Professional Documents
Culture Documents
This study further evaluated a computer- all hands (healthy and pathological) based
based infrared thermography (IRT) system, on dorsal images and > 80% of hands when
which employs artificial neural networks only severely affected and healthy hands
for the diagnosis of carpal tunnel syndrome were considered. Compared with the gold
(CTS) using a large database of 502 thermal standard electromyographic diagnosis of
images of the dorsal and palmar side of 132 CTS, IRT cannot be recommended as an
healthy and 119 pathological hands. It adequate diagnostic tool when exact
confirmed the hypothesis that the dorsal severity level diagnosis is required, however
side of the hand is of greater importance we conclude that IRT could be used as a
than the palmar side when diagnosing CTS screening tool for severe cases in
thermographically. Using this method it populations with high ergonomic risk
was possible correctly to classify 72.2% of factors of CTS.
KEY WORDS: CARPAL TUNNEL SYNDROME; DIAGNOSIS; INFRARED THERMOGRAPHY; SKIN TEMPERATURE;
ARTIFICIAL INTELLIGENCE
779
B Jesenšek Papež, M Palfy, M Mertik et al.
Artificial intelligence-based infrared thermography
780
B Jesenšek Papež, M Palfy, M Mertik et al.
Artificial intelligence-based infrared thermography
781
B Jesenšek Papež, M Palfy, M Mertik et al.
Artificial intelligence-based infrared thermography
FIGURE 2: Typical thermal image of the dorsal side of a patient’s hand after
segmentation into 12 areas of interest: fingers (five segments), metacarpus (five
segments) and carpus with wrist (two segments)
782
B Jesenšek Papež, M Palfy, M Mertik et al.
Artificial intelligence-based infrared thermography
A0 = 1
W0
A1
W1
I
N
P
W2 Sum Output
U
T
A2
Σ
S Input Activation
function function
Wn
An
FIGURE 3: Mathematical model of an artificial neuron (A0, A1, etc. represent attributes
[inputs]; W0, W1, etc. represent the weight of each input, which changes with the
learning process)19
783
B Jesenšek Papež, M Palfy, M Mertik et al.
Artificial intelligence-based infrared thermography
In1
In2 Out1
Out2
Inn
to be classified are usually divided into two images, only from dorsal images, only from
sets. The first set consists of cases used for the palmar images, and data from dorsal
learning process through which the ANN images of healthy and severe cases only).
adapts itself. The second set consists of cases Each time a fully connected multilayer
previously unknown to the trained ANN. perceptron with two hidden layers (nine
These cases are then classified and the results neurons in the first hidden layer, five
compared to actual class values. In theory, if neurons in the second hidden layer) was
the training set is large and diverse enough, used and 100 training repetitions were
an ANN can accumulate enough knowledge carried out (each case from the training set
to classify unknown objects reliably. In the was used 100 times). ANN topology and
present study, the training set was training process parameters were chosen
constructed by computer random selection according to the results of our previous
and represented 80% of the whole set, with work.8,14 Each classification was repeated five
the remaining 20% used for testing the times, each time using a randomly selected
classification reliability. Before training training set of 80% of all hands (200 or 148
started, the temperature of each individual hands when mild and moderate CTS cases
segment was normalized according to the were omitted), and the percentage of
mean temperature of the whole hand. This successful classifications was calculated from
ensured that differences in the temperatures the mean of the five attempts.
of hands between different people did not
influence the classification outcome. Such STATISTICAL ANALYSIS
temperature differences between individuals All statistical analyses were performed using
are common and usually unrelated to any the R Project for Statistical Computing, a
pathology. The remaining cases were then software language and environment for
classified. Different classification attempts statistical computing, which is available as
were carried out by altering the inclusion free software under the terms of the GNU
criteria for the input set (data from all General Public License.23 Where appropriate,
784
B Jesenšek Papež, M Palfy, M Mertik et al.
Artificial intelligence-based infrared thermography
TABLE 1:
Mean classification success rate of five classification runs for diagnosis when only dorsal
segments were included and no distinction was made between patients with different
severities of CTS (n = 51; 20% of all hands)
CTS correctly CTS incorrectly
Classification run classified, n classified, n Success rate (%)
1 37 14 72.5
4 38 13 74.5
3 37 14 72.5
4 36 15 70.6
5 36 15 70.6
Mean ± SD 36.8 ± 0.84 14.2 ± 0.84 72.2 ± 1.64
CTS, carpal tunnel syndrome.
785
B Jesenšek Papež, M Palfy, M Mertik et al.
