Age prediction of hematoma using hyperspectral imaging (HSI)

Abstract Hyperspectral imaging (HSI) analyzes the reflected light spectrum of an object, providing insights into its material composition. In this experimental, prospective study, standardized hematomas were created in subjects and observed over 21 days using a portable hyperspectral camera, aiming to correlate changes in the reflected light spectrum with hematoma age and enable an objective method for age determination of hematomas. In 25 young and healthy subjects, a hematoma was induced by injecting 3 ml of autologous blood on the volar side of the forearm. The hematomas were documented over a 7-day period in 24-hour intervals and then for an additional 14 days in 48-hour intervals using a portable HSI camera covering the wavelength range from 400 nm to 1000 nm. The datasets from the hematomas were normalized using the spectrum of unaffected skin. Lasso regression models were trained on the normalized data to identify age-dependent changes in the reflection spectra and to make age predictions for hematomas of unknown age. The different regression models were compared based on their predictive accuracy and then evaluated against the actual hematoma age. The best age prediction model based on HSI recordings achieved a mean prediction error of 3.35 days over a 21-day observation period.Expanding the data set and methodology, as well as combining them with other techniques and testing on naturally occurring hematomas of various sizes and locations, are necessary steps to transfer this method into practical application.