biomedical image processing analysis ppt
- 1. Advanced biomedical image analysis (BME-6231) Selamawit Workalemahu FECE Introduction
- 2. Selamawit Workalemahu Introduction What is an image? • Simple definition :- a visual representation of something • A signal = function (variable/variables with physical meaning) one-dimensional (e.g. dependent on time) two-dimensional (e.g. dependent on two co-ordinates in a plane) three-dimensional (e.g. describing an object in space) higher-dimensional. • In general an image is a signal and as with all signals they are functions of physical things.
- 3. Selamawit Workalemahu Introduction • Image function value = brightness at image points • Brightness dependent on several factors object surface reflectance properties • surface material, microstructure and marking Illumination properties • provide their own light as in glow in the dark stickers object surface orientation with respect to a viewer and light source temperature, distance from the observer
- 4. Selamawit Workalemahu Types of images Analog image • Is a continuous image • Is described by the spatial distribution of brightness or gray levels that reflect a distribution of detected energy • The image can be displayed using a medium such as paper or film
- 5. Selamawit Workalemahu Types of images Analog image • Black and white images require only one gray level or intensity variable while color images require multiple variables like three basic colors, RGB • When combined together, the RGB intensities can produce a selected color at a spatial location of the image
- 6. Selamawit Workalemahu Types of images Digital images • A digital image is discrete in both spatial and intensity (gray level) domains • A discrete spatial location or finite size with a discrete gray level values is called a pixel E.g. an image of 1024 x1024 pixels (discreate locations) may be displayed in an 8-bit gray level resolution. This means that each pixel in the image may have any value from 0 to 255 (discrete in terms of intensity values) • The pixel dimensions would depend on the spatial sampling
- 7. Selamawit Workalemahu Major medical image Modalities • Projection X-ray (Radiography) • X-ray Computed Tomography (CT) • Nuclear Medicine (SPECT, PET) • Ultrasound • Magnetic Resonance Imaging • Optical Imaging (Endoscopy)
- 8. Selamawit Workalemahu Anatomical vs Functional Imaging Anatomical imaging • Modalities that show how the human anatomy / structure looks like • Eg. X-ray, CT, MRI
- 9. Selamawit Workalemahu Anatomical vs Functional Imaging Functional imaging • Imaging techniques that show how the human body system works/ functions • Eg. SPECT, PET, fMRI, CT with contrast
- 10. Selamawit Workalemahu Need for image processing • The images produced by equipment's are composed of pixels, to which discrete brightness and color values are assigned Through image processing they can be efficiently processed, evaluated and analyzed and through compression, stored and made available to many places at the same time through appropriate communication networks • It is possible for doctors to see the interior portions of the human body, with extreme clarity, ease and detail thus facilitating easy detection and diagnosis of various diseases
- 11. Selamawit Workalemahu Need for image processing • It helps to improve images for human interpretation. • Information can be processed and extracted from images for machine interpretation.
- 12. Selamawit Workalemahu Components of image processing • Image processing covers signal gathering, image forming, picture processing, and image display to medical diagnosis based on features extracted from images • Image processing covers four main areas: – Image formation – Visualization – Analysis of image – Management of the acquired information
- 13. Selamawit Workalemahu Components of image processing
- 14. Selamawit Workalemahu Image processing • Image enhancement
- 15. Selamawit Workalemahu Image processing (cont’d) Image Restoration( e.g., correcting out-focus images) • Image Restoration is the operation of taking a corrupt/noisy image and estimating the clean, original image. • Corruption may come in many forms such as motion blur, noise and camera misfocus
- 16. Selamawit Workalemahu Image processing (cont’d) • Image Compression
- 17. Selamawit Workalemahu Computer vision • Computer vision (CV) is the subcategory of artificial intelligence (AI) that focuses on building and using digital systems to process, analyze and interpret visual data. • The goal of computer vision is to enable computing devices to correctly identify an object or person in a digital image and take appropriate action.
- 19. Selamawit Workalemahu Computer vision vs. image processing Computer vision Digital image processing • Input and output are images • Changes the input properties • Doesn’t interpret an image • Often the first step of an application • Input can be an image or a video. The output can be a label or a bounding box • Usually it doesn’t changes the input’s properties • Extract useful information from the input • Used after image processing step
- 20. Selamawit Workalemahu Applications of computer vision Robotic vision • Application of computer vision in robotics. a sophisticated technology that helps a robot, usually an automated robot, better identify things, navigate, find objects, inspect, and handle parts or bits before an application is performed • Some important applications include : Autonomous robot navigation Video demo showing robotic vacuum cleaner Inspection and assembly
- 21. Selamawit Workalemahu Applications of Image processing
- 23. Selamawit Workalemahu Autonomous vehicles Land, underwater, space
- 24. Selamawit Workalemahu Traffic monitoring Video demo, showing computer vision used in traffic monitoring
- 26. Selamawit Workalemahu Facial expression recognition
- 27. Selamawit Workalemahu Hand gesture recognition
- 28. Selamawit Workalemahu Human activity recognition
- 29. Selamawit Workalemahu Why is medical image analysis Special? • Because of the patient • Computer Vision: Good at detecting irregulars, e.g. on the factory floor But no two patients are alike—everyone is “irregular” • Medicine is war Radiology is primarily for investigation/inspection Surgeons are the marines Life/death decisions made on insufficient information Success measured by patient recovery
- 30. Selamawit Workalemahu Medical applications Skin cancer detection Diagnosis of breast cancer
- 31. Selamawit Workalemahu Segmentation • Labeling every voxel • Discrete vs. fuzzy • How good are such labels? Gray matter (circuits) vs. white matter (cables). Tremendous oversimplification • Requires a model
- 32. Selamawit Workalemahu Registration • Image to Image same vs. different imaging modality same vs. different patient topological variation • Image to Model deformable models • Model to Model matching graphs
- 33. Selamawit Workalemahu Course objectives This course will focus on developing deep knowledge of Biomedical image analysis in image processing operators, image feature extraction and application • Understand the digital image fundamentals and transforms to enhance the biomedical images • Understand and develop algorithms for medical image processing and analysis