevel Thresholding and Improved Harmony Search Algorithm for Segm...Hybrid Multilevel Thresholding and Improved Harmony Search Algorithm for Segm...
Hybrid Multilevel Thresholding and Improved Harmony Search Algorithm for Segm...
 

Recently uploaded

Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104misteraugie
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Celine George
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdfQucHHunhnh
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingTechSoup
 
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptxMaritesTamaniVerdade
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfAdmir Softic
 
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17  How to Extend Models Using Mixin ClassesMixin Classes in Odoo 17  How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17 How to Extend Models Using Mixin ClassesCeline George
 
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...Shubhangi Sonawane
 
Class 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdfClass 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdfAyushMahapatra5
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeThiyagu K
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhikauryashika82
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfciinovamais
 
ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.MaryamAhmad92
 
Unit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxUnit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxVishalSingh1417
 
psychiatric nursing HISTORY COLLECTION .docx
psychiatric  nursing HISTORY  COLLECTION  .docxpsychiatric  nursing HISTORY  COLLECTION  .docx
psychiatric nursing HISTORY COLLECTION .docxPoojaSen20
 
Python Notes for mca i year students osmania university.docx
Python Notes for mca i year students osmania university.docxPython Notes for mca i year students osmania university.docx
Python Notes for mca i year students osmania university.docxRamakrishna Reddy Bijjam
 
Micro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdfMicro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdfPoh-Sun Goh
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactPECB
 

Recently uploaded (20)

Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdf
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy Consulting
 
Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024
 
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdf
 
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17  How to Extend Models Using Mixin ClassesMixin Classes in Odoo 17  How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
 
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
 
Class 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdfClass 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdf
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and Mode
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
 
ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.
 
Unit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxUnit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptx
 
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptxINDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
 
psychiatric nursing HISTORY COLLECTION .docx
psychiatric  nursing HISTORY  COLLECTION  .docxpsychiatric  nursing HISTORY  COLLECTION  .docx
psychiatric nursing HISTORY COLLECTION .docx
 
Python Notes for mca i year students osmania university.docx
Python Notes for mca i year students osmania university.docxPython Notes for mca i year students osmania university.docx
Python Notes for mca i year students osmania university.docx
 
Micro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdfMicro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdf
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global Impact
 

Paper review final.pptx

  • 1. Ultrasound Image Enhancement Using Structure-Based Filtering Ultrasonics in Medicine (BMEG – 6316) Journal Name: Hindawi Publishing Corporation Computational and Mathematical Methods in Medicine Publishing Date: June 19, 2014 Authors: Shyh-Kuang Ueng, Guan-Zhi Chen & Cho-Li Yen December 2022 Center of Biomedical Engineering Addis Ababa Institute of Technology (AAiT) Addis Ababa University , Ethiopia Reviewers: Sakata Abera , Solomon Assefa & Obseni Legesse Paper Review Course Instructor: Gizeaddis L. (Ph.D.)
  • 2. Introduction • Explained as ultrasound images are susceptible to noises produced by echoes from a homogeneous structures in a tissue during scanning. • Interference produces speckle pattern in the ultrasound image. • Speckles deteriorate tissue boundary and make tissue boundaries rough – Loss in information. • Proposed procedures and technique used to get speckle free image. 2 Sakata Abera ,Solomon Assefa & Obseni Legesse
  • 3. Methods • Proposed procedures and techniques used to get speckle free image . • Detailed experimental studies • Statistical & Mathematical Computation – several despeckling stages. • Reduces noises produced by homogeneous tissue boundaries. • Gives a better noise reduction and preserve edge. • Developed different techniques to smooth noises and preserve image features. 3 Sakata Abera ,Solomon Assefa & Obseni Legesse
  • 4. Methods • Referred different papers and methodologies to solve the problem • Gaussian Filters – Suppress speckle, but blurs edge • Adaptive Gaussian filters • Adaptive Median filters – produce unnatural patterns on image • They proposed structure-based despeckling method for ultrasound data. • Divided despeckle method in to several stages of pixel sizes. 4 Sakata Abera ,Solomon Assefa & Obseni Legesse
  • 5. Methods • Used different mathematical and statistical computations. • They used Eigen system of a Hessian matrix to measure the strength and orientation of specific image sections. • Classify the image structures based on their pixel size. • Feasible filters are adaptively selected to suppress speckle. • Heterogeneous despeckling strategy - Pixels of different types are smoothed by using different filters so that speckles in uniform regions are reduced and tissue boundaries and edges are preserved. 5 Sakata Abera ,Solomon Assefa & Obseni Legesse
  • 6. Methods 6 The flowchart of the proposed despeckle method Sakata Abera ,Solomon Assefa & Obseni Legesse
  • 7. Result • The final result employs combination of the following filters. • 2D median filter • 1D Gaussian filter and • 2D Gaussian filter • Test results show that the despeckle method used reduces speckles in uniform areas and enhances tissue boundaries and spots. 7 Sakata Abera ,Solomon Assefa & Obseni Legesse
  • 8. Discussion • Six test images, two ultrasound image and four grey scale images are filtered. • The resulted images filtered are compared visually, computed and corrected with developed mathematical correction parameters. • Peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) values are used to evaluate the filtered results. 8 Sakata Abera ,Solomon Assefa & Obseni Legesse
  • 9. Discussion • The proposed method produces the best PSNR values in most cases. • Compared with the other filters, the proposed method usually produces better SSIM values. 9 Sakata Abera ,Solomon Assefa & Obseni Legesse
  • 10. Conclusion • In this paper, they presented procedures of despeckling ultrasound data. • Their method is capable of reducing speckles in homogeneous tissue regions. • Preserving edges, enhancing region boundaries in heterogeneous regions and removes multiplicative noises for grey-level images based on the proposed statistical mathematical results presented. 10 Sakata Abera ,Solomon Assefa & Obseni Legesse
  • 11. Gap Analysis • If all of the tests fail, it cannot identify the structure type, and thus the pixel is classified as unknown typed. • Three passes of the despeckling pipeline are required to reduce speckles. • Extra filtering methods are required for some images with a different noise level. 11 Sakata Abera ,Solomon Assefa & Obseni Legesse
  • 12. ☺ Sakata Abera ,Solomon Assefa & Obseni Legesse 12