Age Prediction of Hematoma from Hyperspectral Images Using Convolutional Neural Networks
Open Access
- 11 February 2026
- journal article
- research article
- Published by MDPI AG in Journal of Imaging
- Vol. 12 (2) , 78
Abstract
Accurate estimation of hematoma age remains a major challenge in forensic practice, as current assessments rely heavily on subjective visual interpretation. Hyperspectral imaging (HSI) captures rich spectral signatures that may reflect the biochemical evolution of hematomas over time. This study evaluates whether a convolutional neural network (CNN) integrating both spectral and spatial information improves hematoma age estimation accuracy. Additionally, we investigate whether performance can be maintained using a reduced, physiologically motivated subset of wavelengths. Using a dataset of forearm hematomas from 25 participants, we applied radiometric normalization and SAM-based segmentation to extract hyperspectral patches. In leave-one-subject-out cross-validation, the CNN outperformed a spectral-only Lasso baseline, reducing the mean absolute error (MAE) from 3.24 days to 2.29 days. Band-importance analysis combining SmoothGrad and occlusion sensitivity identified 20 highly informative wavelengths; using only these bands matched or exceeded the accuracy of the full 204-band model across early, middle, and late hematoma stages. These results demonstrate that spectral–spatial modeling and physiologically grounded band selection can enhance estimation accuracy while significantly reducing data dimensionality. This approach supports the development of compact multispectral systems for objective clinical and forensic evaluation.
Keywords
All Related Versions
Funding Information
- German Federal Ministry of Economic Affairs and Energy (KK5110003GM4)
This publication has 37 references indexed in Scilit:
- Age prediction of hematoma using hyperspectral imaging (HSI)Forensic Science, Medicine and Pathology, 2025
- The Utility of Infrared Thermography and Hyperspectral Imaging in Peripheral Artery Disease: A Systematic ReviewHeart, Lung and Circulation, 2025
- Colour Measurements and Ultraviolet/Visible Spectroscopy2025
- Handheld hyperspectral imaging as a tool for the post-mortem interval estimation of human skeletal remainsHeliyon, 2024
- High Precision Monitoring of Radiofrequency Ablation for Liver Using Hyperspectral ImagingAnnals of Biomedical Engineering, 2021
- Age determination of soft tissue hematomasNMR in Biomedicine, 2014
- Visualizing and Understanding Convolutional Networks2014
- The science behind the quest to determine the age of bruises—a review of the English language literatureForensic Science, Medicine and Pathology, 2007
- A novel approach to age determination of traumatic injuries by reflectance spectroscopyLasers in Surgery and Medicine, 2006
- Spectrophotometric evaluation of the colour of intra- and subcutaneous bruisesInternational journal of legal medicine, 2000