An approach based on Fourier descriptors and decision trees to perform presumptive diagnosis of esophagitis for educational purposes

According to World Cancer Research Fund International the esophageal cancer is the eighth most common malignancy and the sixth most common cause of cancer-related death in the world. This disease can be originated by various causes, being the Barrett's esophagus his previous stage. The Barrett's esophagus is present in several cases of patients suffering from gastric reflux. Therefore, it is fundamental to have tools able to detect the earlier stages of esophageal cancer (esophagitis). On those grounds, in this paper we propose a method that allows detecting the esophagitis using an approach based on the analysis of esophageal irregularities (the Z-line). In order to analyze these irregularities, we have applied the Fourier transform on shape signature of the Z-line. With the aim of validate the proposed method, we have used K Nearest Neighbor criterion and Random Forest on a database consisting on 26 real cases of patients (10 healthy and 16 suffering from the disease). The results are promising in terms of precision, sensitivity, and specificity (0.81, 0.86 and 0.72, respectively).