![](bg1.png)
AUTOMATED DETECTION OF SUPPORTING DEVICE
POSITIONING IN RADIOGRAPHY
Chen Sheng, Li Li and Ying Jun
College of Mathematics and Science, Shanghai Normal University, Guilin Road 100, Shanghai, China
Keywords: Gaussian Filter, Contrast-Limited Adaptive Histogram Equalization (CLAHE), Hough Transform, Tube.
Abstract: Portable X-ray radiographs are heavily used in the ICU for detecting significant or unexpected conditions
requiring immediate changes in patient management. One concern for effective patient management relates
to the ability to detect the proper positioning of tubes that have been inserted into the patient. These include,
for example, endo-tracheal tubes (ET), feeding tubes (FT), naso-gastric tubes (NT), and other tubes. Proper
tube positioning can help to ensure delivery or disposal of liquids and air/gases to and from the patient
during a treatment procedure. Improper tube positioning can cause patient discomfort, render a treatment
ineffective, or can even be life-threatening. However, because the poor image quality in portable AP X-ray
images due to the variability in patients, apparatus positioning, and X-ray exposure, it is often difficult for
clinicians to visually detect the position of tube tips. Thus, there is a need for detecting and identifying tube
position and type to assist clinicians. The purpose of this paper is to present a computer-aided method for
automated detection of tubes and identification of tube types. Use of this method may allow clinicians to
detect the tube tips more easily and accurately, thus improving the quality of patient management in the
ICU.
1 INTRODUCTION
Computer-aided diagnosis is designed to help
physicians improve the diagnostic accuracy of
radiological images and for detection of the disease,
and to explain the consistency, reduce the rate of
misdiagnosis, and cause less opportunity for eye
fatigue
. The chest CAD system (Brem and Baum,
2003) and the Mammography CAD system (Bram
and Bart, 2001) are both used in clinics. Clinical
results show two aspects: Medical diagnostic
radiology consults the CAD output and it is thus
easier to find more features, such as micro-
calcifications and the changes that have taken place
in the tiny structures, greatly improving the
efficiency and accuracy of diagnosis. We research
the method of tube automatic detection for
improving the quality of patient management in the
Intensive Care Unit (ICU) (Doi and MacMahon,
1999).
ICU patients, particularly those with heart and
lung diseases, rely on the existence of tubes to live
and be treated. In the intensive care setting, catheters,
tubes, and monitoring devices play an important role.
Proper placement of these devices is crucial to their
function Personnel are well aware of the need for
timely medical ICU care for patients, correct
placement of tubes, and the changes that need to be
made around these tubes’ positions. If the computer
can automatically identify the location of tubes and
their tips, and enhance medical images around tubes
to provide diagnosis, it is a clear and very important
improvement to their procedures.
ICU patients’ chest X-ray images can be fuzzy,
exhibit low contrast and noise, and contain many
different types of tube connections on the image,
such as the endo-tracheal tube, feeding tube, naso-
gastric tube, pulmonary artery, central venous
catheter, and other catheters required for the
treatment of a variety of medical conditions. These
bring a significant challenge to accurately detect
tubes and their tips. Figure 1 shows a general
original ICU chest image.
2 METHODS AND MATERIALS
We collected a database consisting of 107 portable
X-ray images from 20 patients using Kodak’s
computed radiography (CR) system. An experienced
420
Sheng C., Li L. and Jun Y. (2008).
AUTOMATED DETECTION OF SUPPORTING DEVICE POSITIONING IN RADIOGRAPHY.
In Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing, pages 420-424
DOI: 10.5220/0001061004200424
Copyright
c
SciTePress