To evaluate the correlation between CT-derived quantitative texture features,
histologic subtypes (WHO) and staging (Masaoka,
TNM) in patients with thymic neoplasms.
Methods & Materials
In this retrospective study,
CT scans of patients with histologically confirmed and categorized thymic neoplasms were extracted from the PACS and reformatted to a fixed slice thickness of 2 mm and an in-plane resolution of 1 x 1 mm².
Tumors were manually segmented using the open source software 3D Slicer.
Either using the original image or applying filters (Laplace of Gaussian filter,
3D-based texture features of 7 major categories were calculated (First Order Statistics,
Gray Level Cooccurence Matrix,
CT scans of 15 Patients (4 female patients,
mean age 51±12 years,
range 30-69 years) could be included for this preliminary analysis.
Subcategories of thymic neoplasms were distributed as follows: WHO A: 2,
C: 3; Masaoka: I: 2,
IV: 4; TNM T-Stage: I: 8,
Of the initial 1316 features,
352 were excluded due to poor to moderate intra- or interreader agreement (Figure 2).
Correlation-based attribute selection resulted...
Preliminary results indicate that machine learning-based classification based on quantitative,
CT-derived texture features may be able to correctly predict thymic neoplasm subtypes.
This system could potentially be used to create radiomic signatures as biomarkers.
(2013) Thymic neoplasm: a rare disease with a complex clinical presentation.
J Thorac Dis.,
(2014) 3D Slicer: a platform for subject-specific image analysis,
and clinical support. Intraoperative Imaging Image-Guided Therapy,
Editor 3(19):277–289 ISBN: 978-1-4614-7656-6 (Print) 978-1-4614-7657-3 (Online)
 van Griehuysen,
et al (2017).
Computational Radiomics System to Decode the Radiographic Phenotype.
 Shrout PE,
Intraclass correlations: uses in assessing rater reliability....
Institute for Diagnostic und Interventional Radiology
University Hospital Zurich