4016 Background: 70% of esophageal carcinoma are unresectable at diagnosis. Despite active clinical research on the treatment of esophageal squamous cell carcinoma (ESCC), the long-term survival rate of advanced patients is still very low, with a 5-year survival rate of 30%-40%. A prospective, randomized-controlled, double-blinded, multicenter, and phase III study (NXCEL1311) was designed to investigate the efficacy and safety of nimotuzumab (anti-EGFR humanized monoclonal antibody;abbreviate,Nimo) plus concurrent chemo-radiotherapy compared with placebo plus chemo-radiotherapy in unresectable locally advanced ESCC. Methods: Unresectable locally advanced ESCC patients were randomized (1:1) to receive Nimo (400 mg, qw) or placebo in combination with concurrent chemo-radiotherapy (paclitaxel+ cisplatin+3DCRT/IMRT) for seven weeks. Patients were followed for five years.The primary endpoints were OS, and the secondary endpoints included ORR, DCR, PFS. Results: 200 patients were assigned to the Nimo group (n = 99) or placebo group (n = 101). An interim analysis was conducted for short term efficacy, i.e secondary endpoints (ORR, DCR) and safety, after completing the 6 months follow-up. The OS events are not enough for analysis. The two groups were comparable on baseline characteristics. Eighty patients in the Nimo group and eighty-two patients in the placebo group were evaluable. The ORR of the Nimo group (75/80, 93.8%) was significantly higher than the placebo group (59/82, 72.0%;Chi-square test, p < 0.001). Twenty-six patients in the Nimo group reached the complete response (CR), and ten placebo group patients were CR. The CR rate in the Nimo group was significantly higher than placebo group (32.5% vs.12.2%, p = 0.002). The DCR of the Nimo group and placebo group were 98.8% (79/80) and 91.5% (75/82), respectively (p = 0.064). Single factor logistic aggression analysis showed that age, sex, target lesion number, and BMI did not affect ORR, CR, and DCR (p > 0.05). Multiple factor correction analysis showed the difference of CR, ORR and DCR between two groups is 20% (95%CI 6.0%̃40.2%), 30% (95%CI 10.6%̃52.1%) and 10% (95%CI -5.2%̃31.1%). The incidence of grade 3-5 drug-related AEs was 11.1%vs.10.9% (p > 0.05). Common drug-related AEs in patients with Nimo plus chemo-radiotherapy treatment were leucopenia, neutrophilic granulocytopenia, thrombocytopenia, hemoglobin, bone marrow inhibition, nutritional anemia, and radioactive inflammation. Conclusions: This interim analysis showed that nimotuzumab in combination with chemo-radiotherapy is safe and can increase the CRR and ORR of the treated patients. The OS needs to be followed and finally analyzed. Clinical trial information: 02409186.

PurposeThe aim of this study was to propose and evaluate a novel three-dimensional (3D) V-Net and two-dimensional (2D) U-Net mixed (VUMix-Net) architecture for a fully automatic and accurate gross tumor volume (GTV) in esophageal cancer (EC)–delineated contours.MethodsWe collected the computed tomography (CT) scans of 215 EC patients. 3D V-Net, 2D U-Net, and VUMix-Net were developed and further applied simultaneously to delineate GTVs. The Dice similarity coefficient (DSC) and 95th-percentile Hausdorff distance (95HD) were used as quantitative metrics to evaluate the performance of the three models in ECs from different segments. The CT data of 20 patients were randomly selected as the ground truth (GT) masks, and the corresponding delineation results were generated by artificial intelligence (AI). Score differences between the two groups (GT versus AI) and the evaluation consistency were compared.ResultsIn all patients, there was a significant difference in the 2D DSCs from U-Net, V-Net, and VUMix-Net (p=0.01). In addition, VUMix-Net showed achieved better 3D-DSC and 95HD values. There was a significant difference among the 3D-DSC (mean ± STD) and 95HD values for upper-, middle-, and lower-segment EC (p&lt;0.001), and the middle EC values were the best. In middle-segment EC, VUMix-Net achieved the highest 2D-DSC values (p&lt;0.001) and lowest 95HD values (p=0.044).ConclusionThe new model (VUMix-Net) showed certain advantages in delineating the GTVs of EC. Additionally, it can generate the GTVs of EC that meet clinical requirements and have the same quality as human-generated contours. The system demonstrated the best performance for the ECs of the middle segment.