AUTHOR=Liu Yi-yang , Zhang Huan , Wang Lan , Lin Shu-shen , Lu Hao , Liang He-jun , Liang Pan , Li Jun , Lv Pei-jie , Gao Jian-bo 

TITLE=Predicting Response to Systemic Chemotherapy for Advanced Gastric Cancer Using Pre-Treatment Dual-Energy CT Radiomics: A Pilot Study

JOURNAL=Frontiers in Oncology

VOLUME=Volume 11 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2021.740732

DOI=10.3389/fonc.2021.740732

ISSN=2234-943X

ABSTRACT=Objective: To build and assess a pre-treatment dual-energy CT (DECT)–based clinical-radiomics nomogram for the individualized prediction of clinical response to systemic chemotherapy in advanced gastric cancer (AGC).
Methods: A total of 69 patients with pathologically confirmed AGC were enrolled from two centers in this retrospective study.  Patients underwent DECT before receiving systemic chemotherapy.  Clinical information and quantitative DECT parameters were collected.  The quantitative radiomics metrics of the primary lesion were extracted from three mono-energetic levels (40keV, 70keV and 100keV) at venous phase.  Univariate analysis and least absolute shrinkage and selection operator (LASSO) was used to select the most relevant radiomics features.  Multivariable logistic regression was performed to establish clinical model, radiomics model included three single-energy levels and a multi-energy levels model.  ROC analysis and Delong test were used to evaluate and compare the predictive performance among models.  A clinical-radiomics nomogram was developed; moreover, its discrimination, calibration, and clinical usefulness were assessed.
Result: Clinical stages and the iodine concentration (IC) of the tumor were significant clinical predictors of chemotherapy response (all p <.05).  The multi-energy level radiomics model showed a higher predictive accuracy (AUC: 0.914) than those single-energy level radiomics model and clinical model (AUC: 40keV: 0.747, 70keV: 0.793, clinical: 0.775).  However, the predictive accuracy of the 100keV model (AUC:0.881) was not significantly different from that of the multi-energy level model (p=0.221).  The clinical-radiomics nomogram integrating the multi-energy level radiomics signature with IC value and clinical staging showed good calibration and discrimination with an AUC of 0.934. Decision curve analysis proved the clinical usefulness of the nomogram and multi-energy radiomics model.
Conclusion: The pre-treatment DECT-based clinical-radiomics nomogram showed good performance in predicting clinical response to systemic chemotherapy in AGC, which may contribute to clinical decision-making and improving patient survival.