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

Abstract

ObjectiveTo build and assess a pre-treatment dual-energy CT-based clinical-radiomics nomogram for the individualized prediction of clinical response to systemic chemotherapy in advanced gastric cancer (AGC).MethodsA total of 69 pathologically confirmed AGC patients who underwent dual-energy CT before systemic chemotherapy were enrolled from two centers in this retrospective study. Treatment response was determined with follow-up CT according to the RECIST standard. Quantitative radiomics metrics of the primary lesion were extracted from three sets of monochromatic images (40, 70, and 100 keV) at venous phase. Univariate analysis and least absolute shrinkage and selection operator (LASSO) were used to select the most relevant radiomics features. Multivariable logistic regression was performed to establish a clinical model, three monochromatic radiomics models, and a combined multi-energy 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.ResultAmong the included patients, 24 responded to the systemic chemotherapy. Clinical stage and the iodine concentration (IC) of the tumor were significant clinical predictors of chemotherapy response (all p < 0.05). The multi-energy radiomics model showed a higher predictive capability (AUC = 0.914) than two monochromatic radiomics models and the clinical model (AUC: 40 keV = 0.747, 70 keV = 0.793, clinical = 0.775); however, the predictive accuracy of the 100-keV model (AUC: 0.881) was not statistically different (p = 0.221). The clinical-radiomics nomogram integrating the multi-energy radiomics signature with IC value and clinical stage 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.ConclusionThe 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.

Response Evaluation after Neoadjuvant Chemotherapy for Resectable Gastric Cancer

“…A further shortcoming resides in the low sensitivity of CT to detect peritoneal carcinomatosis [ 40 ]. Of the 10,000 patients constituting the evidence base for RECIST, no trials on gastric cancer patients or NAC were included [ 41 ]; still, the method is persistently used for this purpose even today [ 27 , 28 , 42 ]. We argue that this inappropriate use should be abandoned.…”

“…The first is quantifying the response by measuring any change in tumor size, with the response evaluation criteria in solid tumors (RECIST) being the most frequently used tool [ 13 ]. This method was designed for evaluating solid tumors in a non-curative setting, but it is frequently encountered in scientific reporting on the response to NAC in gastric cancer [ 9 , 25 , 26 , 27 , 28 , 29 ]. It is of great importance to disclose any limitations of downsizing as a concept of the response to NAC in a Western cohort of resectable gastric cancers.…”

Native T1 Mapping-Based Radiomics for Noninvasive Prediction of the Therapeutic Effect of Pulmonary Arterial Hypertension

“…The innovative radiomics method allows for extracting a lot of information hidden in imaging and utilizing machine learning algorithms to build models to assist in the prediction of important clinical outcomes. Prior studies reported that radiomics might facilitate the prediction of the treatment response in several disease entities, such as hepatocellular carcinoma, pancreatic cancer, rectal cancer and gastric cancer [ 24 , 25 , 26 , 27 ]. As for the application of radiomics in cardiology, the study conducted by Son et al [ 22 ] revealed that a native T1 radiomics model could differentiate thrombi from tumors better than the mean T1 value (AUC 0.98 vs. 0.86).…”

Development and validation of a radiomic nomogram based on pretherapy dual-energy CT for distinguishing adenocarcinoma from squamous cell carcinoma of the lung

“…Recently, some researchers have demonstrated in their studies that radiomic models based on multi-energy images can more effectively support the diagnosis and prediction of tumors compared with clinical and monoenergetic models As demonstrated by Liu et al. ( 19 ), the radiomics model based on multi-energy images can better predict the clinical response of systemic chemotherapy in advanced gastric cancer (AGC) compared to clinical and monoenergetic models. This study extracts the radiomics features from DECT multi-energy images and jointly constructs the model, which proves that the image radiomics features extracted from DECT multi-energy images can reflect the heterogeneity of NSCLC.…”

“…To further explore the additional value of the DECT image, some studies combine DECT with radiomics. Liu et al (19) built and evaluated a pretherapy dual-energy CT-based clinicalradiomics model that can effectively predict the clinical response to systemic chemotherapy in patients with advanced gastric cancer (AGC). However, to our knowledge, the application and potential advantages of DECT-based radiomics in predicting the pathological subtypes of NSCLC have not been explored.…”