Thermography only allows the measurement of the surface temperature of objects, which in humans means the temperature of the skin. However, if we place a piece of clothing between the lens and the skin, the thermographic camera will return the surface temperature of the fabric, which we are not interested in and then we would fall into one of the seven most common errors in thermography data collection. Therefore, if we need to expose the skin to be able to measure its temperature, the ideal would be to take the data in complete nudity.
But how to expose as much skin as possible without conflicting with a person's privacy? To solve this complex question, we propose some intermediate solutions, which make it possible to analyze as many interesting regions as possible for both prevention and monitoring of injuries without exposing intimate areas.
In Figure 1a, we can observe a subject in underwear. There is an important difference in the placement of the underpants, so it is assumed that the thermographic analysis will be incorrect. Figure 1b clearly shows that the segmentation is asymmetrical, due to the underpants. Finally, in figure 1c, we verify a thermal asymmetry, whose origin is not in the physiology of the person, but in the incorrect comparison of regions of interest.
To exemplify the ideal leg protocol, we can see in Figure 1d the same athlete with his underwear properly positioned and tucked in. Figures 1e and 1f only confirm that the correct placement of the underwear allows for a more correct analysis and interpretation.
Figure 1.Comparison of segmentation and avatar of the same subject, modifying the position of the underwear in thermography.
In the case of measuring the torso region in women, respect for privacy is at its highest level. If we want to analyze the breast region we need to expose the skin of the breasts, which means that the patient must be without a bra during the session.
Figure 2 shows the thermographic segmentation of the torso of a woman wearing a bra. The interpretation of the temperature of the breast regions of this patient is null, since we do not obtain information on the patient's skin, but on that of the garment.
Figure 2. Example of a thermogram of a woman wearing a bra.
Therefore, if we want to analyze the breast region with good quality, in addition to not including the bra, it is recommended to use the specific protocol. In Figures 3a, 3b and 3c, we can observe the thermogram, the segmentation and the avatar of a patient without a bra, which exposes the skin of the breasts, so that both the segmentation and the avatar are faithful to reality.
Figure 3. Example of breast protocol, with segmentation and avatar.
There are certain lesions that cannot be assessed in thermography if they do not respect this principle of exposure. As we saw in the previous section, if our objective is to assess breast cancer, we will need the patient to be without a bra. In the same way, a muscular or myotendinous lesion in the rectus femoris, very common in soccer, will not be visible if this area of the skin is not exposed.
In that sense, one of the improvements in the ThermoHuman software in 2021, was the integration of this region in the segmentation of the lower protocol. In Figure 4, we can see an athlete with a muscle injury in the rectus femoris (left thigh) and with two different segmentations (4b and 4e). The segmentation that includes this more proximal region of the thigh (4e) gives us much more relevant information about the location, severity and nature of the injury. This is corroborated when we compare the results in the avatars (4c vs. 4f).
Figure 4.Comparison of the same image of an athlete with a myotendinous lesion in the left rectus femoris, with two different segmentations: 4b shows the old segmentation, which does not include the proximal thigh region, and 4e does include the proximal thigh region. 4c does not provide thermal data on the region, while 4f does.
Finally, the posterior area of the legs, which includes the gluteal region, experiences the same problem. If it is covered by underwear, it is not possible to draw conclusions based on temperature. It is therefore recommended to roll up the sleeves to expose the skin of the buttocks. Figure 5 shows an individual with the underwear incorrectly positioned (a-c) and the same individual following the thermographic protocol (e-f). Currently, the new algorithms of the ThermoHuman software make it possible to discriminate whether the subject is exposing the buttocks or has them covered by clothing, as we can see in Figure 5.
Figure 5. Comparison of the same subject, with underwear covering the gluteal region (a-c) and without (d-f).
In addition, the segmentation of the gluteal region has also evolved significantly with the latest improvements in ThermoHuman software algorithms. Previously, faced with the problem that undergarment fabric often covered the buttocks, we chose to ignore the entire region. Currently, we have much more robust algorithms that are able to discriminate whether there is underwear or not, and if there is not, the thermal information is extracted to add it to the analysis and subsequent interpretation of the data, as we saw in the case of Figure 5.
In the vast majority of body regions, when we expose the skin, there is no ethical conflict. However, there is when we analyze certain intimate regions, such as the inguinal region or the breasts in women. Therefore, we must find a balance between respect for the privacy of the person and quality in thermography data collection. From ThermoHuman, we opt for an intermediate alternative that respects the person and extracts an optimal quality of thermal information.
If you have any questions or would like to make a comment, do not hesitate to write to us. We will be glad to read you.
ThermoHuman has had the support of the Funds of the European Union and the Community of Madrid through the Operational Programme on Youth Employment. Likewise, ThermoHuman within the framework of the Export Initiation Program of ICEX NEXT, had the support of ICEX and the co-financing of the European Regional Development Fund (ERDF).
Thermohuman has received funding from the Centre for the Development of Industrial Technology (CDTI), in participation with the European Regional Development Fund (ERDF), for the R+D activities involved in creating a new tool, based on thermography, for the prediction and prevention of rheumatoid arthritis. See project detail.
