The MRI radiomics signature can predict the pathologic response to neoadjuvant chemotherapy in locally advanced esophageal squamous cell carcinoma.

OBJECTIVES: To investigate the MRI radiomics signatures in predicting pathologic response among patients with locally advanced esophageal squamous cell carcinoma (ESCC), who received neoadjuvant chemotherapy (NACT). METHODS: Patients who underwent NACT from March 2015 to October 2019 were prospectively included. Each patient underwent esophageal MR scanning within one week before NACT and within 2-3 weeks after completion of NACT, prior to surgery. Radiomics features extracted from T2-TSE-BLADE were randomly split into the training and validation sets at a ratio of 7:3. According to the progressive tumor regression grade (TRG), patients were stratified into two groups: good responders (GR, TRG 0 + 1) and poor responders (non-GR, TRG 2 + 3). We constructed the Pre/Post-NACT model (Pre/Post-model) and the Delta-NACT model (Delta-model). Kruskal-Wallis was used to select features, logistic regression was used to develop the final model. RESULTS: A total of 108 ESCC patients were included, and 3/2/4 out of 107 radiomics features were selected for constructing the Pre/Post/Delta-model, respectively. The selected radiomics features were statistically different between GR and non-GR groups. The highest area under the curve (AUC) was for the Delta-model, which reached 0.851 in the training set and 0.831 in the validation set. Among the three models, Pre-model showed the poorest performance in the training and validation sets (AUC, 0.466 and 0.596), and the Post-model showed better performance than the Pre-model in the training and validation sets (AUC, 0.753 and 0.781). CONCLUSIONS: MRI-based radiomics models can predict the pathological response after NACT in ESCC patients, with the Delta-model exhibiting optimal predictive efficacy. CLINICAL RELEVANCE STATEMENT: MRI radiomics features could be used as a useful tool for predicting the efficacy of neoadjuvant chemotherapy in esophageal carcinoma patients, especially in selecting responders among those patients who may be candidates to benefit from neoadjuvant chemotherapy. KEY POINTS: • The MRI radiomics features based on T2WI-TSE-BLADE could potentially predict the pathologic response to NACT among ESCC patients. • The Delta-model exhibited the best predictive ability for pathologic response, followed by the Post-model, which similarly had better predictive ability, while the Pre-model performed less well in predicting TRG.

MR imaging characteristics of different pathologic subtypes of esophageal carcinoma.

OBJECTIVES: To describe the specific MRI characteristics of different pathologic subtypes of esophageal carcinoma (EC) METHODS: This prospective study included EC patients who underwent esophageal MRI and esophagectomy between April 2015 and October 2021. Pathomorphological characteristics of EC such as localized type (LT), ulcerative type (UT), protruding type (PT), and infiltrative type (IT) were assessed by two radiologists relying on the imaging characteristics of tumor, especially the specific imaging findings on the continuity of the mucosa overlying the tumor, the opposing mucosa, mucosa linear thickening, and transmural growth pattern. Intraclass correlation coefficients (ICC) were calculated for the consistency between two readers. The associations of imaging characteristics with different pathologic subtypes were assessed using multilogistic regression model (MLR). RESULTS: A total of 201 patients were identified on histopathology with a high inter-reader agreement (ICC = 0.991). LT showed intact mucosa overlying the tumor. IT showed transmural growth pattern extending from the mucosa to the adventitia and a "sandwich" appearance. The remaining normal mucosa on the opposing side was linear and nodular in UT. PT showed correlation with T1 staging and grade 1; IT showed correlation with T3 staging and grades 2-3. Four MLR models showed high predictive performance on the test set with AUCs of 0.94 (LT), 0.87 (PT), 0.96 (IT), and 0.97 (UT), respectively, and the predictors that contributed most to the models matched the four specific characteristics. CONCLUSIONS: Different pathologic subtypes of EC displayed specific MR imaging characteristics, which could help predict T staging and the degree of pathological differentiation. CLINICAL RELEVANCE STATEMENT: Different pathologic subtypes of esophageal carcinoma displayed specific MR imaging characteristics, which correspond to differences in the degree of differentiation, T staging, and sensitivity to radiotherapy, and could also be one of the predictive factors of cause-specific survival and local progression-free rates. KEY POINTS: Different types of EC had different characteristics on MR images. A total of 91/95 (96%) LTEC showed intact mucosa over the tumor, while masses or nodules are specific to PTEC; 21/27 (78%) ITEC showed a "sandwich" sign; and 33/35 (60%) UTEC showed linear and nodular opposing mucosa. In the association of tumor type with degree of differentiation and T staging, PTEC was predominantly associated with T1 and grade 1, and ITEC was associated with T3 and grades 2-3, while LTEC and UECT were likewise primarily linked with T2-3 and grades 2-3.

