Pre-clinical evaluation of a low-cost tool for skin temperature measurements as a proxy to assess autonomic nerve function in leprosy neuropathy

Abstract

Peripheral autonomic nerve function (ANF) impairment (ANFI) can be one of the first indicators for leprosy or leprosy neuropathy. However, within leprosy, hardly any ANF assessment methods are used in current practice. Skin temperature could be a proxy measure to assess ANF. Therefore, this research aims to explore whether low-cost infrared (IR) video thermography can be used as an ANF assessment tool by measuring the skin temperature response (STR) of human hands before, and after applying a cold pressor test (CPT). A protocol was defined to perform a baseline measurement, apply CPT, and record the resulting STR curve during 15 minutes. An IR video camera connected to a mobile phone was selected as sensor. A setup was developed to immobilize the position of the hands and fingers relative to the camera. A Python script was developed to extract the hand palm skin temperature STR curve from an IR video for 12 ulnar and median innervated regions of interest (ROI) in 1s intervals. A Matlab script was developed to post-process the raw temperature data into filtered data. This data is used to calculate key metrics that describe the STR curve. This approach was evaluated on technical accuracy and precision by comparing IR data for 3 cameras to a reference sensor. The variability caused by the observer analyzing the data was studied by analyzing the same video 5 times by 2 observers. The subject variability was studied by enrolling 7 subjects into a pilot, testing them daily for 5 consecutive days. The results show a high mean Interclass correlation of 0.94 between the 3 IR cameras and the reference sensor. Bland-Altman plots show a mean accuracy of +0.090°C between the cameras and the reference, and a variation between -1.30 and +1.50°C. High agreement was shown between observers analyzing the data. The pilot test showed high variability in STR curve within subjects. Although the general shape of the STR was similar, the location of the steep increase in recovery varied strongly within and between subjects. This study shows that a low-cost, portable IR camera can be used to measure STR of human hands after CPT. A pilot study showed high subject variability for repeated testing of the STR curve. Future research is needed to establish its value in assessing ANF in leprosy patients or other systemic and local neuropathies and traumatic nerve conditions.

Fig 1. Metrics defined for STR quantification shown on a hypothetical, typical STR curve.

Green relates to measurements in absolute temperature, red relates to measurements relative to the temperature drop.

Fig 2. Temperature images.

Left: Interface to select start and end points of both baseline and recovery phase. Right: Annotated frame with 12 ROI on the hands and 1 ROI on background. Also highlighted are the minimum and maximum value of the temperature scale.

Fig 3. The hardware setup.

The picture shows the setup consisting of a wooden plate, with 2 hand supports with finger separators, an IR camera in its 3D printed holder mounted on the vertical rod, a mobile phone in its holder, and a subject with his hands positioned in the hand supports.

Fig 4. Test setup for infrared camera accuracy testing. The camera is above the hands, just outside the picture.

Fig 5. The phone screen during the accuracy test, showing the rectangle for reading the average temperature that is displayed in the top right corner.

Fig 6. Effect of filtering.

Top: Filter performance on steady background temperature reading showing the Raw and Filtered signal. Bottom: Filtering on a healthy subject’s response, showing the Raw and Filtered signal. The big spikes in the raw signal are caused by misreading of the minimum or maximum temperature scale value by the OCR.

Fig 7. Combined correlation plot (left) and Bland-Altman plot (right) of all 3 cameras each having 2 repetitions.

Fig 8. Combined correlation plot (left) and Bland-Altman plot (right) of all 3 cameras against temperature extracted from video.

Fig 9. Repeatability of data extraction on some key metrics.

5 repetitions on the same video by 2 observers. L2, R2, L4 and R4 correspond with ROI located at the distal phalanx of the left index finger, right index finger, left pinky finger, and right pinky finger, respectively.

Fig 10. Temperature variability results of 1 ROI for 5 repeated measurements over 6 subjects.

Top panel: Temperature STR curves grouped by unique color and line style combination per subject. The instance of t = −1 minute indicates the baseline temperature before applying CPT. The instance t = 0 indicates T_o, the temperature direct after applying CPT. Bottom panel: The resulting key metrics (mean and SD) extracted from the STR curves. Subject P3 was excluded as this subject did only do 3 repetitions instead of 5.