Tài liệu Cơ sở dữ liệu hình ảnh P4 pptx

As shown in Table 4.1,except for digital electronic microscopy DEM and digital color microscopyDCM, which are pathological and histological images of microscopic tissues,all the modaliti

Image Databases: Search and Retrieval of Digital Imagery

Edited by Vittorio Castelli, Lawrence D Bergman Copyright  2002 John Wiley & Sons, Inc ISBNs: 0-471-32116-8 (Hardback); 0-471-22463-4 (Electronic)

STEPHEN WONG and KENT SOO HOO, JR

University of California at San Francisco, San Francisco, California

Medical imaging has its roots in the accidental discovery of a new class ofelectromagnetic radiation, X rays, by Wilhelm Conrad Roentgen in 1895 Thefirst X-ray radiograph ever taken was of his wife’s hand, revealing a picture

of the living skeleton [1] In the subsequent decades, physicians refined the art

of X-ray radiography to image the structural and physiological state of internalorgans such as the stomach, intestines, lungs, heart, and brain

Unlike the gradual evolution of X-ray radiography, the convergence ofimaging physics and computers has spawned a revolution in medical imagingpractice over the past two decades This revolution has produced a multitude ofnew digital imaging modalities: film scanners, diagnostic ultrasound, computedtomography (CT), magnetic resonance imaging (MRI), digital subtractionangiography (DSA), single-photon-emission computed tomography (SPECT),positron-emission tomography (PET), and magnetic source imaging (MSI) toname just a few [2,3] Most of these modalities are routinely being used

in clinical applications, and they allow in vivo evaluation of physiology andanatomy in ways that conventional X-ray radiography could never achieve.Digital imaging has revolutionized the means to acquire patient images, providesflexible means to view anatomic cross sections and physiological states, andfrequently reduces patient radiation dose and examination trauma The other 70percent of radiological examinations are done using conventional X rays anddigital luminescent radiography These analog images can be converted intodigital format for processing by using film digitizers, such as laser scanners,solid-state cameras, drum scanners, and video cameras

Medical images are digitally represented in a multitude of formats depending

on the modality, anatomy, and scanning technique The most outstanding feature

of medical images is that they are almost always displayed in gray scalerather than color, with the exception of Doppler ultrasound and pseudocolornuclear medicine images A two-dimensional (2D) medical image has a size of

83

Table 4.1 Dimensions and sizes of biomedical images

Dimension (Bits) Size/Exam.

Digital electronic microscopy (DEM) 512 × 512 8 varies

Digital color microscopy (DCM) 512 × 512 24 varies

Cardiac catheterization 512 × 512 or 8 500 – 1000 MB

1024 × 1024

Computed radiography 2048 × 2048 12 8 – 32 MB Digitized mammogram 4096 × 4096 12 64 MB (a pair)

M× N × k bits, where M is the height in pixels and N is the width, and wherethere are 2kgray levels Table 4.1 lists the average number of megabytes (MB) perexamination generated by medical imaging technologies, where a 12-bit image isrepresented by 2 bytes in memory The size of an image and the number of imagestaken in one patient examination varies with the modality As shown in Table 4.1,except for digital electronic microscopy (DEM) and digital color microscopy(DCM), which are pathological and histological images of microscopic tissues,all the modalities are classified as radiological images (that broadly includeimages for use in other medical disciplines such as cardiology and neurology) andused for diagnosis, treatment, and surgery-planning purposes Each radiologicalexamination follows a well-defined procedure One examination (about 40 imageslices) of X-ray CT with uniform image slice size of 512× 512 × 12 bits isaround 20 MB, whereas one digital mammography image usually generates

32 MB of data

Digital imaging modalities produce huge amounts of image data that requirethe creation of new systems for visualization, manipulation, archiving, andtransmission The traditional method of handling images using paper and filmscannot possibly satisfy the needs of the modern, digitally enabled radiologicalpractice Picture archiving and communication systems (PACS) have beendeveloped in the past decade to handle the large volume of digital imagedata generated in radiology departments, and proponents envision an all-digital, filmless radiology department in the near future Today’s managed careenvironment further demands the reduction of medical costs, and computersystems can help to streamline the process of handling all patient data, includingimages Telemedicine enables physicians to consult with regional expert centers

APPLICATIONS 85

using wide area networks and telephones, improving the quality of care and alsoeliminating the cost of maintaining such expertise on-site at smaller clinics orrural hospitals In addition, there is great interest in integrating all the healthcare information systems into one computerized patient record (CPR) in order toreduce costs and to provide full access to longitudinal patient data and historyfor care providers

The most prevalent clinical application of medical image database systems(MIDS) is acquiring, storing, and displaying digital images so that radiologistscan perform primary diagnosis These systems are responsible for managingimages from the acquisition modalities to the display workstations Advancedcommunication systems are enabling doctors to exchange voice, image, andtextual data in real time, over long distances in the application known as

teleconsultation Finally, researchers are utilizing MIDS in constructing brain

atlases for discovering how the brain is organized and how it functions

4.2.1 Display Workstations

Clinicians interact with MIDS through display workstations Clinicians interpretimages and relevant data using these workstations, and the results of their analysisbecome the diagnostic report, which is permanently archived in hospital andradiology information systems (HIS and RIS) Generally, the clinician entersthe patient name or hospital identification into the display station’s query field

to survey which image studies are available The clinician selects only thoseimages that need to be transferred from the central storage archive to the displayworkstation for the task at hand

The six basic types of display workstations support six separate clinical cations: diagnosis, review, analysis, digitization and printing, interactive teaching,

appli-and desktop applications Radiologists make primary diagnoses using diagnostic

workstations These workstations are constructed using the best hardware

avail-able and may include multiple high-resolution monitors (having a significantly

higher dynamic range than typical displays and a matrix of 2,000 × 2,000 or 2,500 × 2,000 pixels) for displaying projection radiographs Redundant arrays

of inexpensive disks (RAID) are used for local storage to enable rapid retrieval

of images with response time on the order of 1 to 2 seconds In addition to theprimary diagnosis, radiologists and referring physicians often review cases in the

hospital wards using a review workstation Review workstations may not require

high-resolution monitors, because the clinician is not generating a primary nosis and the referring physicians will not be looking for every minute detail

diag-Analysis workstations differ from diagnostic and review workstations in that

they are used to extract useful parameters from images An example of a usefulparameter might be the volume of a brain tumor: a clinician would then perform

a region of interest (ROI) analysis by outlining the tumor on the images, and the

workstation would calculate its volume Clinicians obtain hard copies (printouts)

of digital medical images at digitizing and printing workstations, which consist

of a paper printer for pictorial report generation When a patient is examined atother hospitals, the workstation’s laser film scanner allows the radiology depart-ment technician to digitize hard copy films from outside the department and store

the digitized copy into the local image archival system An interactive teaching

workstation is used to train radiologists in the art of interpreting medical images;

a software program leads the student through a series of images and choice questions that are intended to teach him/her how to recognize variouspathologies Finally, physicians or researchers need to generate lecture slides forteaching and research materials from images and related data in the MIDS The

multiple-desktop workstation uses everyday computer equipment to satisfy requirements

that are outside the scope of daily clinical operations

As examples, a pair of multimedia physician workstation prototypes developed

at University of California, San Francisco (UCSF) is described using an oriented multimedia graphical user interface (GUI) builder Age assessment ofpediatric bone images and Presurgical planning in epilepsy are the two supportedapplications

object-In the first application, a pediatrician assesses bone age and compares it withthe chronological age of the patient based on a radiological examination of theskeletal development of a left-hand wrist A discrepancy indicates abnormalities

in skeletal development Query of the database for pediatric hand bone imagescan be by image content, for example, by radius bone age or ratio of epiphysealand metaphyseal diameters; by patient attributes, for example, by name, age,and exam date; or by a combination of these features Programs for extractingfeatures of hand bone images were discussed in Refs [4,5] The sliders in the

“Query-by-Image Attributes” window can be used to specify the range of theimage attributes for data retrieval The Image Database System (IDBS) returnswith a list of five patients and representative thumbnail images satisfying thecombined image- and patient-attribute constraints The user can click on anythumbnail image to retrieve, visualize, and analyze the original digitized handradiographs (Fig 4.1)

The second application, assisting the presurgical evaluation of complex partialseizure is illustrated in Figure 4.2 Here, the user specifies the structural, func-tional, and textual attributes of the MRI studies of interest The IDBS returns alist of patients satisfying the query constraints and a set of representative images

in thumbnail form The user then clicks on one of the thumbnail images to zoom

to full size or to retrieve the complete three-dimensional (3D) MRI data setfor further study After studying the retrieved images, the user can update thedatabase with new pictures of interest, regions of interest, image attributes, ortextual reports

4.2.2 An Application Scenario: Teleconsultation

Consolidation of health care resources and streamlining of services has motivatedthe development of communication technologies to support the remote diagnosis,

APPLICATIONS 87

Figure 4.1 Content-based retrieval of MRI images based on ranges, structural volume,

and functional glucose count of the amygdala and hippocampus A color version of this

figure can be downloaded from ftp://wiley.com/public/sci tech med/image databases.

Figure 4.2 Content-based retrieval for hand-bone imaging based on hand-bone age and

epiphyseal and metaphyseal diameter ratio A color version of this figure can be

down-loaded from ftp://wiley.com/public/sci tech med/image databases.

consultation, and management of patient cases For the referring physician toaccess the specialist located in an expert medical center, the specialist musthave access to the relevant patient data and images Telemedicine is simply thedelivery of health care using telecommunications and computer technologies.Teleradiology adds radiological images to the information exchange In the past,textual and image information was exchanged on computer networks and theconsultation between doctors was carried out over conventional phone lines.Teleconsultation enables the real time interaction between two physicians andimproves the mutual understanding of the case Both physicians see the exactimage on their computer monitors, and each of them can see the mouse pointer

of the other When one physician outlines an area of interest or changes a window

or level setting, the other physician’s computer monitor is automatically updatedwith the new settings

A neuroradiological teleconsultation system has been implemented betweenthe UCSF main hospital and Mt Zion hospital for emergency consultationsand cooperative readouts [6] Images are transferred from the referring site(Mt Zion) to the expert center at UCSF over local area network using digitalimaging and communications in medicine (DICOM) protocols and transmissioncontrol protocol/Internet protocol (TCP/IP) During the consultation, information

is exchanged over both TCP (stream) and UDP (datagram) channels for remotecontrol and display synchronization Conversation is over regular telephone lines

4.2.3 Image Archives for the Research Community: Brain Atlases

In addition to being used for diagnostic purposes, imagery finds an importantapplication as reference for clinical, research, and instructional purposes Brainatlases provide a useful case in point In this section, the construction of brainatlases [7] and their use is described briefly

Historically, brain maps have relied almost exclusively on a single ysis technique, such as analysis at the cellular level [8], 3D tomography [9],anatomic analysis [10], PET [11], functional MRI [12], and electrophysiology[13] Although each of these brain maps is individually useful for studying limitedaspects of brain structure and function, they provide far more information whenthey are combined into a common reference model such as a brain atlas.The problem of combining data from different sources (both from differentpatients and from different modalities) into a single representation is a commonone throughout medical imagery and is central to the problem of brain atlasconstruction Brain atlases typically employ a common reference system, called

anal-stereotaxic space, onto which individual brains are mapped The deformable

atlas approach assumes that there exists a prototypical template of human brainanatomy and that individual patient brains can be mapped onto this template

by continuous deformation transformations Such mappings include piecewiseaffine transformations [14], elastic deformations [15], and fluid-based warpingtransforms [16,17] In addition to geometric information, the atlas can also containanatomic models to ensure the biological validity of the results of the mappingprocess [18]

CHALLENGES 89

As an alternative to a single deformable model, the probabilistic approachemploys a statistical confidence limit, retaining quantitative information on inter-subject variations in brain architecture [19] Since no “ideal” brain faithfullyrepresents all brains [19,20], probabilistic models can be used to capture vari-ations in shape, size, age, gender, and disease state A number of differenttechniques for creating probabilistic atlases have been investigated [21–24].Brain atlases have been used in a number of applications including automaticsegmentation of anatomy to measure and study specific regions or structures [25],[26,27]; statistical investigation of the structural differences between the atlas and

a subject brain to detect abnormal pathologies [28]; and automatic labeling ofneuroanatomic structures [28]

An MIDS stores medical image data and associated textual information for thepurpose of supporting decision making in a health care environment The imagedata is multimodal, heterogeneous, and changing over time Patients may havedifferent parts of the body imaged by using any number of the available imagingmodalities, and disease progression is tracked by repeating the imaging exams

at regular timely intervals A well-designed imaging database can outperformthe capabilities of traditional film library storage and compensate for limita-tions in human memory A powerful query language coupled with an easy-to-usegraphic user interface can open up new vistas to improve patient care, biomedicalresearch, and education

