2019
DOI: 10.1109/access.2019.2903682
|View full text |Cite
|
Sign up to set email alerts
|

Semantic Features Prediction for Pulmonary Nodule Diagnosis Based on Online Streaming Feature Selection

Abstract: Early diagnosis significantly improves the survival rate in lung carcinoma patients. This study attempts to construct a predictive network between the computational features and semantic features of pulmonary nodules using online feature selection and causal structure learning. In this paper, we exploit the causal discovery based on the streaming feature algorithm and causal discovery with symmetrical uncertainty based on the streaming feature algorithm. Different from the traditional learning methods that usu… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
5
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
4
1

Relationship

0
5

Authors

Journals

citations
Cited by 10 publications
(5 citation statements)
references
References 25 publications
0
5
0
Order By: Relevance
“…Moreover, since the Ref. 33 only gathers radiomics features in feature extraction, its accuracy is not as good as that of the method proposed by this article. Therefore, the feature set construction method based on CNN and radiomics features can reflect information in CT images in a more comprehensive way.…”
Section: Methodsmentioning
confidence: 86%
See 1 more Smart Citation
“…Moreover, since the Ref. 33 only gathers radiomics features in feature extraction, its accuracy is not as good as that of the method proposed by this article. Therefore, the feature set construction method based on CNN and radiomics features can reflect information in CT images in a more comprehensive way.…”
Section: Methodsmentioning
confidence: 86%
“…Reference 32 proposes a multilevel transfer learning method to assess the classification performance of pulmonary nodules, which extract features construct a neural network of each CT semantics, and input features to first‐order transfer network to explore which attribute can support cancer diagnosis. Reference 33 obtains feature sets of seven CT signs and malignancy degrees by extracting and selecting radiomics features and then feed them into classifiers to get lung nodule malignancy level. In Ref.…”
Section: Methodsmentioning
confidence: 99%
“…The main aim of this paper is to reduce the correlation between data features when choosing the best features. The objective function is defined in Equation (19). Then, in Equation (20), the correlation between two data features Fea 1 and Fea 2 is represented, where i denoting the set of data features.…”
Section: Objective Functionmentioning
confidence: 99%
“…The feature extraction is the initial stage of preprocessing as it helps in extracting the data features. [15][16][17][18][19] The FS assists in deducing the dimensionality of the data features. The FS is also referred as subset selection, which makes use of the machine learning techniques to select the ideal data applicable for the learning algorithm.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation