Esophageal cancer is a common malignant tumor in daily life, which seriously affects human health. Esophageal cancer in China. The incidence rate is among the highest in the world, and there are a large number of new cases of esophageal cancer every year. At present, the diagnosis of esophageal cancer is mainly based on the use of electronic gastroscopy, which reflects the observed situation on the fluorescent screen and conducts detection through the fluorescent screen. With the increasing number of patients, the pressure and intensity of the doctor's work are getting greater and greater[1]. From the perspective of molecular level, the occurrence and development of esophageal cancer, like other cancers, are related to the activation of proto-oncogenes and the inhibition of anti-apoptosis genes. CBAM Faster R-CNN is proposed to solve the problems such as the esophageal region is not obvious and the background region occupies a large proportion in the feature map obtained by the backbone network of Faster R-CNN in barium meal imaging. CBAM is added to the convolutional attention module CBAM on the basis of the original Faster R-CNN model. To enhance the saliency of the features of the esophageal region in the feature map. CBAM Faster R-CNN model was used to train the training set after data enhancement, and Recall, Precision and AP values were used for evaluation and analysis.