{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T15:02:56Z","timestamp":1770822176883,"version":"3.50.1"},"reference-count":38,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T00:00:00Z","timestamp":1770768000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"German Federal Ministry of Economic Affairs and Energy","award":["KK5110003GM4"],"award-info":[{"award-number":["KK5110003GM4"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>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 64\u00d764\u00d7204 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\u2013spatial 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.<\/jats:p>","DOI":"10.3390\/jimaging12020078","type":"journal-article","created":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T13:25:49Z","timestamp":1770816349000},"page":"78","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Age Prediction of Hematoma from Hyperspectral Images Using Convolutional Neural Networks"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2944-0994","authenticated-orcid":false,"given":"Arash","family":"Keshavarz","sequence":"first","affiliation":[{"name":"Visual Computing, Fraunhofer-Institute for Computer Graphics Research IGD, 18059 Rostock, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2496-6232","authenticated-orcid":false,"given":"Gerald","family":"Bieber","sequence":"additional","affiliation":[{"name":"Visual Computing, Fraunhofer-Institute for Computer Graphics Research IGD, 18059 Rostock, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8892-5371","authenticated-orcid":false,"given":"Daniel","family":"Wulff","sequence":"additional","affiliation":[{"name":"Institute of Visual & Analytic Computing, University of Rostock, 18059 Rostock, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6621-9705","authenticated-orcid":false,"given":"Carsten","family":"Babian","sequence":"additional","affiliation":[{"name":"Institute of Forensic Medicine Leipzig, 04103 Leipzig, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1488-4236","authenticated-orcid":false,"given":"Stefan","family":"L\u00fcdtke","sequence":"additional","affiliation":[{"name":"Institute of Visual & Analytic Computing, University of Rostock, 18059 Rostock, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,11]]},"reference":[{"key":"ref_1","unstructured":"National Library of Medicine (1999). Hematoma. Medical Subject Headings (MeSH), U.S. National Library of Medicine. MeSH Descriptor Data."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1397","DOI":"10.1002\/nbm.3202","article-title":"Age determination of soft tissue hematomas","volume":"27","author":"Neumayer","year":"2014","journal-title":"NMR Biomed."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1258\/msl.2011.010135","article-title":"Can we assess the age of bruises? An attempt to develop an objective technique","volume":"51","author":"Grossman","year":"2011","journal-title":"Med. Sci. Law"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1007\/s12024-007-9019-3","article-title":"The science behind the quest to determine the age of bruises\u2014A review of the English language literature","volume":"3","author":"Langlois","year":"2007","journal-title":"Forensic Sci. Med. Pathol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1007\/s004149900107","article-title":"Spectrophotometric evaluation of the colour of intra-and subcutaneous bruises","volume":"113","author":"Bohnert","year":"2000","journal-title":"Int. J. Leg. Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1136\/jcp.2003.011445","article-title":"The practical application of reflectance spectrophotometry for the demonstration of haemoglobin and its degradation in bruises","volume":"57","author":"Hughes","year":"2004","journal-title":"J. Clin. Pathol."},{"key":"ref_7","first-page":"277","article-title":"A novel approach to age determination of traumatic injuries by reflectance spectroscopy","volume":"38","author":"Randeberg","year":"2006","journal-title":"Lasers Surg. Med. Off. J. Am. Soc. Laser Med. Surg."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Marin, A., Hren, R., and Milani\u010d, M. (2023). Pulsed photothermal radiometric depth profiling of bruises by 532 nm and 1064 nm lasers. Sensors, 23.","DOI":"10.3390\/s23042196"},{"key":"ref_9","unstructured":"Rajadhyaksha, M., and Zeng, H. (2025). Documenting bruises with spectroscopy and imaging. Proceedings of the Photonics in Dermatology and Plastic Surgery 2025, SPIE."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1111\/1556-4029.14578","article-title":"Bruise dating using deep learning","volume":"66","author":"Tirado","year":"2021","journal-title":"J. Forensic Sci."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"420","DOI":"10.2478\/raon-2022-0051","article-title":"Imaging perfusion changes in oncological clinical applications by hyperspectral imaging: A literature review","volume":"56","author":"Hren","year":"2022","journal-title":"Radiol. Oncol."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Hren, R., D\u00f3czi, T., Orszagh, E., and Babi\u010d, D. (2025). Recent Advances in Perfusion Assessment in Clinical Oncology Using Hyperspectral Imaging. Electronics, 14.","DOI":"10.3390\/electronics14173439"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1840","DOI":"10.1111\/iwj.13474","article-title":"Hyperspectral imaging in wound care: A systematic review","volume":"17","author":"Saiko","year":"2020","journal-title":"Int. Wound J."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"102195","DOI":"10.1016\/j.pdpdt.2021.102195","article-title":"Hyperspectral imaging assessment for radiotherapy induced skin-erythema: Pilot study","volume":"33","author":"Abdlaty","year":"2021","journal-title":"Photodiagn. Photodyn. Ther."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2430","DOI":"10.1007\/s10439-021-02797-w","article-title":"High precision monitoring of radiofrequency ablation for liver using hyperspectral imaging","volume":"49","author":"Abdlaty","year":"2021","journal-title":"Ann. Biomed. Eng."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2546819","DOI":"10.1080\/24699322.2025.2546819","article-title":"Surgical hyperspectral imaging: A systematic review","volume":"30","author":"Ali","year":"2025","journal-title":"Comput. Assist. Surg."