Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
36
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
4
4
1

Relationship

1
8

Authors

Journals

citations
Cited by 53 publications
(37 citation statements)
references
References 34 publications
1
36
0
Order By: Relevance
“…In a retrospective study on a fairly large cohort of patients (n = 545), PET texture features were able to differentiate between primary and metastatic lung lesions, whereas CT features were not [48]. PET radiomic features were also found to correlate with histological subtype (specifically adenocarcinoma vs. squamous cell carcinoma) in [21,44], whereas, in [49,52], radiomics signatures based on CT texture features were significantly associated with tumor histology.…”
Section: Classification Between Primary and Metastatic Lesions; Histomentioning
confidence: 97%
See 1 more Smart Citation
“…In a retrospective study on a fairly large cohort of patients (n = 545), PET texture features were able to differentiate between primary and metastatic lung lesions, whereas CT features were not [48]. PET radiomic features were also found to correlate with histological subtype (specifically adenocarcinoma vs. squamous cell carcinoma) in [21,44], whereas, in [49,52], radiomics signatures based on CT texture features were significantly associated with tumor histology.…”
Section: Classification Between Primary and Metastatic Lesions; Histomentioning
confidence: 97%
“…Feature selection consists of retaining a subset of the original features by selecting the most discriminative ones. This is crucial in radiomics, for some image features tend to be strongly correlated with one another [44]. Approaches to feature selection come in different varieties, such as correlation-based selection, reduction based on mutual information gain, recursive elimination, and Lasso regularization (see [45] for a recent review on this subject).…”
Section: Post Processingmentioning
confidence: 99%
“…In this study, the multivariate analysis showed that wMTV and wTLG were signi cant independent prognostic factors for melanoma-speci c survival, even after adjusting for clinical prognostic factors in patients with metastatic CMM. wMTV and wTLG, which quantify the overall tumor burden and represent information about both tumor volume and metabolic activity, respectively [11,26], have been investigated in many tumors, such as nasopharyngeal carcinoma [27], lymphoma [28], breast cancer [29] and lung cancer [30,31]. In this study, wMTV and wTLG were the best predictive factors for MSS but not DFS.…”
Section: Discussionmentioning
confidence: 76%
“…Some studies also found that there was a certain correlation between the radiomic features and PET metabolic parameters. A study on non-small-cell lung cancer based on PET/CT found that some texture features like volume of the lesion were highly positively correlated with MTV, the CT average density was moderately positively correlated with SUV, and CT kurtosis was moderately positively correlated with MTV (27). However, another PET/CT study on non-small-cell lung cancer showed that texture and shape features had stronger correlations with MTV and GTV compared to SUV measurements (28).…”
Section: Feature Type Formulamentioning
confidence: 99%