Abstract
Sphenoid sinus fluid is considered a supportive indicator of drowning in forensic medicine, but traditional manual assessment on postmortem computed tomography (PMCT) is labor-intensive and observer-dependent. Efficient, reproducible methods for quantitative evaluation are needed in forensic practice. This study developed deep learning–based approaches for the automated segmentation and volumetric estimation of sphenoid sinus fluid using PMCT images from 165 autopsy-confirmed drowning cases. Three U-Net–based models (2D, 2.5D, and 3D) were developed and evaluated against manually annotated reference standards. In the test dataset, mean Dice coefficients were 0.866 (2D), 0.869 (2.5D), and 0.798 (3D). Volumetric estimates showed no statistically significant differences from the reference standard, with strong correlations (Spearman’s ρ = 0.976–0.988). Mean absolute errors were 0.218 (2D), 0.206 (2.5D), and 0.310 ml (3D). The 2.5D approach provided the most balanced performance between segmentation accuracy and volumetric estimation. These findings demonstrate the feasibility of automated PMCT-based segmentation and volumetric quantification of sphenoid sinus fluid, enabling quantitative assessment on PMCT images prior to autopsy.
Similar content being viewed by others
Data availability
The datasets generated and/or analyzed during the current study are available from the corresponding author upon reasonable request, except for postmortem CT imaging data, which cannot be publicly shared owing to legal and ethical restrictions.
References
Tyr, A., Heldring, N., Winskog, C. & Zilg, B. Diagnosing fatal drownings: A review of the postmortem findings. Forensic Sci. Int. 364, 112251 (2024).
Piette, M. H. A. & De Letter, E. A. Drowning: still a difficult autopsy diagnosis. Forensic Sci. Int. 163, 1–9 (2006).
Lin, C. Y. et al. Diatomological investigation in sphenoid sinus fluid and lung tissue from cases of suspected drowning. Forensic Sci. Int. 244, 111–115 (2014).
Hayakawa, A., Terazawa, K., Matoba, K., Horioka, K. & Fukunaga, T. Diagnosis of drowning: Electrolytes and total protein in sphenoid sinus liquid. Forensic Sci. Int. 273, 102–105 (2017).
Dedouit, F. et al. The current state of forensic imaging–post mortem imaging. Int. J. Leg. Med. 139, 1141–1159 (2025).
Mendes, L. F., Lago, L. P., Egger, E. & Schmid, J. Characterization of fluid in facial sinuses on post-mortem CT in case of death by drowning. Int. J. Leg. Med. 139, 2233–2240 (2025).
Heo, J. H. et al. The significance of evaluating sphenoid sinus fluid by postmortem computed tomography in cases of drowning. J. Forensic Leg. Med. 97, 102551 (2023).
Kim, Y. et al. Application of deep learning for detecting implants in computed tomography scout images with multi-institution and multi-vendor for personal identification. Sci. Justice. 65, 101315 (2025).
Gu, G. et al. Automated diatom detection in forensic drowning diagnosis using a single shot multibox detector with plump receptive field. Appl. Soft Comput. 122, 108885 (2022).
Ebert, L. et al. Image segmentation of post-mortem computed tomography data in forensic imaging: Methods and applications. Forensic Imaging. 28, 200483 (2022).
Song, D. et al. Comparison of segmentation performance of cnn, vision transformers, and hybrid networks for paranasal sinuses with sinusitis on CT images. Sci. Rep. 15, 32087 (2025).
Schneppe, S., Dokter, M. & Bockholdt, B. Macromorphological findings in cases of death in water: a critical view on drowning signs. Int. J. Leg. Med. 135, 281–291 (2021).
Tyr, A., Zilg, B., Gelius, T., Mollby, R. & Heldring, N. Postmortem CT analysis of paranasal sinuses using an experimental model of drowning. Int. J. Leg. Med. 138, 1401–1409 (2024).
Kakimoto, Y. et al. Assessment of maxillary sinus fluid volume for postmortem diagnosis of drowning. Radiography 30, 308–312 (2024).
Vaid, S. & Vaid, N. Normal anatomy and anatomic variants of the paranasal sinuses on computed tomography. Neuroimag Clin. N Am. 25, 527–548 (2015).
Kawazoe, Y. et al. A simple method for semi-automatic readjustment for positioning in post-mortem head computed tomography imaging. J. Forensic Radiol. Imaging. 16, 57–64 (2019).
Dobay, A. et al. Potential use of deep learning techniques for postmortem imaging. Forensic Sci. Med. Pathol. 16, 671–679 (2020).
Zhang, Y., Liao, Q., Ding, L. & Zhang, J. Bridging 2D and 3D segmentation networks for computation-efficient volumetric medical image segmentation: An empirical study of 2.5D solutions. Comput. Med. Imaging Graph. 99, 102088 (2022).
Acknowledgements
This work was supported by the National Forensic Service (NFS2025MED01), Ministry of the Interior and Safety, Republic of Korea.
Funding
This work was supported by the National Forensic Service (NFS2025MED01), Ministry of the Interior and Safety, Republic of Korea.
Author information
Authors and Affiliations
Contributions
Jin-Haeng Heo: conceptualization and writing—original draft preparation. Min-Jae Kim, Seon Jung Jang and Junghye Lee: data analysis. Sang-Beom Im: data curation. Sookyoung Lee and Joo-Young Na: writing—review and editing. Yeji Kim: model development. Yongsu Yoon and Jeong-hwa Kwon: supervision and project administration.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Heo, JH., Kim, MJ., Jang, S.J. et al. Multi-dimensional deep learning–based segmentation and volumetric assessment of sphenoid sinus fluid on postmortem CT in drowning cases. Sci Rep (2026). https://doi.org/10.1038/s41598-026-44094-3
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-44094-3
