Quantitative MRI-based radiomics analysis identifies blood flow feature associated to overall survival for rectal cancer patients
Knuth, Franziska; Tohidinezhad, Fariba; Winter, Rene Mario; Bakke, Kine Mari; Negård, Anne; Holmedal, Stein Harald; Ree, Anne Hansen; Meltzer, Sebastian; Traverso, Alberto; Redalen, Kathrine Røe
Journal article, Peer reviewed
Published version
Permanent lenke
https://hdl.handle.net/11250/3164535Utgivelsesdato
2024Metadata
Vis full innførselSamlinger
- Institutt for fysikk [2770]
- Publikasjoner fra CRIStin - NTNU [39093]
Sammendrag
Radiomics objectively quantifies image information through numerical metrics known as features. In this study, we investigated the stability of magnetic resonance imaging (MRI)-based radiomics features in rectal cancer using both anatomical MRI and quantitative MRI (qMRI), when different methods to define the tumor volume were used. Second, we evaluated the prognostic value of stable features associated to 5-year progression-free survival (PFS) and overall survival (OS). On a 1.5 T MRI scanner, 81 patients underwent diagnostic MRI, an extended diffusion-weighted sequence with calculation of the apparent diffusion coefficient (ADC) and a multiecho dynamic contrast sequence generating both dynamic contrast-enhanced and dynamic susceptibility contrast (DSC) MR, allowing quantification of Ktrans, blood flow (BF) and area under the DSC curve (AUC). Radiomic features were extracted from T2w images and from ADC, Ktrans, BF and AUC maps. Tumor volumes were defined with three methods; machine learning, deep learning and manual delineations. The interclass correlation coefficient (ICC) assessed the stability of features. Internal validation was performed on 1000 bootstrap resamples in terms of discrimination, calibration and decisional benefit. For each combination of image and volume definition, 94 features were extracted. Features from qMRI contained higher prognostic potential than features from anatomical MRI. When stable features (> 90% ICC) were compared with clinical parameters, qMRI features demonstrated the best prognostic potential. A feature extracted from the DSC MRI parameter BF was associated with both PFS (p = 0.004) and OS (p = 0.004). In summary, stable qMRI-based radiomics features was identified, in particular, a feature based on BF from DSC MRI was associated with both PFS and OS.