Bioimaging Systems

Dr. Zeyad Qasim Habeeb

Bioimaging Systems

• Image Processing

• Computer Vision

• Machine Learning

• Medical imaging
modalities
Motivation

Imaging sciences is experiencing a rapid growth

in the world. Some organizations recently ranked
biomedical jobs as the number one fastest
growing career field and listed bio-medical
imaging as the primary reason for the growth.
 This course will mostly focus on analysis of
biomedical images and Bioimaging Modalities,
and imaging part will be briefly taught
Syllabus
 Basics of Radiological Image Modalities and
their clinical use (MRI, PET, CT, fMRI, DTI, …)
Medical Image Registration
Medical Image Segmentation
Medical Image Visualization
Machine Learning in Medical Imaging
Shape Modeling/Analysis of Medical Images
Optional Reading List
 Visual Computing for Medicine: Theory,
Algorithms, and Applications. B. Preim, C. Botha.
Morgan Kaufmann, 2013.
 Medical Image Registration. J. Hajnal, D. Hill, D.
Hawkes (eds). CRC Press, 2001.
Medical Imaging Signals and Systems, by Jerry
Prince & Jonathan Links, Publisher: Prentice Hall
Biomedical Images
 (Bio)medical images are different from other
pictures
 They describe the various physical features measured from the
human body (or animal).

Analysis of biomedical images Focuses on:

 Automatic detection of tumors, characterizing their types
 Measurement of normal/abnormal structures
 Visualization of anatomy, surgery guidance, therapy
planning
 Exploring relationship between clinical, genomic, and
imaging based markers
Medical Image Formats
Dicom
Nifti
Analyze (img/hdr)
Raw data
…
DICOM (the mostly used)
 Digital Imaging and Communications in Medicine
standard
 Since its first publication in 1993, DICOM has
revolutionized the practice of radiology, allowing
the replacement of X-ray film with a fully digital
workflow.
 It is the international standard for medical images
and related information (ISO 12052)
 It is implemented in almost every radiology imaging,
and radiotherapy device (X-ray, CT, MRI, ultrasound,
etc.), and increasingly in devices in other medical
domains such as dentistry.
Medical Imaging
The most direct way to see inside the human (or
animal) body is cut it open (i.e., surgery)
We can see inside the human body in ways that
are less invasive or (completely non-invasive)
We can even see functional activities which are
not visible to naked eye
Medical Image Analysis
Because of the rapid technical advances in
medical imaging technology and the
introduction of new clinical applications,
medical image analysis has become a highly
active research field.
Improvements in image quality, changing
clinical requirements, advances in computer
hardware, and algorithmic progress in medical
image processing all have a direct impact on
the state of the art in medical image analysis.
Medical Image Analysis
Medical images are often multidimensional (2D,
3D, 4D,nD), have a large dynamic range, are
produced on different imaging modalities in the
hospital, and make high demands upon the
software for visualization and human–computer
interaction.
A high resolution MR image of the brain, for
instance, may consist of more than 200 slices of
512 x 512 pixels each, i.e., more than 50 million
voxels in total. (100MB)
Medical Image Analysis-Manual
Often accepted as replacement of the truth (if
biopsy or real ground truth is not available)
However, manual analysis is highly subjective
because it relies on the observer’s perception.
It is highly slow
Medical Image Analysis
Medical Image Analysis-Automated
Different strategies for image analysis exist.
However, few of them are suited for medical
applications
The reason is that both the medical image data
and the model or prototype (i.e., the a priori
description of the features to be analyzed), are
typically quite complex.
Brief Introduction to Imaging Modalities
Bioimaging Modalities
X-ray
Ultrasound
Computed Tomography (CT)
Magnetic Resonance Imaging (MRI)
Positron Emission Tomography (PET)
Diffusion Weighted Imaging (DWI)
Diffusion Tensor Imaging (DTI)
Magnetic Particle Imaging (MPI)
Optical Coherence Tomography (OCT)
Brief Introduction to Imaging Modalities
X-Ray Imaging / Radiography
X-Ray Imaging / Radiography
X-Ray Imaging / Sensitometric Curve
Basics Use of X-Rays
Clinical Examples – X-Rays
How Radiologists Search Abnormal Patterns
in Chest X-Rays?
Ultrasound Imaging
US is defined as any sound wave above 20KHz
In 1794, First to study US physics by deducing
bats used to US to navigate