Artificial intelligence-based infrared thermography
TABLE 2:
Mean classification success rate of five classification runs for the diagnosis of CTS when
dorsal and palmar segments were included and no distinction was made between patients
with different severities of CTS (n = 51; 20% of all hands)
CTS correctly CTS incorrectly
Classification run classified, n classified, n Success rate (%)
1 33 18 64.7
2 31 20 60.8
3 32 19 62.7
4 30 21 58.8
5 32 19 62.7
Mean ± SD 31.6 ± 1.14 19.4 ± 1.14 62.0 ± 2.23
CTS, carpal tunnel syndrome.
TABLE 3:
Mean classification success rate of five classification runs for the diagnosis of CTS when
only palmar segments were included and no distinction was made between patients with
different severities of CTS (n = 51; 20% of all hands)
CTS correctly CTS incorrectly
Classification run classified, n classified, n Success rate (%)
1 29 22 56.9
2 31 20 60.8
3 29 22 56.9
4 30 21 58.8
5 29 22 56.9
Mean ± SD 29.6 ± 0.89 21.4 ± 0.89 58.0 ± 1.75
CTS, carpal tunnel syndrome.
TABLE 4:
Statistical significance of the differences between segment temperatures in patients’ and
volunteers’ hands according to the non-parametric Mann–Whitney–Wilcoxon test
Statistical significance
Segment Dorsal side Palmar side
Whole hand 0.007162 0.1621 (NS)
First finger (thumb) 0.034990 0.1676 (NS)
Second (index) finger 0.029850 0.2174 (NS)
Third (middle) finger 0.017270 0.1169 (NS)
Fourth (ring) finger 0.017840 0.1701 (NS)
Fifth (little) finger 0.053060 (NS) 0.2399 (NS)
Below first finger 0.008782 0.0939 (NS)
Below second finger 0.004250 0.1610 (NS)
Below third finger 0.003147 0.1722 (NS)
Below fourth finger 0.003551 0.2700 (NS)
Below fifth finger 0.011470 0.4620 (NS)
NS, not statistically significant (P > 0.05).
786
B Jesenšek Papež, M Palfy, M Mertik et al.
Artificial intelligence-based infrared thermography
the database (n = 185), the classification segments of hands of severe CTS cases and
results improved (83.2%; Table 5). The segments of healthy hands were even more
decision to focus on severe cases only significant (Fig. 5).
originated from results of the statistical
analysis that compared dorsal segments Discussion
across different NCS severity levels (Table 6). In recent years, artificial intelligence-based
When the dorsal segments of all CTS cases systems have proved to be useful and
were compared with the corresponding successful tools that have often been used for
segments of healthy hands, there were decision support, data mining and
statistically significant differences between knowledge discovery in medicine. Despite its
all of them with only one exception (fifth practical advantages over EMG, IRT has not
[little] finger). The differences between the established itself in the field of CTS
TABLE 5:
Mean classification success rate of five classification runs for the diagnosis of CTS when only
dorsal segments of severe cases and healthy hands were used (n = 37; 20% of all hands)
CTS correctly CTS incorrectly
Classification run classified, n classified, n Success rate (%)
1 31 6 83.8
2 32 5 86.5
3 29 8 78.4
4 32 5 86.5
5 30 7 81.1
Mean ± SD 30.8 ± 1.30 6.2 ± 1.30 83.24 ± 3.52
CTS, carpal tunnel syndrome.
TABLE 6:
Statistical significances of the differences between dorsal segment temperatures for
different NCS severity levels of CTS according to the non-parametric Mann–Whitney–
Wilcoxon test
Severe– Moderate– Mild– All CTS–
Segment Normal normal normal normal
Whole hand 1.79 × 10-6 0.285800 (NS) 0.237400 (NS) 0.007162
First finger (thumb) 5.07 × 10-5 0.509300 (NS) 0.244800 (NS) 0.034990
Second (index) finger 6.19 × 10-5 0.449800 (NS) 0.295100 (NS) 0.029850
Third (middle) finger 4.90 × 10-5 0.397900 (NS) 0.470900 (NS) 0.017270
Fourth (ring) finger 3.49 × 10-5 0.557500 (NS) 0.550600 (NS) 0.017840
Fifth (little) finger 4.03 × 10-4 0.619200 (NS) 0.473400 (NS) 0.053060
Below first finger 2.32 × 10-6 0.165400 (NS) 0.111200 (NS) 0.008782
Below second finger 3.36 × 10-7 0.218600 (NS) 0.166000 (NS) 0.004250
Below third finger 1.42 × 10-7 0.228700 (NS) 0.175600 (NS) 0.003147
Below fourth finger 1.24 × 10-7 0.279400 (NS) 0.176200 (NS) 0.003551
Below fifth finger 1.69 × 10-7 0.318200 (NS) 0.132300 (NS) 0.011470
NS, not statistically significant (P > 0.05).
