Convolutional Neural Networks for Optical Discrimination Between Histological Types of Colorectal Polyps Based on White Light Endoscopic Images.

The objective of this study was to compare different convolutional neural networks (CNNs), as employed in a Python-produced deep learning process, used on white light images of colorectal polyps acquired during the process of a colonoscopy, in order to estimate the accuracy of the optical recognition of particular histologic types of polyps. The TensorFlow framework was used for Inception V3, ResNet50, DenseNet121, and NasNetLarge, which were trained with 924 images, drawn from 86 patients.

Predictive Value of Preoperative Endoscopic Ultrasound (EUS) After Neoadjuvant Chemotherapy in Locally Advanced Esophagogastric Cancer - Data From a Randomized German Phase II Trial.

Purpose: The role of EUS before or after neoadjuvant chemotherapy (nCTX) in advanced esophagogastric cancer (EGC) is still unclear. The phase II NEOPECX trial evaluated perioperative chemotherapy with or without panitumumab in this setting. The aim of this sub-study was to investigate the prognostic value of EUS-guided preoperative staging before and after nCTX.

Outcomes in patients receiving palliative chemotherapy for advanced biliary tract cancer.

Background & Aims: Advanced biliary tract cancer (ABTC) is associated with a poor prognosis. Real-world data on the outcome of patients with ABTC undergoing sequential chemotherapies remain scarce, and little is known about treatment options beyond the established first- and second-line treatments with gemcitabine + cisplatin and FOLFOX. This study aimed to evaluate the outcome of patients with regard to different oncological therapies and to identify prognostic factors.