Infrared thermography as a modality for tracking cutaneous temperature change and post-mortem interval in the critical care setting.

PURPOSE: To evaluate the potential use of cutaneous facial temperature change as measured by an infrared camera as a marker of postmortem interval (PMI) in the minutes immediately following death. METHODS: This was a prospective, observational pilot study using a convenience sample of all deaths which occurred in a room in an Intensive Care Unit equipped with a ceiling mounted thermal camera. Cutaneous temperature measurements were taken from 60 min antemortem to as long as possible postmortem. RESULTS: A total of 134 separate measurements was taken from 5 patients, with 65 occurring antemortem, and 69 occurring post-mortem. The longest recorded post-mortem time was 130 min. A Kruskal-Wallis ANOVA testing the hypothesis that there was a difference in facial temperature at each of the different timepoints showed significance (p = 0.029). Post-Hoc comparisons were then performed to compare median temperature values at each timeframe to the baseline value. Compared to baseline, there was a significant difference in facial temperature at 30, 60, and 90 min (p = 0.007, p = 0.01, p = 0.016) (Table 2). CONCLUSION: There is a statistically significant cutaneous facial temperature change in patients immediately following death as measured by a thermal camera. There is potential for infrared thermography to identify changes immediately before and after death in environments where traditional temperature measurement cannot be accomplished. More work needs to be done to confirm whether a precise postmortem interval (PMI) could be derived from these values.

A Deep Learning-Based Camera Approach for Vital Sign Monitoring Using Thermography Images for ICU Patients.

Infrared thermography for camera-based skin temperature measurement is increasingly used in medical practice, e.g., to detect fevers and infections, such as recently in the COVID-19 pandemic. This contactless method is a promising technology to continuously monitor the vital signs of patients in clinical environments. In this study, we investigated both skin temperature trend measurement and the extraction of respiration-related chest movements to determine the respiratory rate using low-cost hardware in combination with advanced algorithms. In addition, the frequency of medical examinations or visits to the patients was extracted. We implemented a deep learning-based algorithm for real-time vital sign extraction from thermography images. A clinical trial was conducted to record data from patients on an intensive care unit. The YOLOv4-Tiny object detector was applied to extract image regions containing vital signs (head and chest). The infrared frames were manually labeled for evaluation. Validation was performed on a hold-out test dataset of 6 patients and revealed good detector performance (0.75 intersection over union, 0.94 mean average precision). An optical flow algorithm was used to extract the respiratory rate from the chest region. The results show a mean absolute error of 2.69 bpm. We observed a computational performance of 47 fps on an NVIDIA Jetson Xavier NX module for YOLOv4-Tiny, which proves real-time capability on an embedded GPU system. In conclusion, the proposed method can perform real-time vital sign extraction on a low-cost system-on-module and may thus be a useful method for future contactless vital sign measurements.