Exploring the variability of radiomic features of lung cancer lesions on unenhanced and contrast-enhanced chest CT imaging
| Autor: | Giovanni Battista Meloni, Enrico Sanna, A. Poggiu, Rino Aldo Montella, M. Tamponi, Nicola Sverzellati, Maurizio Conti, Domenico Gabriele, Paola Crivelli, Fabrizio Sanna, P. Marini |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
medicine.medical_specialty
Lung Neoplasms media_common.quotation_subject Biophysics Chest ct General Physics and Astronomy Silhouette Lesion Correlation Carcinoma Non-Small-Cell Lung Humans Medicine Contrast (vision) Radiology Nuclear Medicine and imaging Lung cancer media_common Phantoms Imaging business.industry General Medicine medicine.disease Contrast medium Feature (computer vision) Radiology medicine.symptom Tomography X-Ray Computed business |
| Zdroj: | Physica Medica. 82:321-331 |
| ISSN: | 1120-1797 |
| DOI: | 10.1016/j.ejmp.2021.02.014 |
| Popis: | The aim of this methods work is to explore the different behavior of radiomic features resulting by using or not the contrast medium in chest CT imaging of non-small cell lung cancer.Chest CT scans, unenhanced and contrast-enhanced, of 17 patients were selected from images collected as part of the staging process. The major T1-T3 lesion was contoured through a semi-automatic approach. These lesions formed the lesion phantoms to study features behavior. The stability of 94 features of the 3D-Slicer package Radiomics was analyzed. Feature discrimination power was quantified by means of Gini's coefficient. Correlation between distance matrices was evaluated through Mantel statistic. Heatmap, cluster and silhouette plots were applied to find well-structured partitions of lesions.The Gini's coefficient evidenced a low discrimination power,0.05, for four features and a large discrimination power, around 0.8, for five features. About 90% of features was affected by the contrast medium, masking tumor lesions variability; thirteen features only were found stable. On 8178 combinations of stable features, only one group of four features produced the same partition of lesions with the silhouette width greater than 0.51, both on unenhanced and contrast-enhanced images.Gini's coefficient highlighted the features discrimination power in both CT series. Many features were sensitive to the use of the contrast medium, masking the lesions intrinsic variability. Four stable features produced, on both series, the same partition of cancer lesions with reasonable structure; this may merit being objects of further validation studies and interpretative investigations. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect