Robustness of radiomics features of virtual unenhanced and virtual monoenergetic images in dual-energy CT among different imaging platforms and potential role of CT number variability.
Jingyu ZhongZilai PanYong ChenLingyun WangYihan XiaLan WangJianying LiWei LuXiaomeng ShiJianxing FengFuhua YanHuan ZhangWeiwu YaoPublished in: Insights into imaging (2023)
The majority of DECT radiomics features were non-reproducible. The differences in CT number were considered as an indicator of inter-platform DECT radiomics variation. Critical relevance statement: The majority of radiomics features extracted from the VUE images and the VMI70keV were non-reproducible among platforms, while synchronizing energy levels of VMI to reduce the CT number value variability may be a potential way to mitigate radiomics instability.
Keyphrases
- dual energy
- contrast enhanced
- computed tomography
- image quality
- lymph node metastasis
- magnetic resonance imaging
- magnetic resonance
- deep learning
- positron emission tomography
- squamous cell carcinoma
- high resolution
- human health
- climate change
- convolutional neural network
- risk assessment
- high throughput
- machine learning