EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Dual-Level Augmentation Radiomics Analysis for Multisequence MRI Meningioma Grading

Zongyou Cai, Lun M Wong iD, Ye Heng Wong, Hok-Lam Lee, Kam-Yau Li iD, Tiffany Y So iD

Cancers · 17.11.2023 · 15 (22) · 5459

DOI: 10.3390/cancers15225459 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cancers, online erschienen am 17.11.2023. Verfasst von Zongyou Cai und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Imaging and Interventional Radiology, The Chinese University of Hong Kong, Hong Kong SAR, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Preoperative, noninvasive prediction of meningioma grade is important for therapeutic planning and decision making. In this study, we propose a dual-level augmentation strategy incorporating image-level augmentation (IA) and feature-level augmentation (FA) to tackle class imbalance and improve the predictive performance of radiomics for meningioma grading on Magnetic Resonance Imaging (MRI).

Methods

This study recruited 160 consecutive patients with pathologically proven meningioma (129 low-grade (WHO grade I) tumors; 31 high-grade (WHO grade II and III) tumors) with preoperative multisequence MRI imaging. A dual-level augmentation strategy combining IA and FA was applied and evaluated in 100 repetitions in 3-, 5-, and 10-fold cross-validation.

Results

The best area under the receiver operating characteristics curve of our method in 100 repetitions was ≥0.78 in all cross-validations. The corresponding cross-validation sensitivities (cross-validation specificity) were 0.72 (0.69), 0.76 (0.71), and 0.63 (0.82) in 3-, 5-, and 10-fold cross-validation, respectively. The proposed method achieved significantly better performance and distribution of results, outperforming single-level augmentation (IA or FA) or no augmentation in each cross-validation.

Conclusions

The dual-level augmentation strategy using IA and FA significantly improves the performance of the radiomics model for meningioma grading on MRI, allowing better radiomics-based preoperative stratification and individualized treatment.

Schlagwörter

Stichwörter der Autor:innen

data augmentationmachine learningmagnetic resonance imagingmeningiomaradiomics

Autor:innen und Institutionen

  • Department of Imaging and Interventional Radiology, The Chinese University of Hong Kong, Hong Kong SAR, China.

ORCID-Profile: Lun M Wong, Kam-Yau Li, Tiffany Y So

Zitieren

APA

Cai, Z., Wong, L. M., Wong, Y. H., Lee, H. L., Li, K. Y., & So, T. Y. (2023). Dual-Level Augmentation Radiomics Analysis for Multisequence MRI Meningioma Grading. Cancers, 15(22), 5459. https://doi.org/10.3390/cancers15225459

Vancouver

Cai Z, Wong LM, Wong YH, Lee HL, Li KY, So TY. Dual-Level Augmentation Radiomics Analysis for Multisequence MRI Meningioma Grading. Cancers. 2023;15(22):5459. doi:10.3390/cancers15225459

BibTeX
@article{Cai2023,
  author = {Cai, Zongyou and Wong, Lun M and Wong, Ye Heng and Lee, Hok-Lam and Li, Kam-Yau and So, Tiffany Y},
  title = {Dual-Level Augmentation Radiomics Analysis for Multisequence MRI Meningioma Grading},
  journal = {Cancers},
  year = {2023},
  volume = {15},
  number = {22},
  pages = {5459},
  doi = {10.3390/cancers15225459}
}
Kostenlos starten →