A student trained convolutional neural network competing with a commercial AI software and experts in organ at risk segmentation.

This retrospective, multi-centered study aimed to improve high-quality radiation treatment (RT) planning workflows by training and testing a Convolutional Neural Network (CNN) to perform auto segmentations of organs at risk (OAR) for prostate cancer (PCa) patients, specifically the bladder and rectum. The objective of this project was to develop a clinically applicable and robust artificial intelligence (AI) system to assist radiation oncologists in OAR segmentation. The CNN was trained using manual contours in CT-datasets from diagnostic Ga-PSMA-PET/CTs by a student, then validated (n = 30, PET/CTs) and tested (n = 16, planning CTs).

Isolation of β-O-4-Rich Lignin From Birch in High Yields Enabled by Continuous-Flow Supercritical Water Treatment.

The continuous flow supercritical water (scHO) treatment of Birch wood (T=372-382 °C; t=0.3-0.7 s; p=260 bar) followed by alkali extraction of lignin allowed for the isolation of lignin and lignin carbohydrate complexes (LCCs) with a high number of β-O-4 moieties in the range 29-57/100 Ar (evaluated by quantitative C NMR analysis) in yields ranging between 13-19 wt % with respect to the initial wood.

The impact of multicentric datasets for the automated tumor delineation in primary prostate cancer using convolutional neural networks on F-PSMA-1007 PET.

Purpose: Convolutional Neural Networks (CNNs) have emerged as transformative tools in the field of radiation oncology, significantly advancing the precision of contouring practices. However, the adaptability of these algorithms across diverse scanners, institutions, and imaging protocols remains a considerable obstacle. This study aims to investigate the effects of incorporating institution-specific datasets into the training regimen of CNNs to assess their generalization ability in real-world clinical environments.