2020
DOI: 10.1038/s41598-020-76989-0
|View full text |Cite
|
Sign up to set email alerts
|

Impact of different scanners and acquisition parameters on robustness of MR radiomics features based on women’s cervix

Abstract: MR Radiomics based on cervical lesions from one single scanner has achieved promising results. However, it is a challenge to achieve clinical translation. Considering multi-scanners and non-uniform scanning parameters from different centers in a real-world medical scenario, we should first identify the influence of such conditions on the robustness of MR radiomics features (RFs) based on the female cervix. In this study, 9 healthy female volunteers were enrolled and 3 kiwis were selected as references. Each of… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

1
21
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
7

Relationship

0
7

Authors

Journals

citations
Cited by 17 publications
(22 citation statements)
references
References 39 publications
1
21
0
Order By: Relevance
“…The main novelty of the current study lies in its multicenter aspect. Although previous studies have already identified acquisition parameters [13,15,16], segmentation [19], and post-processing methods [15,18] as factors affecting feature reproducibility, these studies have so far mainly been performed on non-MRI data or in small patient cohorts or phantoms. The extent to which these effects influence feature reproducibility and may obscure correlations with common clinical outcomes in a representative "real life" clinical cohort of MRI data acquired at various institutions has not been previously reported.…”
Section: Discussionmentioning
confidence: 99%
See 2 more Smart Citations
“…The main novelty of the current study lies in its multicenter aspect. Although previous studies have already identified acquisition parameters [13,15,16], segmentation [19], and post-processing methods [15,18] as factors affecting feature reproducibility, these studies have so far mainly been performed on non-MRI data or in small patient cohorts or phantoms. The extent to which these effects influence feature reproducibility and may obscure correlations with common clinical outcomes in a representative "real life" clinical cohort of MRI data acquired at various institutions has not been previously reported.…”
Section: Discussionmentioning
confidence: 99%
“…Even in controlled prospective study designs with harmonized acquisition protocols, variation in ADC can still be a limiting factor as coefficients of variation range as high as 4–37% depending on the measured organ [ 23 , 24 ]. Differences in acquisition settings have previously also been shown to substantially reduce inter- and intra-scanner reproducibility of T2W-MRI radiomics features, with particularly poor results for higher-order features [ 13 , 16 ].…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…To extract stable features, image preprocessing is essential to exclude the influence of different machines, scanning parameters, reconstruction algorithms, and noise. 54 , 55 The procedures of image preprocessing usually include resampling, standardization, normalization, smoothing, and filtering ( Figure 1 ).…”
Section: Workflowmentioning
confidence: 99%
“…The problem is not unique to CT, as magnetic resonance (MR) imaging intensity is also highly dependent on manufacturer, sequence, and acquisition parameters 5 . A recent study of cervix MR showed that few MR features were robust across scanners and acquisition parameters, while another study of brain MR demonstrated that MR-derived radiomic features vary widely with pulse sequence 6 , 7 .…”
Section: Introductionmentioning
confidence: 99%