Textual medical databases have attained a high degree of technical tion and real-world usage owing to the considerable effort expended in applyingtraditional relational database technology in the health field However, the inclu-sion of medical images with other patient data in a multimodal, heterogeneousimaging database raises many new challenges, owing to fundamental differencesbetween the information acquired and represented in images and that in text Thefollowing have been identified as key issues [29,30]:

sophistica-1 Large Data Sets. The sheer size of individual data sets differentiatesimaging records from textual records, posing new problems in informa-tion management Images acquired in one examination can range from one

or two megabytes in nuclear medicine modalities to around 32 megabyteseach in mammograms and digital radiographs A major hospital typicallygenerates around one terabyte of digital imaging data per year [31] Because

of the large volumes, traditional methods employed in textual databases areinadequate for managing digital imagery Advanced algorithms are required

to process and manage multimodal images and their associated textualinformation

2 Multimodality Medical imaging modalities are differentiated by the type

of biomedical information, for example, anatomic, biochemical, ical, geometric, and spatial, that they can reveal of the body organ under

physiolog-study in vivo, for example, brain, heart, chest, and liver Modalities areselected for diagnosis depending on the type of disease, and it is the job

of the radiologist to synthesize the resulting image information to make

a decision Features and information contained in multimodal images arediverse and interrelated in complex ways that make interpretation and corre-lation difficult For example, Figure 4.3 shows both a CT scan and an MRIscan of the torso, and despite imaging the same part of the body, the twoimages look very different CT is especially sensitive to hard tissue such

as bone, but it presents soft tissue with less contrast On the other hand,MRI renders soft tissue with very high contrast but does not image bone aswell as CT Scans of PET and CT look entirely different from one anotherand are also distinct from other modalities, such as computed radiography(CR) and ultrasound PET acquires images of different body parts fromthose of mammographic images (Fig 4.4) Even within the same modalityand for the same anatomy, two sets of medical images can vary greatly inslice thickness, data set orientation, scanning range, and data representation.Geometric considerations, such as location and volume, are as important

as organ functionality in the image interpretation and diagnosis

3 Data Heterogeneity Medical image data are heterogeneous in how they

are collected, formatted, distributed, and displayed Images are acquired

Bone

Soft tissue

(a)

Figure 4.3 (a) Single image slice from a CT scan of the body Note that bone appears

as areas of high signal intensity (white) The soft tissue does not have very good contrast.

(b) Single image slice from a MRI scan of the body Unlike CT, bone does not show

up as areas of high intensity; instead, MRI is especially suited to imaging soft tissue (Courtesy of A Lou).

repre-512× 512 pixels in size, whereas the MRI image contains 256 × 256pixels It is worth noting that, with the exception of Doppler ultrasound,diagnostic images are acquired and displayed in gray scale Hence issuespertaining to color, such as the choice of color space, do not arise formedical images Color images are edited only for illustration purposes,for example, in pseudocolor nuclear medicine; physicians rarely use colorimages in diagnosis and therapy workups.

4 Structural and Functional Contexts Structural information in a medical

image contributes essential knowledge of the disease state as it affects themorphology of the body For example, the location of a tumor, with respect

to its adjacent anatomic structures (spatial context), has profound tions in therapeutic planning, whereas monitoring of growth or shrinkage

implica-of that tumor (geometric context) is an important indicator implica-of the patient’sprogress in therapy However, what distinguishes medical images frommost other types of digital images is the representation of functional infor-mation (e.g., biochemistry and physiology) about body parts, in addition totheir anatomic contents and structures As an example, fluorodeoxyglucosePET scans show the relative oxygen consumption of brain tissue — areas

of low oxygen consumption (i.e., dark areas in the PET image) spond to tissue that is hypometabolic and may be dead or dying ThePET findings can then be compared with MRI findings in expectation thatareas of hypometabolism in PET correspond to areas of tissue atrophy

corre-in the MRI The precedcorre-ing example demonstrates the power of utilizcorre-ingmore than one imaging modality to bolster the clinical decision-makingprocess

5 Imprecision. Because of limited spatial resolution and contrast and thepresence of noise, medical images can only provide the physician with

an approximate and often imprecise representation of anatomic structuresand physiological functionalities This phenomenon applies to the entire

(a)

Figure 4.4 (a) FDG-PET image of the brain, coronal plane, 128× 128 × 8 bits,

(b) Mammography image, 4096× 4096 × 12 bits.