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Kim, H.H., Song, I.S., and Cha, R.J. (2024). Advancing DIEP Flap Monitoring with Optical Imaging Techniques: A Narrative Review. Sensors, 24.","DOI":"10.3390\/s24144457"},{"key":"ref_18","first-page":"652","article-title":"Hyperspectral imaging for noninvasive tissue perfusion measurements of the lower leg: Review of literature and introduction of a standardized measurement protocol with a portable system","volume":"60","author":"Kleiss","year":"2019","journal-title":"J. Cardiovasc. Surg."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1194","DOI":"10.1016\/j.hlc.2025.03.017","article-title":"The Utility of Infrared Thermography and Hyperspectral Imaging in Peripheral Artery Disease: A Systematic Review","volume":"34","author":"Pakarinen","year":"2025","journal-title":"Heart Lung Circ."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1699","DOI":"10.1007\/s12024-025-01076-7","article-title":"Age prediction of hematoma using hyperspectral imaging (HSI)","volume":"21","author":"Babian","year":"2025","journal-title":"Forensic Sci. Med. Pathol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"e49023","DOI":"10.2196\/49023","article-title":"Practical Considerations and Applied Examples of Cross-Validation for Model Development and Evaluation in Health Care: Tutorial","volume":"2","author":"Wilimitis","year":"2023","journal-title":"JMIR AI"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Cui, R., Yu, H., Xu, T., Xing, X., Cao, X., Yan, K., and Chen, J. (2022). Deep Learning in Medical Hyperspectral Images: A Review. Sensors, 22.","DOI":"10.3390\/s22249790"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Baig, N., Fabelo, H., Ortega, S., Callico, G.M., Alirezaie, J., and Umapathy, K. (2021, January 1\u20135). Empirical Mode Decomposition Based Hyperspectral Data Analysis for Brain Tumor Classification. Proceedings of the 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Guadalajara, Mexico.","DOI":"10.1109\/EMBC46164.2021.9629676"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., and Lo, W.Y. (2023). Segment Anything. arXiv.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e220232","DOI":"10.1148\/ryai.220232","article-title":"A Guide to Cross-Validation for Artificial Intelligence in Medical Imaging","volume":"5","author":"Bradshaw","year":"2023","journal-title":"Radiol. Artif. Intell."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Karagiannis, G., and Amanatiadis, S. (2025). Colour Measurements and Ultraviolet\/Visible Spectroscopy. Non-Destructive Methodologies and Adapted Signal Processing Techniques in the Field of Cultural Heritage, Springer Nature.","DOI":"10.1007\/978-3-031-85780-5_10"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3555","DOI":"10.1364\/BOE.493588","article-title":"Relevance and utility of the in-vivo and ex-vivo optical properties of the skin reported in the literature: A review [Invited]","volume":"14","author":"Setchfield","year":"2023","journal-title":"Biomed. Opt. Express"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"146","DOI":"10.17691\/stm2025.17.1.12","article-title":"Study of Minor Chromophores in Biological Tissues by Diffuse Optical Spectroscopy (Review)","volume":"17","author":"Bylinskaya","year":"2025","journal-title":"Sovrem. Tehnol. V Med."},{"key":"ref_29","unstructured":"Smilkov, D., Thorat, N., Kim, B., Vi\u00e9gas, F., and Wattenberg, M. (2017). SmoothGrad: Removing noise by adding noise. arXiv."},{"key":"ref_30","first-page":"85","article-title":"Explainable Deep Learning Methods in Medical Image Classification: A Survey","volume":"56","author":"Neves","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Zeiler, M.D., and Fergus, R. (2014). Visualizing and Understanding Convolutional Networks. Computer Vision\u2013ECCV 2014, Springer International Publishing.","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1331","DOI":"10.1016\/j.icte.2024.09.008","article-title":"Explainable AI (XAI) in image segmentation in medicine, industry, and beyond: A survey","volume":"10","author":"Tsai","year":"2024","journal-title":"ICT Express"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1364\/BOE.479320","article-title":"Measurement of tissue optical properties in a wide spectral range: A review [Invited]","volume":"14","author":"Martins","year":"2022","journal-title":"Biomed. Opt. Express"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"102811","DOI":"10.1016\/j.jflm.2025.102811","article-title":"Optimizing the detection and characterization of bruises using multispectral imaging","volume":"111","author":"Wilk","year":"2025","journal-title":"J. Forensic Leg. Med."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Marin, A., Verdel, N., Milani\u010d, M., and Majaron, B. (2021). Noninvasive Monitoring of Dynamical Processes in Bruised Human Skin Using Diffuse Reflectance Spectroscopy and Pulsed Photothermal Radiometry. Sensors, 21.","DOI":"10.3390\/s21010302"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"010901","DOI":"10.1117\/1.JBO.29.1.010901","article-title":"Effect of skin color on optical properties and the implications for medical optical technologies: A review","volume":"29","author":"Setchfield","year":"2024","journal-title":"J. Biomed. Opt."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1191","DOI":"10.1111\/1556-4029.14294","article-title":"Detection of Inflicted Bruises by Alternate Light: Results of a Randomized Controlled Trial","volume":"65","author":"Scafide","year":"2020","journal-title":"J. Forensic Sci."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"e25844","DOI":"10.1016\/j.heliyon.2024.e25844","article-title":"Handheld hyperspectral imaging as a tool for the post-mortem interval estimation of human skeletal remains","volume":"10","author":"Schmidt","year":"2024","journal-title":"Heliyon"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/2\/78\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T14:03:21Z","timestamp":1770818601000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/2\/78"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,11]]},"references-count":38,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["jimaging12020078"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12020078","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,11]]}}}