A new scheme of global feature management improved the performance and stability of radiomics model: a study based on CT images of acute brainstem infarction

Li, Yuefeng; Xie, Yuhang; Xu, Yijuan; Li, Guohai; Ju, Shenghong

doi:10.1007/s00330-022-08659-w

Cited by 2 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Radiomics was an emerging discipline that converted medical images into mineable data by extracting a large number of quantitative imaging features (Kumar et al 2012, Lambin et al 2012. The majority of contemporary radiomics research was focused on discovering novel imaging markers or building innovative predictive models to aid in disease diagnosis, prognosis, and prediction of response to specific treatments (Hao et al 2018, Gugliandolo et al 2021, Li et al 2022. Although prior research suggested that imaging features were associated with clinical endpoints in a variety of tumors, the complicated interactions between imaging features, clinical factors, and tumor biology remained largely unexplained (Grossmann et al 2017, Sun et al 2018, Tunali et al 2021.…”

Section: Introductionmentioning

confidence: 99%

Exploring the biological basis of CT imaging features in pancreatic neuroendocrine tumors: a two-center study

Xu,

Wu,

Shen

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective Medical imaging offered a non-invasive window to visualize tumors, with radiomics transforming these images into quantitative data for tumor phenotyping. However, the intricate web linking imaging features, clinical endpoints, and tumor biology was mostly uncharted. This study aimed to unravel the connections between CT imaging features and clinical characteristics, including tumor histopathological grading, clinical stage, and endocrine symptoms, alongside immunohistochemical markers of tumor cell growth, such as the Ki-67 index and nuclear mitosis rate.Approach We conducted a retrospective analysis of data from 137 patients with pancreatic neuroendocrine tumors who had undergone contrast-enhanced CT scans across two institutions. Our study focused on three clinical factors: pathological grade, clinical stage, and endocrine symptom status, in addition to two immunohistochemical markers: the Ki-67 index and the rate of nuclear mitosis. We computed both predefined (2D and 3D) and learning-based features (via sparse autoencoder, or SAE) from the scans. To unearth the relationships between imaging features, clinical factors, and immunohistochemical markers, we employed the Spearman rank correlation along with the Benjamini-Hochberg method. Furthermore, we developed and validated radiomics signatures to foresee these clinical factors.Main results The 3D imaging features showed the strongest relationships with clinical factors and immunohistochemical markers. For the association with pathological grade, the mean absolute value of the correlation coefficient (CC) of 2D, SAE, and 3D features was 0.3318±0.1196, 0.2149±0.0361, and 0.4189±0.0882, respectively. While for the association with Ki-67 index and rate of nuclear mitosis, the 3D features also showed higher correlations, with CC as 0.4053±0.0786 and 0.4061±0.0806. In addition, the 3D feature-based signatures showed optimal performance in clinical factor prediction.Significance We found relationships between imaging features, clinical factors, and immunohistochemical markers. The 3D features showed higher relationships with clinical factors and immunohistochemical markers.

show abstract