Biomedical Engineering Reference
In-Depth Information
maximize the effect of the computer output on their diagnosis. Thus, the research
and development of CAD has involved a team effort by investigators with different
backgrounds such as physicists, radiologists, computer scientists, engineers, psy-
chologists and statisticians.
CAD has become one of the major research subjects in medical imaging and
diagnostic radiology. In fact, a large number of CAD systems has been employed
for assisting physicians in the early detection of cancer (breast tumors in mammo-
grams [
10
,
11
], lung nodules in chest radiographs/CT [
12
,
13
], colorectal polyps in
CT colonography [
14
]), intracranial aneurysms in magnetic resonance angiography
(MRA) [
15
,
16
] or musculoskeletal diseases (vertebral fracture or deformity due to
osteoporosis in radiographs/MRI [
17
], bone erosions due to rheumatoid arthritis in
MRI [
18
,
19
]).
This chapter provides an overview of the main functionalities of CAD systems,
with particular attention to musculoskeletal diseases (MSD). MSD and related dis-
orders are often considered as an inevitable consequence of aging [
20
]. Many MSD
lead to joint pain, stiffness and limitedmotion, affecting all human body articulations.
As the population ages and physical capabilities decline, the aspiration to maintain
a normal and active lifestyle will unfortunately increase the development of MSD
yielding a staggering economical burden [
21
] and significant challenges in health-
care. As recognized by the new EU strategic programme [
22
], the strong synergy
of ICT and medicine that includes the CAD systems paves the way for predictive
medicine to better prevent and treat illnesses [
23
].
The chapter is organized as follows. In Sect.
12.2
, the state of the art of CAD
systems will be presented and some hints will be given on historical review and
current research status. In Sect.
12.3
, the main functionalities of CAD systems will be
described. In Sect.
12.4
, a CAD case study related to musculoskeletal diseases will be
presented: theRheumatoidArthritis (RA) scenariowill be described in the framework
of the RheumaSCORE system [
18
] and some clinical trials will be discussed. In
Sect.
12.5
, the chapter will be concluded by a summary and future prospects.
12.2 CAD Systems: State of the Art
Early studies on quantitative analysis of medical images by computers [
24
-
29
]were
reported in the 1960s. At that time, it was generally assumed that computers could
replace radiologists in detecting abnormalities, because computers and machines are
better at performing certain tasks than human beings. Although interesting results
have been reported, these early attempts were not successful, because computers were
not sufficiently powerful, advanced image-processing techniques were not available,
and digital images were not easily accessible. However, a serious flaw was an exces-
sively high expectation from computers. In fact, many different approaches to auto-
mated computer diagnosis have been attempted as aids in decision-making in many
fields of medicine since the 1950s.
