Infantile hemangioma status by dynamic infrared thermography: A preliminary study

Abstract

Background: Infantile hemangiomas (IH) are initially warm due to increased proliferation and perfusion then involute with apoptosis and reduced perfusion. Objective quantitative evaluation of IH treatment response is essential for improving outcomes. We applied a functional imaging method, dynamic infrared (IR) thermography, to investigate IH status versus control skin and over time.

Materials and methods: A preliminary prospective observational study was conducted among 25 subjects with superficial or mixed IHs (< 19 months) over 59 clinic visits. Infrared images of IHs and control sites, standardized color images, and three-dimensional images were obtained. Tissue responses following application and removal of a cold stress were recorded with video IR thermography. Outcomes included areas under the curve during cooling (AUCcool ) and rewarming (AUCrw ) and thermal intensity distribution maps.

Results: AUCcool and AUCrw were significantly higher and cooling rate slower for IHs versus uninvolved tissue indicating greater heat, presumably due to greater perfusion and metabolism for the IH. IR distribution maps showed specific areas of high and low temperature. Significant changes in IH thermal activity were reflected in the difference (AUCcool - AUCrw ), with 6.2 at 2.2 months increasing to 37.6 at 12.8 months. IH cooling rate increased with age, indicating slower recovery, and interpreted as reduced proliferation and/or involution.

Conclusions: Dynamic IR thermography was a well-tolerated, quantitative functional imaging modality appropriate for the clinic, particularly when structural changes, i.e., height, volume, color, were not readily observed. It may assist in monitoring progress, individualizing treatment, and evaluating therapies.

Clinical trial registration: www.clinicaltrials.gov (Identifier NCT02061735).

Keywords: dynamic infrared thermography; functional imaging; infantile hemangioma; infrared; propranolol; quantitative imaging; vascular tumors.

Figure 1. Dynamic Thermal Imaging Outcomes

Figure 1 shows the behavior of an IH and uninvolved control site during application and removal of a cold stress for a subject with AUCrw comparable to the overall mean. AUCcool, AUCrw, temperature after cooling, ΔT cool, ΔT rewarm and static temperature are indicated.

Figure 2. Dynamic Thermal Response

Figure 2 illustrates the color image, corresponding static IR image and dynamic IR images over 60 seconds for a mixed IH treated with propranolol (a). Thermal intensity is indicated by colors (white highest, red, orange, yellow, green, etc.) in panels (b) prior to cooling, (c) after 30 seconds of cooling, (d) after 5 seconds of rewarming, and after 30 seconds of rewarming (e). The co-registered color and static IR images (panel a) show the hemangioma thermal area of involvement to extend beyond the visible borders in the color image. The graphs show thermal distributions of the highest 10% of temperature. The graphs (panels f – i) show the areas of highest thermal activity relative to the color image (panel a). Before cooling (static, time 0), temperature and area were 36.1 °C and 2252 pixels, respectively (panel f). Immediately after cool stress removal (T30 sec), temperature and area were 35.0 °C and 247 pixels, respectively (panel g). Five seconds later (T35 sec), temperature and area were 35.8 °C, respectively (panel h). After 30 seconds of rewarming (T60 sec), temperature and area were 36.4 °C and 1787 pixels (panel i). Graph colors indicate temperature, i.e., red color indicates 37.5 – 38.0 °C (panels f – i). IR areas increased over time after cooling (panels g – i). The area of 1787 pixels after 30 seconds of rewarming was lower than the pre-cooling value of 2252, indicating the area had not yet returned to pre-cooling levels.

Figure 3. a,b Dynamic IR Responses Over Time

Figure 3 illustrates the dynamic IR responses over time for two individual subjects. A progressive reduction in AUCcool and AUCrw from 2 to 12 months was observed for an IH treated with topical timolol (Fig 3a). Curves are shown for responses at 1.8 (-◊-), 2.9 (-■-), 5.0 (-Δ-), 8.2 (-x-) and 12.1 (-o-) months (Fig 3a). Little change in response to cooling was found from 4.9 to 8.9 months in a subject receiving oral propranolol (Fig 3b). Curves are shown for cooling responses at 4.8 (-◊-), 6.1 (-■-), 8.0 (-x-) and 8.9 (-o-) months

Figure 3. a,b Dynamic IR Responses Over Time

Figure 3 illustrates the dynamic IR responses over time for two individual subjects. A progressive reduction in AUCcool and AUCrw from 2 to 12 months was observed for an IH treated with topical timolol (Fig 3a). Curves are shown for responses at 1.8 (-◊-), 2.9 (-■-), 5.0 (-Δ-), 8.2 (-x-) and 12.1 (-o-) months (Fig 3a). Little change in response to cooling was found from 4.9 to 8.9 months in a subject receiving oral propranolol (Fig 3b). Curves are shown for cooling responses at 4.8 (-◊-), 6.1 (-■-), 8.0 (-x-) and 8.9 (-o-) months

Figure 4. Thermal Intensity Distribution Map 1

The figure shows co-registered color images (panel a) and thermal distribution maps (panels b – e) before cooling and during rewarming. The superficial IH was approximately 1.8 cm × 1.6 cm (color image, panel a) at 1.8 months before initiation of topical timolol treatment. The temperature is lower in the center (panel b), 36.7 °C and 1296 pixels in area. After cooling, the highest temperatures were in regions toward the periphery with increasing activity at the top and left (panels d, e)). The area of the highest 10% temperature increased from 150 pixels (panel c, temperature 34.7 °C), to 503 pixels (panel d, temperature 35.2 °C) and 753 pixels (panel e, temperature 35.5 °C) over 26 seconds of rewarming. The area (panel e) was smaller than the static image (panel b) indicating that the IH had not yet returned to static conditions. The temperature increased from 34.7 to 35.5 °C.

Figure 5. Thermal Intensity Distribution Map 2

The figure shows co-registered color images and thermal distribution maps before cooling and during rewarming. The untreated mixed IH was approximately 4.3 cm × 3.7 cm (color image, panel a) at 13.4 months. Prior to cooling, the highest temperatures were at the top and bottom with cooler regions toward the center (panel b). After cooling and during rewarming, the highest activity was at the top and in the deep portion of the IH (panels c, d, e). The thermal area increased from 485 pixels after 30 sec of cooling (panel c, temperature 36.3 °C), to 1440 pixels after 7 seconds of rewarming (panel d, temperature 36.3 °C), and 2857 pixels after 29 seconds of rewarming (panel c, temperature 36.4 °C). Temperature increased from 36.2 to 36.4 °C. Lower temperatures were noted in the superficial portion (panels a, c, d, e).

Figure 6. Thermal Distribution Maps with Color Images

The figure shows color images of three hemangiomas overlaid with the corresponding thermal distribution maps. immediately after the 30 sec cool stress. Panel (a) is the mixed IH treated with propranolol from Figure 2 where Fig 2 (a) is overlaid with the thermal map of Fig 2 (g). The area of highest thermal activity is in the deeper portion above the red superficial area. Panel (b) is the superficial IH in Figure 4 prior to initiation of timolol therapy where Fig 4 (a) is overlaid with the thermal map of Fig 4 (c). The highest thermal activity is at the outer edges of the hemangioma. Panel (c) is the untreated mixed IH in Figure 5 where Fig 5 (a) is overlaid with Fig 5 (c). The highest thermal activity is at the top portion of the red superficial portion.