Search

Hilar cholangiocellular carcinoma (CCC) is a malignant neoplasm of epithelial origin occurring at the confluence of the right and left hepatic bile ducts. Typically, these tumors are small, poorly differentiated, exhibit aggressive biologic behavior with non-specific symptoms and tend to obstruct the intrahepatic bile ducts. Surgery is the only available curative option. Unfortunately, in less than half of the patients a complete resection is possible with poor survival rate in unresectable cases. In this report, we present the case of a 58-year-old woman with a history of unresectable hilar cholangiocarcinoma. Initially she was treated with intraductal dilatation of malignancy and placement of a plastic stent and chemotherapy (Gemcitabin® and Platinol®). Two years later she underwent a second-line chemotherapy with Gemcitabin® and Oxyplatin® because of tumor progression. Despite a second line chemotherapy and placement of an uncovered self-expandible metal stent (ucSEMS) that was extended later on by stent-in stent technique, there was tumor progression which led to a complex course with relapsing obstructive cholangiosepsis and cholestasis. Because of tumor ingrowth, endobiliary radiofrequency ablation of the malignant stenosis was performed in repeated sessions. This case illustrates that radiofrequency ablation of solitary malignant biliary obstruction is feasible, safe and allows an improvement of quality of life in non-operable patients.

International audience; Early attempts on imitating human driving behavior with deep learning have been implemented in an reactive navigation scheme which is to directly map the sensory measurement to control signal. Although this approach has successfully delivered the first half of the driving task-predicting steering angles, learning vehicle speed in an end-to-end setting requires significantly large and complex networks as well as the accompanying dataset. Motivated by the rich literature in trajectory planning which timestamps a geometrical path under some dynamic constraints to provide the corresponding velocity profile, we propose an end-to-end architecture for generating a non-parametric path given an image of the environment in front of a vehicle. The level of accuracy of the resulting path is 70%. The first and foremost benefit of our approach is the ability of incorporating deep learning into the navigation pipeline. This is desirable because the neural network can ease the hardness of developing the see-think-act scheme, while the trajectory planning at the end adds a level of safety to the final output by ensuring it obeys static and dynamic constraint.