TY - JOUR
T1 - Prediction of Response of Hepatocellular Carcinoma to Radioembolization
T2 - Machine Learning Using Preprocedural Clinical Factors and MR Imaging Radiomics
AU - İnce, Okan
AU - Önder, Hakan
AU - Gencturk, Mehmet
AU - Cebeci, Hakan
AU - Golzarian, Jafar
AU - Young, Shamar J
N1 - Publisher Copyright:
© 2022 SIR
PY - 2023/2
Y1 - 2023/2
N2 - Purpose: To create and evaluate the ability of machine learning–based models with clinicoradiomic features to predict radiologic response after transarterial radioembolization (TARE). Materials and Methods: 82 treatment-naïve patients (65 responders and 17 nonresponders; median age: 65 years; interquartile range: 11) who underwent selective TARE were included. Treatment responses were evaluated using the European Association for the Study of the Liver criteria at 3-month follow-up. Laboratory, clinical, and procedural information were collected. Radiomic features were extracted from pretreatment contrast-enhanced T1-weighted magnetic resonance images obtained within 3 months before TARE. Feature selection consisted of intraclass correlation, followed by Pearson correlation analysis and finally, sequential feature selection algorithm. Support vector machine, logistic regression, random forest, and LightGBM models were created with both clinicoradiomic features and clinical features alone. Performance metrics were calculated with a nested 5-fold cross-validation technique. The performances of the models were compared by Wilcoxon signed-rank and Friedman tests. Results: In total, 1,128 features were extracted. The feature selection process resulted in 12 features (8 radiomic and 4 clinical features) being included in the final analysis. The area under the receiver operating characteristic curve values from the support vector machine, logistic regression, random forest, and LightGBM models were 0.94, 0.94, 0.88, and 0.92 with clinicoradiomic features and 0.82, 0.83, 0.82, and 0.83 with clinical features alone, respectively. All models exhibited significantly higher performances when radiomic features were included (P = .028, .028, .043, and .028, respectively). Conclusions: Based on clinical and imaging-based information before treatment, machine learning–based clinicoradiomic models demonstrated potential to predict response to TARE.
AB - Purpose: To create and evaluate the ability of machine learning–based models with clinicoradiomic features to predict radiologic response after transarterial radioembolization (TARE). Materials and Methods: 82 treatment-naïve patients (65 responders and 17 nonresponders; median age: 65 years; interquartile range: 11) who underwent selective TARE were included. Treatment responses were evaluated using the European Association for the Study of the Liver criteria at 3-month follow-up. Laboratory, clinical, and procedural information were collected. Radiomic features were extracted from pretreatment contrast-enhanced T1-weighted magnetic resonance images obtained within 3 months before TARE. Feature selection consisted of intraclass correlation, followed by Pearson correlation analysis and finally, sequential feature selection algorithm. Support vector machine, logistic regression, random forest, and LightGBM models were created with both clinicoradiomic features and clinical features alone. Performance metrics were calculated with a nested 5-fold cross-validation technique. The performances of the models were compared by Wilcoxon signed-rank and Friedman tests. Results: In total, 1,128 features were extracted. The feature selection process resulted in 12 features (8 radiomic and 4 clinical features) being included in the final analysis. The area under the receiver operating characteristic curve values from the support vector machine, logistic regression, random forest, and LightGBM models were 0.94, 0.94, 0.88, and 0.92 with clinicoradiomic features and 0.82, 0.83, 0.82, and 0.83 with clinical features alone, respectively. All models exhibited significantly higher performances when radiomic features were included (P = .028, .028, .043, and .028, respectively). Conclusions: Based on clinical and imaging-based information before treatment, machine learning–based clinicoradiomic models demonstrated potential to predict response to TARE.
UR - http://www.scopus.com/inward/record.url?scp=85145679321&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85145679321&partnerID=8YFLogxK
U2 - 10.1016/j.jvir.2022.11.004
DO - 10.1016/j.jvir.2022.11.004
M3 - Article
C2 - 36384224
AN - SCOPUS:85145679321
SN - 1051-0443
VL - 34
SP - 235-243.e3
JO - Journal of Vascular and Interventional Radiology
JF - Journal of Vascular and Interventional Radiology
IS - 2
ER -