EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Electron Density and Effective Atomic Number as Quantitative Biomarkers for Differentiating Malignant Brain Tumors: An Exploratory Study with Machine Learning

Tsubasa Nakano, Daisuke Hirahara iD, Tomohito Hasegawa, Kiyohisa Kamimura iD, Masanori Nakajo, Junki Kamizono iD, Koji Takumi iD, Masatoyo Nakajo, Fumitaka Ejima iD, Ryota Nakanosono, Ryoji Yamagishi iD, Fumiko Kanzaki iD und 9 weitere

Tomography · 2025

DOI: 10.3390/tomography11110120 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Tomography, 2025. Verfasst von Tsubasa Nakano und 20 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Kagoshima University Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima 890-8544, Japan. Hauptthemen laut MEDLINE: Brain Neoplasms, Machine Learning, Tomography, X-Ray Computed, Glioblastoma. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

The potential use of electron density (ED) and effective atomic number (Zeff) derived from dual-energy computed tomography (DECT) as novel quantitative imaging biomarkers for differentiating malignant brain tumors was investigated.

Methods

Data pertaining to 136 patients with a pathological diagnosis of brain metastasis (BM), glioblastoma, and primary central nervous system lymphoma (PCNSL) were retrospectively reviewed. The 10th percentile, mean and 90th percentile values of conventional 120-kVp CT value (CTconv), ED, Zeff, and relative apparent diffusion coefficient derived from diffusion-weighted magnetic resonance imaging (rADC: ADC of lesion divided by ADC of normal-appearing white matter) within the contrast-enhanced tumor region were compared across the three groups. Furthermore, machine learning (ML)-based diagnostic models were developed to maximize diagnostic performance for each tumor classification using the indices of DECT parameters and rADC. Machine learning models were developed using the AutoGluon-Tabular framework with rigorous patient-level data splitting into training (60%), validation (20%), and independent test sets (20%).

Results

The 10th percentile of Zeff was significantly higher in glioblastomas than in BMs (p = 0.02), and it was the only index with a significant difference between BMs and glioblastomas. In the comparisons including PCNSLs, all indices of CTconv, Zeff, and rADC exhibited significant differences (p < 0.001–0.02). DECT-based ML models exhibited high area under the receiver operating characteristic curves (AUC) for all pairwise differentiations (BMs vs. Glioblastomas: AUC = 0.83; BMs vs. PCNSLs: AUC = 0.91; Glioblastomas vs. PCNSLs: AUC = 0.82). Combined models of DECT and rADC demonstrated excellent diagnostic performance between BMs and PCNSLs (AUC = 1) and between Glioblastomas and PCNSLs (AUC = 0.93).

Conclusion

This study suggested the potential of DECT-derived ED and Zeff as novel quantitative imaging biomarkers for differentiating malignant brain tumors.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Brain NeoplasmsMachine LearningTomography, X-Ray ComputedGlioblastomaHumansFemaleMaleRetrospective StudiesMiddle AgedDiagnosis, DifferentialAgedAdultDiffusion Magnetic Resonance ImagingBiomarkers, TumorLymphoma

Stichwörter der Autor:innen

brain metastasisdual-energy CTeffective atomic numberelectron densityglioblastomaprimary central nervous system lymphoma

Substanzen

Biomarkers, Tumor

Autor:innen und Institutionen

  • Department of Radiology, Kagoshima University Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima 890-8544, Japan.
  • Department of Management Planning Division, Harada Academy, 2-54-4 Higashitaniyama, Kagoshima 890-0113, Japan.
  • Department of Advanced Radiological Imaging, Kagoshima University Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima 890-8544, Japan.
  • Department of Neurosurgery, Kagoshima University Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima 890-8544, Japan.
  • Department of Pathology, Kagoshima University Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima 890-8544, Japan.
  • Philips Japan Ltd., 1-3-1 Azabudai, Minatoku, Tokyo 106-0041, Japan.

ORCID-Profile: Daisuke Hirahara, Kiyohisa Kamimura, Junki Kamizono, Koji Takumi, Fumitaka Ejima, Ryoji Yamagishi, Fumiko Kanzaki, Jihun Kwon, Gregor Pahn, Ko Higuchi, Takashi Yoshiura

Zitieren

APA

Nakano, T., Hirahara, D., Hasegawa, T., Kamimura, K., Nakajo, M., Kamizono, J., Takumi, K., Nakajo, M., Ejima, F., Nakanosono, R., Yamagishi, R., Kanzaki, F., Muraoka, H., Higa, N., Yonezawa, H., Kitazono, I., Kwon, J., Pahn, G., Langzam, E., …, & Yoshiura, T. (2025). Electron Density and Effective Atomic Number as Quantitative Biomarkers for Differentiating Malignant Brain Tumors: An Exploratory Study with Machine Learning. Tomography. https://doi.org/10.3390/tomography11110120

Vancouver

Nakano T, Hirahara D, Hasegawa T, Kamimura K, Nakajo M, Kamizono J, et al. Electron Density and Effective Atomic Number as Quantitative Biomarkers for Differentiating Malignant Brain Tumors: An Exploratory Study with Machine Learning. Tomography. 2025. doi:10.3390/tomography11110120

BibTeX
@article{Nakano2025,
  author = {Nakano, Tsubasa and Hirahara, Daisuke and Hasegawa, Tomohito and Kamimura, Kiyohisa and Nakajo, Masanori and Kamizono, Junki and Takumi, Koji and Nakajo, Masatoyo and Ejima, Fumitaka and Nakanosono, Ryota and Yamagishi, Ryoji and Kanzaki, Fumiko and Muraoka, Hiroki and Higa, Nayuta and Yonezawa, Hajime and Kitazono, Ikumi and Kwon, Jihun and Pahn, Gregor and Langzam, Eran and Higuchi, Ko and Yoshiura, Takashi},
  title = {Electron Density and Effective Atomic Number as Quantitative Biomarkers for Differentiating Malignant Brain Tumors: An Exploratory Study with Machine Learning},
  journal = {Tomography},
  year = {2025},
  doi = {10.3390/tomography11110120}
}
Kostenlos starten →