Ultrasound Imaging
Principle of US Imaging
Features of US Imaging
Clinical Use of US Imaging
Clinical Use of US Imaging
Computed Tomography (CT)

Computed Tomography (CT)

3D Nature of CT

3D Nature of CT

3D Nature of CT

Clinical Use of CT Imaging
Standard imaging technique in many organs,
particularly gold standard for lung imaging
Fast
Radiation exposure
Often used in surgery rooms
Show anatomy

Magnetic Resonance Imaging (MRI)

MRI Basics

MRI Basics
Repetition Time (TR) is the amount of time
between successive pulse sequences applied to
the same slice.
Time to Echo (TE) is the time between the
delivery of the RF pulse and the receipt of the
echo signal.
Types of MRI

Safety in MRI

Diffusion Tensor Imaging (DTI)
Diffusion tensor imaging (DTI) is a magnetic
resonance imaging technique that enables the
measurement of the restricted diffusion of water
in tissue
MRI (sub-)modality
useful for tumor characterization (densely
cellular tissues exhibit lower diffusion).
Diffusion Tensor Imaging (DTI)
Diffusion Weighted Imaging (DWI)
Diffusion Weighted Imaging (DWI)
 It is a form of MR imaging.
 DWI is the use of specific MRI sequences as well as
software that generates images from the resulting
data that uses the diffusion of water molecules to
generate contrast in MR images
 A special kind of DWI, diffusion tensor imaging (DTI),
has been used extensively to map (white matter
tractography) in the brain.
 White matter refers to areas of the central nervous
system (CNS)
 tractography is a 3D modeling technique used to
visually represent nerve tracts using data collected
by diffusion MRI
DTI and DWI
Diffusion-weighted and diffusion tensor imaging
(DWI/DTI) has revolutionized clinical
neuroimaging.
Pathology may be detected earlier and with
greater specificity than with conventional
magnetic resonance imaging sequences.
In addition, DWI/DTI allows exploring the
microarchitecture of the brain.
Functional MRI (fMRI)
measures brain activity through oxygen
concentration in the blood flow.
when area of the brain is active (in use), blood
flow to that area also increases
which part/location of the brain is activated
when reading?
which part/location of the brain is activated
when listening music?
which part/location of the brain is activated
when searching puzzle?
Functional MRI (fMRI)
Nuclear Medicine Imaging – PET/SPECT
PET: Positron Emission Tomography
SPECT: Single Photon Emission Tomography
Basics of PET Imaging
Basics of PET Imaging
Basics of PET Imaging
Late 1950s, David L. concept of emission and
transmission molecular activity is measured.
PTE uses short-lived positron emitting isotopes
PTE is a technique that detects pairs of gamma
rays emitted indirectly by a positron-emitting
resulting image show the distribution of isotopes
PET/CT and MRI/PET (Hybrid Imaging)
What to Measure in PET?
Metabolic lesion/tumor volume (MTV)
Shape information of lesion
Texture information of lesion (heterogeneous vs
homogeneous)
Number and distribution of the lesions (focal,
multi-focal)
Serial and Simultaneous MRI/PET
Comparison of Imaging Methods

Chest Abdomen Head/Neck Cardiovascular Skeletal

Need
gold contrast for Good for Gold Gold
CT
standard excellency, trauma standard standard
widely used

no use Problems
US except heart Poor Poor Elastography
with gas

Extensive
Perfusion(the
use in heart CT or MRI is
Nuclear PET passage of bone marrow
and therapy merged
blood)
in lung

Will replace
growing Increased Gold
MRI CT in near Excellent
role of MRI standard
future
Thanks