Robustness of radiomic features in CT images with different slice thickness, comparing liver tumour and muscle
| Autor: | Matthew Hoare, Eva M. Serrao, Leonardo Rundo, Evis Sala, Andrew B. Gill, Lorena Escudero Sanchez |
|---|---|
| Přispěvatelé: | Escudero Sanchez, Lorena [0000-0003-3464-9206], Rundo, Leonardo [0000-0003-3341-5483], Gill, Andrew [0000-0002-9287-9563], Hoare, Matthew [0000-0001-5990-9604], Sala, Evis [0000-0002-5518-9360], Apollo - University of Cambridge Repository |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
639/705/1042
Carcinoma Hepatocellular Computer science Slice thickness Science 692/4028/67/1857 Tumour heterogeneity Computed tomography 631/67/2329 631/67/1857 692/4028/67/1504/1610 Article 030218 nuclear medicine & medical imaging Tumour biomarkers 03 medical and health sciences 0302 clinical medicine 692/4028/67/2321 Robustness (computer science) 631/67/2321 medicine Humans 692/4028/67/2329 Radiometry Retrospective Studies 631/67/1504/1610 Multidisciplinary medicine.diagnostic_test Muscles Computational science Liver Neoplasms Therapy response Liver Feature (computer vision) Homogeneous 030220 oncology & carcinogenesis 639/166/985 Medicine Cancer imaging Tumour classification Tomography X-Ray Computed Liver cancer Biomedical engineering |
| Zdroj: | Scientific Reports Scientific Reports, Vol 11, Iss 1, Pp 1-15 (2021) |
| ISSN: | 2045-2322 |
| Popis: | Radiomic image features are becoming a promising non-invasive method to obtain quantitative measurements for tumour classification and therapy response assessment in oncological research. However, despite its increasingly established application, there is a need for standardisation criteria and further validation of feature robustness with respect to imaging acquisition parameters. In this paper, the robustness of radiomic features extracted from computed tomography (CT) images is evaluated for liver tumour and muscle, comparing the values of the features in images reconstructed with two different slice thicknesses of 2.0 mm and 5.0 mm. Novel approaches are presented to address the intrinsic dependencies of texture radiomic features, choosing the optimal number of grey levels and correcting for the dependency on volume. With the optimal values and corrections, feature values are compared across thicknesses to identify reproducible features. Normalisation using muscle regions is also described as an alternative approach. With either method, a large fraction of features (75–90%) was found to be highly robust ( |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink