Military Medical Research

Table 2 Applications of radiomics-based tumor staging

From: Artificial intelligence-driven radiomics study in cancer: the role of feature engineering and modeling

Image modality	Number of patients	Cancer	Target	Number of radiomics features	Commercial or open-source software	Method	References
MRI	127	HNSCC	Preoperative staging (stage I–II from stage III–IV)	6	ITK-SNAP, Matlab, R, SPSS	ML: LASSO, LR SM: Mann–Whitney U test, McNemar test	[17]
CT	154	Esophageal cancer	Preoperative staging	10	Matlab, R	ML: LASSO, fivefold CV SM: Mann–Whitney U test, DeLong test, Net reclassification improvement, Chi-square test, ICC	[18]
CT	494	Primary colorectal cancer	Preoperative staging	16	Matkab, SPSS	ML: LASSO, LR SM: Mann–Whitney U test, DeLong test	[19]
US	157	Bladder cancer	Tumor staging	30	ITK-SNAP, Intelligence Foundry, SPSS	ML: SVM-RFE, L1-regularized LR, Random forests, DT, Naive Bayes, KNN, Bagging, Extremely RF, AdaBoost, Gradient boosting regression trees, fivefold CV SM: t-test, Chi-square test, Z-score, Spearman correlation analysis, Mann–Whitney U test	[20]

MRI magnetic resonance imaging, CT computed tomography, US ultrasonography, ML machine learning, SM statistical method, HNSCC head and neck squamous cell carcinoma, LASSO least absolute shrinkage and selection operator, LR logistic regression, CV cross validation, ICC intraclass correlation coefficients, SVM support vector machine, RFE recursive feature elimination, DT decision tree, KNN K-nearest neighbors, RF random forest, AdaBoost adaptive boosting

Back to article page

ISSN: 2054-9369

Contact us

Submission enquiries: Access here and click Contact Us
General enquiries: info@biomedcentral.com