TY - JOUR
T1 - Radiomics-Based Classification of Tumor and Healthy Liver on Computed Tomography Images
AU - Zossou, Vincent Béni Sèna
AU - Gnangnon, Freddy Houéhanou Rodrigue
AU - Biaou, Olivier
AU - de Vathaire, Florent
AU - Allodji, Rodrigue S.
AU - Ezin, Eugène C.
N1 - Publisher Copyright:
© 2024 by the authors.
PY - 2024/3/1
Y1 - 2024/3/1
N2 - Liver malignancies, particularly hepatocellular carcinoma and metastasis, stand as prominent contributors to cancer mortality. Much of the data from abdominal computed tomography images remain underused by radiologists. This study explores the application of machine learning in differentiating tumor tissue from healthy liver tissue using radiomics features. Preoperative contrast-enhanced images of 94 patients were used. A total of 1686 features classified as first-order, second-order, higher-order, and shape statistics were extracted from the regions of interest of each patient’s imaging data. Then, the variance threshold, the selection of statistically significant variables using the Student’s t-test, and lasso regression were used for feature selection. Six classifiers were used to identify tumor and non-tumor liver tissue, including random forest, support vector machines, naive Bayes, adaptive boosting, extreme gradient boosting, and logistic regression. Grid search was used as a hyperparameter tuning technique, and a 10-fold cross-validation procedure was applied. The area under the receiver operating curve (AUROC) assessed the performance. The AUROC scores varied from (Formula presented.) to (Formula presented.), with naive Bayes achieving the best score. The radiomics features extracted were classified with a good score, and the radiomics signature enabled a prognostic biomarker for hepatic tumor screening.
AB - Liver malignancies, particularly hepatocellular carcinoma and metastasis, stand as prominent contributors to cancer mortality. Much of the data from abdominal computed tomography images remain underused by radiologists. This study explores the application of machine learning in differentiating tumor tissue from healthy liver tissue using radiomics features. Preoperative contrast-enhanced images of 94 patients were used. A total of 1686 features classified as first-order, second-order, higher-order, and shape statistics were extracted from the regions of interest of each patient’s imaging data. Then, the variance threshold, the selection of statistically significant variables using the Student’s t-test, and lasso regression were used for feature selection. Six classifiers were used to identify tumor and non-tumor liver tissue, including random forest, support vector machines, naive Bayes, adaptive boosting, extreme gradient boosting, and logistic regression. Grid search was used as a hyperparameter tuning technique, and a 10-fold cross-validation procedure was applied. The area under the receiver operating curve (AUROC) assessed the performance. The AUROC scores varied from (Formula presented.) to (Formula presented.), with naive Bayes achieving the best score. The radiomics features extracted were classified with a good score, and the radiomics signature enabled a prognostic biomarker for hepatic tumor screening.
KW - classification
KW - hepatocellular carcinoma
KW - liver lesions
KW - machine learning
KW - metastasis
KW - radiomic features
UR - http://www.scopus.com/inward/record.url?scp=85188722402&partnerID=8YFLogxK
U2 - 10.3390/cancers16061158
DO - 10.3390/cancers16061158
M3 - Article
AN - SCOPUS:85188722402
SN - 2072-6694
VL - 16
JO - Cancers
JF - Cancers
IS - 6
M1 - 1158
ER -