Aorta and tracheobronchial invasion in esophageal cancer: comparing diagnostic performance of 3.0-T MRI and CT.

OBJECTIVES: To compare between the diagnostic performance of 3.0-T MRI and CT for aorta and tracheobronchial invasion in patients with esophageal cancer (EC). METHODS: We prospectively included patients with pathologically confirmed EC from November 2018 to June 2021, who had baseline stage of T3-4N0-2M0 and restaging after neoadjuvant chemotherapy. All patients underwent contrast-enhanced CT and MRI of the thorax. Two independent blinded radiologists scored image quality and the presence of invasion. Agreements between the two readers were calculated using kappa test. The sensitivity, specificity, accuracy, positive predict value (PPV), and negative predict value (NPV) of MRI and CT in evaluating invasion were calculated. The net reclassification index (NRI) was used to evaluate the change in the number of patients correctly classified by MRI and CT. RESULTS: A total of 70 patients (64.8 ± 9.0 years; 53 men) were enrolled. Inter-reader agreements of image quality scores and presence of invasion by MRI and CT between the two readers were almost perfect (kappa > 0.80). The accuracy of MRI in evaluating thoracic aorta invasion was significantly higher than that of CT (reader 1: 90.0% vs. 71.4%; reader 2: 92.9% vs. 70.0%, respectively), and the accuracy of MRI in evaluating tracheobronchial invasion also was significantly higher than that of CT (reader 1: 92.9% vs. 72.9%; reader 2: 95.7% vs. 70.0%, respectively). NRI values were positive in both the evaluation of aorta and tracheobronchial invasion. CONCLUSIONS: The accuracy of 3-T MRI in determining thoracic aorta and tracheobronchial invasion is significantly higher than that of CT. KEY POINTS: • 3.0-T MRI was significantly more accurate than CT in assessing invasion of the thoracic aorta in patients with esophageal cancer. • 3.0-T MRI was also significantly more accurate than CT in assessing tracheobronchial invasion in patients with esophageal cancer. • 3.0-T MRI has a higher diagnostic performance than CT in evaluating patients with suspected aortic or tracheobronchial invasion in esophageal cancer.

Development and validation of MRI-based radiomics signatures models for prediction of disease-free survival and overall survival in patients with esophageal squamous cell carcinoma.

OBJECTIVES: To develop and validate an optimal model based on the 1-mm-isotropic-3D contrast-enhanced StarVIBE MRI sequence combined with clinical risk factors for predicting survival in patients with esophageal squamous cell carcinoma (ESCC). METHODS: Patients with ESCC at our institution from 2015 to 2017 participated in this retrospective study based on prospectively acquired data, and were randomly assigned to training and validation groups at a ratio of 7:3. Random survival forest (RSF) and variable hunting methods were used to screen for radiomics features and LASSO-Cox regression analysis was used to build three models, including clinical only, radiomics only and combined clinical and radiomics models, which were evaluated by concordance index (CI) and calibration curve. Nomograms and decision curve analysis (DCA) were used to display intuitive prediction information. RESULTS: Seven radiomics features were selected from 434 patients, combined with clinical features that were statistically significant to construct the predictive models of disease-free survival (DFS) and overall survival (OS). The combined model showed the highest performance in both training and validation groups for predicting DFS ([CI], 0.714, 0.729) and OS ([CI], 0.730, 0.712). DCA showed that the net benefit of the combined model and of the clinical model is significantly greater than that of the radiomics model alone at different threshold probabilities. CONCLUSIONS: We demonstrated that a combined predictive model based on MR Rad-S and clinical risk factors had better predictive efficacy than the radiomics models alone for patients with ESCC. KEY POINTS: • Magnetic resonance-based radiomics features combined with clinical risk factors can predict survival in patients with ESCC. • The radiomics nomogram can be used clinically to predict patient recurrence, DFS, and OS. • Magnetic resonance imaging is highly reproducible in visualizing lesions and contouring the whole tumor.