Integrating Clinical Data and Attentional CT Imaging Features for Esophageal Fistula Prediction in Esophageal Cancer

Background and PurposeThis study aims to develop a risk model to predict esophageal fistula in esophageal cancer (EC) patients by learning from both clinical data and computerized tomography (CT) radiomic features.Materials and MethodsIn this retrospective study, computerized tomography (CT) images and clinical data of 186 esophageal fistula patients and 372 controls (1:2 matched by the diagnosis time of EC, sex, marriage, and race) were collected. All patients had esophageal cancer and did not receive esophageal surgery. 70% patients were assigned into training set randomly and 30% into validation set. We firstly use a novel attentional convolutional neural network for radiographic descriptor extraction from nine views of planes of contextual CT, segmented tumor and neighboring structures. Then clinical factors including general, diagnostic, pathologic, therapeutic and hematological parameters are fed into neural network for high-level latent representation. The radiographic descriptors and latent clinical factor representations are finally associated by a fully connected layer for patient level risk prediction using SoftMax classifier.Results512 deep radiographic features and 32 clinical features were extracted. The integrative deep learning model achieved C-index of 0.901, sensitivity of 0.835, and specificity of 0.918 on validation set with superior performance than non-integrative model using CT imaging alone (C-index = 0.857) or clinical data alone (C-index = 0.780).ConclusionThe integration of radiomic descriptors from CT and clinical data significantly improved the esophageal fistula prediction. We suggest that this model has the potential to support individualized stratification and treatment planning for EC patients.

Clinical profile of new borns with trachea-esophageal fistula and esophageal atresia and factors associated with outcome at a tertiary care centre

Although trachea-esophageal fistula (TEF) and esophageal atresia (EA) is rare, it is one of the most common congenital anomaly. There is paucity of data due to rarity of condition. More and more data on clinical profile, complications, and outcome are needed to guide the future research. To study clinical profile of newborns with TEF and EA and factors associated with outcome.Hospital based prospective study was carried out among 21 newborns with TEF and EA. Diagnosis was confirmed by investigations like X-ray chest after passing nasogastric catheter. Depending upon final diagnosis type of surgery required was determined and procedure was carried out as per the standard guidelines and operating techniques. All cases were followed till the complete post-operative period and the complications and outcome was assessed. Outcome was classified as death or discharge.Males outnumbered females giving a male to female ratio of 2.5:1. 57.1% did not require ventilator pre-operatively. 61.9% of the cases had no associated abnormality. The most common type of surgery required and performed was tracheoesophageal repair in 52.4% of the cases. Two cases (9.5%) died during the post-operative period. 14 cases (66.7%) recovered and were discharged. Most common complication was anastomotic leak (57.1%). Term status and associated abnormalities were not found to be associated with outcome like death (p>0.05). Trachea-esophageal fistula and esophageal atresia was more common in males. Tracheoesophageal repair was commonly required surgery. Recovery rate was good. Anastomotic leak was most common complication. Outcome like death was not associated with term status and associated abnormalities.

Autopsy Techniques in Patients With History of Radiofrequency Ablation for Atrial Fibrillation

Context.— Esophageal fistula formation is one of the most feared complications of radiofrequency catheter ablation. This procedure and its many variations, such as the “maze,” are becoming the mainstream treatment for atrial fibrillation owing to limitations of antiarrhythmic drugs. The incidence of this complication rate has been reported to be from 0.01% to 1%. Objective.— To delineate the importance of using the en bloc Letulle method of dissection for identifying esophageal fistulas for cases with a history of radiofrequency catheter ablation. Design.— Six autopsy cases with a history of radiofrequency catheter ablation for atrial fibrillation were selected from 1736 autopsies performed between 2009 and 2020. Results.— The initial presenting symptoms included neurologic symptoms, chest pains, epigastric discomfort, and sepsis. Transesophageal echocardiogram of 4 cases showed no evidence of thrombus or vegetation, however, 2 cases had evidence of atrial esophageal fistula. The autopsy findings included 5 atrial esophageal fistulas and 1 esophagopericardial fistula. Atrial esophageal fistulas were small and could be detected without difficulty when the en bloc Letulle technique was used and would have been easily missed by the Virchow method. The immediate causes of the deaths were myocardial ischemia, septic emboli to brain and heart, hypovolemic shock secondary to exsanguination, stroke, and coagulopathy. Conclusions.— To date, this is the largest collection of autopsy cases showing esophageal fistula associated with prior radiofrequency catheter ablation. The Letulle dissection method is preferable in this setting.