Dual energy CT and deep learning for an automated volumetric segmentation of the major intracranial tissues: Feasibility and initial findings
Medical Physics · 2026
DOI: 10.1002/mp.70217 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical Physics, 2026. Verfasst von Veronica Fransson und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Hematology, Oncology and Radiation Physics, Skåne University Hospital, Lund, Sweden. Hauptthemen laut MEDLINE: Deep Learning, Tomography, X-Ray Computed, Brain, Image Processing, Computer-Assisted. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Crafoord Foundation, The Swedish Government, Region of Skåne research grant.
Abstract (Originalsprache)
Background
Magnetic resonance imaging (MRI) has traditionally been preferred over computed tomography (CT) for segmentation of intracranial structures due to its superior low contrast resolution. However, a reliable CT‐based segmentation could improve patient management when MRI is not practical. Despite advancements in CT imaging, such as enhanced tissue differentiation using virtual monoenergetic imaging (VMI) from dual energy CT, volumetric analysis remains underexplored.
Purpose
The aim was to evaluate the feasibility of using deep learning (DL) models for segmentation of gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF)—using virtual monoenergetic images (VMI).
Methods
The study included 26 patients (training/validation: 21, test: 5) who underwent brain imaging on a dual‐layer CT and a T1‐weighted MR scan. MR‐based segmentation of GM, WM, and CSF served as the ground truth for training and testing of the DL models. Models included a baseline U‐Net++ trained on 70 keV VMIs and several U‐Net and U‐Net++ extensions designed to leverage spectral information from multiple VMIs (50, 70, and 120 keV). Model performance was evaluated using Dice Similarity Coefficient (DSC) and volumetric accuracy.
Results
The U‐Net++ (Aug) model, using VMIs as augmentations of the input data, outperformed the baseline and other models with DSC 0.84, 0.77, and 0.88 for WM, GM, and CSF, respectively. The superiority was significant compared to several of the other models, and most notably compared to the baseline model with DSC of 0.81 for WM ( p = 0.002) and 0.75 for GM ( p = 0.002). U‐Net++ (Aug) had an average volumetric error of 12%, while U‐Net (Gated) had the lowest error at 10%.
Conclusions
This study demonstrates the feasibility of CT‐based segmentation of intracranial tissue using DL and VMI. The improved accuracy of the U‐Net++ (Aug) compared to the baseline model suggests that spectral information may enhance segmentation performance.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Hematology, Oncology and Radiation Physics, Skåne University Hospital, Lund, Sweden.
- Department of Translational Medicine, Medical Radiation Physics, Lund University, Malmö, Sweden.
- Computer Vision and Machine Learning, Centre for Mathematical Sciences, Lund University, Lund, Sweden.
- Department of Medical Imaging and Physiology, Skåne University Hospital, Lund, Sweden.
- Department of Clinical Sciences, Lund University, Lund, Sweden.
- GrayNumber Analytics, A/B, Copenhagen, Denmark.
Förderung
- Crafoord Foundation
- The Swedish Government
- Region of Skåne research grant
- Skåne University Hospital research grants
- VINNOVA
- AIDA
- Crafoordska Stiftelsen
Zitieren
APA
Fransson, V., Winzell, F., Ramgren, B., Christensen, S., Ydström, K., Arvidsson, I., Overgaard, N. C., Åström, K., Heyden, A., & Wassélius, J. (2026). Dual energy CT and deep learning for an automated volumetric segmentation of the major intracranial tissues: Feasibility and initial findings. Medical Physics. https://doi.org/10.1002/mp.70217
Vancouver
Fransson V, Winzell F, Ramgren B, Christensen S, Ydström K, Arvidsson I, et al. Dual energy CT and deep learning for an automated volumetric segmentation of the major intracranial tissues: Feasibility and initial findings. Medical Physics. 2026. doi:10.1002/mp.70217
BibTeX
@article{Fransson2026,
author = {Fransson, Veronica and Winzell, Filip and Ramgren, Birgitta and Christensen, Søren and Ydström, Kristina and Arvidsson, Ida and Overgaard, Niels Christian and Åström, Kalle and Heyden, Anders and Wassélius, Johan},
title = {Dual energy CT and deep learning for an automated volumetric segmentation of the major intracranial tissues: Feasibility and initial findings},
journal = {Medical Physics},
year = {2026},
doi = {10.1002/mp.70217}
}
EUVIMED