CTS, carpal tunnel syndrome; NCS, nerve conduction studies.
787
B Jesenšek Papež, M Palfy, M Mertik et al.
Artificial intelligence-based infrared thermography
0.010000
0.001000
0.000100
0.000010
0.000001
0.000000
an
d b) ge
r
ge
r r
ge inge inge
r r er er er er
h h um ) fin ) fin ) fin f f f ing f ing fing fing
ole (t x le ng little
)
fir
st
on
d ird urth fifth
W
h er de dd (ri ec th fo
f ing d (in (mi rth h
(
l o w s o w low
i r st o n i r d ou F ift Be l ow B el e low Be
F c Th F B e B
Se
FIGURE 5: The statistical significances of the differences between the dorsal segment
temperatures in the group with ‘severe’ carpal tunnel syndrome (CTS) and the
‘normal’ healthy group (bottom line, data from Table 6) were even more pronounced
than the statistical significances of the differences between the dorsal segment
temperatures in all CTS severity groups and the ‘normal’ healthy group (top line, data
from Table 4) (NS, not statistically significant [P > 0.05])
diagnosis.7 Results from our previous hands. Consistent with other studies, the
research showed how an intelligent system present study clearly demonstrated the
based on an ANN can be used to classify validity of this hypothesis (Table 4).5,6,25 In
thermal images depicting healthy and CTS addition, it was ascertained that palmar
hands without the need for a cold stress test,8 segments are of no use when using IRT to
which is considered to be the standard diagnose CTS.
provocation procedure when diagnosing One of the initial goals, after achieving
nerve entrapments.24 High classification promising results on the smaller image
success rates (> 80% on several occasions) database, was to extend the classification of
were achieved on a small set of images (n = CTS cases to different severity levels
112).8 Due to the possibility of misleading according to NCS. For this purpose, the ANN
results from such a small initial image set, a was redesigned to be able to classify input
much larger database (n = 502) was then data into four different classes (normal,
acquired. The present study tested a mild, moderate and severe); however the
hypothesis, already discussed in the classification results were poor. Another
literature5 and suggested by the results of our established machine-learning tool,26 a
previous study,8 that dorsal segments are of decision tree, was also tested but did not
greater importance than palmar segments produce useful results. Thus, the idea of
when analysing thermal images of CTS trying to develop a direct association
788
B Jesenšek Papež, M Palfy, M Mertik et al.
Artificial intelligence-based infrared thermography
between ANN outputs and NCS severity and sustained wrist or palmar pressure. As
levels was abandoned. Based on statistical CTS has reached epidemic proportions in
analysis that showed the most significant many occupations and is a major cause of
differences were between severe CTS cases loss of work and workers’ compensation,1
and healthy hands, it was decided to include many researchers in both medical and non-
only severe cases. After training and testing medical fields are looking for a CTS
the ANN on this reduced database (dorsal diagnostic method that could be also used in
images of severe CTS level and healthy the area of occupational health and safety.
hands only, n = 185), the best results were According to the findings of the present
achieved with a mean classification success analysis of severe cases of CTS,
rate that exceeded 83% (Table 5). These thermography-based methods could be
results might suggest that IRT could be used recommended for screening for severe nerve
during NCS diagnostic procedures, bearing entrapments since these methods would help
in mind that it is non-invasive and patient- reduce long waiting lists for EMG
friendly when compared with EMG. investigations. The method developed and
Nevertheless, IRT cannot be recommended as described in the present study, with its clear
an adequate diagnostic tool when an exact identification of severe CTS cases, could be
diagnosis of CTS severity level is required. It used to prioritize patients on a waiting list
could, however, be used as a screening for EMG diagnosis as EMG is still the only
method when dealing with populations with reliable gold standard.
high ergonomic risk factors for developing
CTS, such as repetitive hand and wrist use, Conflicts of interest
work with vibrating tools, hand use in the The authors had no conflicts of interest to
cold, prolonged wrist extension and flexion, declare in relation to this article.
• Received for publication 22 December 2008 • Accepted subject to revision 10 January 2009
• Revised accepted 11 May 2009
Copyright © 2009 Field House Publishing LLP
789
B Jesenšek Papež, M Palfy, M Mertik et al.
Artificial intelligence-based infrared thermography
790