Space-Frequency Based Computed TomographyTexture Analysis is more Robust than ImageDomain Features for Radiomics and AIApplications
European Congress Of Radiology, Vienna, Avusturya, 26 Şubat - 02 Mart 2026, ss.1-5, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Doi Numarası: 10.26044/ecr2025/c-19136
- Basıldığı Şehir: Vienna
- Basıldığı Ülke: Avusturya
- Sayfa Sayıları: ss.1-5
- Dokuz Eylül Üniversitesi Adresli: Evet
Özet
AI and radiomics-based analyses tend to improve global health equity. Thus, reliability is a key factor in the sustainability of their services. Computed Tomography Texture Analysis (CTTA) provides effective results in diagnosis, treatment, and follow-up for various clinical conditions. Unfortunately, it is also shown that CTTA has low repeatability, and reproducibility, and is highly dependent on modality, acquisition, and reconstruction parameters.
For instance, The Credence Cartridge Radiomics (CCR) phantom is a specially designed tool used to evaluate the robustness and variability of radiomics features in computed tomography (CT) imaging (1). It consists of multiple cartridges made from different materials, enabling researchers to simulate a wide range of tissue textures and densities. Studies on the CCR phantom highlight the importance of understanding and controlling variability in radiomics texture features caused by differences in CT imaging and scanner types [2-6].
One of the shortcomings of existing studies is the use of image and/or frequency domain textures. However, recent extensive studies, such as the Image Biomarker Standardisation Initiative (IBSI) [7-8], point to the importance of space-frequency information.
Accordingly, this study focuses on space-frequency-based textures (SFBTs) and analyzes their robustness, repeatability, and reproducibility.